US20230385941A1 - Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof - Google Patents
Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof Download PDFInfo
- Publication number
- US20230385941A1 US20230385941A1 US18/232,011 US202318232011A US2023385941A1 US 20230385941 A1 US20230385941 A1 US 20230385941A1 US 202318232011 A US202318232011 A US 202318232011A US 2023385941 A1 US2023385941 A1 US 2023385941A1
- Authority
- US
- United States
- Prior art keywords
- flood
- cover
- measured
- measuring
- damage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005259 measurement Methods 0.000 title claims abstract description 31
- 238000012546 transfer Methods 0.000 title claims description 59
- 230000003044 adaptive effect Effects 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 230000006378 damage Effects 0.000 claims description 42
- 230000011664 signaling Effects 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 13
- 230000001419 dependent effect Effects 0.000 claims description 10
- 230000001960 triggered effect Effects 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 7
- 230000003116 impacting effect Effects 0.000 claims description 7
- 238000012876 topography Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 29
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 17
- 238000012423 maintenance Methods 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 12
- 230000007246 mechanism Effects 0.000 description 10
- 238000006424 Flood reaction Methods 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 9
- 238000013459 approach Methods 0.000 description 8
- 230000000116 mitigating effect Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000013507 mapping Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000011439 discrete element method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 230000001627 detrimental effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 241001237728 Precis Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- JTJMJGYZQZDUJJ-UHFFFAOYSA-N phencyclidine Chemical class C1CCCCN1C1(C=2C=CC=CC=2)CCCCC1 JTJMJGYZQZDUJJ-UHFFFAOYSA-N 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 206010037844 rash Diseases 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000013349 risk mitigation Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000005413 snowmelt Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/14—Rainfall or precipitation gauges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Definitions
- the field of the invention is directed towards automated systems providing parametric flood event impact cover to one or more objects based on forward-looking and/or predictive measurements of occurrences and occurrence rates of measurable physical impacts of catastrophic events, in particular measurably impacting flood events.
- the measurements related to measurands depending on the physical, location-dependent event strength, location (as geographic area-based, cell-based, event strength line based, or geographic or topographic coordinate based (as latitude and longitude)), and measured time window, in particular to measurable impacts associated with the occurrence of flood events.
- the invention is directed to automated parametric mitigation or transfer of the measured forward-looking impact to a specific object by an automated risk-transfer or risk-absorption system, where the impact e.g.
- This invention further relates to automated methods and systems for automated location-dependent recognition of flood occurrence probabilities (denoted as flood risks or flood hazards), where flood states are automatically measured or captured, and location-dependent forward-looking probability values for flood hazards are automatically forecasted (e.g. by stochastic structures or machine-learning structures), measured or generated based on the direct measuring link to the physical environment.
- the invention relates to digital, modular platforms for automated mitigation of impacted physical damages to physical objects on a certain geographic location and future time window.
- risk-transfer systems can be based on the use of the law of large numbers to precisely determine a relatively small premium amount to large numbers of objects in order to cover the occurring damages of the small numbers of impacted objects who have suffered a loss due to the event-based impact to their objects.
- flood event covers typically the numbers of impacted objects is larger than the available number of individuals interested in protecting their property/objects from the peril using risk covers, which means that most prior art insurance systems do not provide risk-transfers to occurring flood events since the probability of operating the system in a sound profit range are regarded as being remote.
- risk-transfer systems that are enabled to provide primary flood risk covers for high value homes, the underwriting and provision of such mitigation processes does not account for many flood risks.
- the lack of flood reliably automatable risk mitigation, risk-transfer and risk covering systems can be detrimental to the operation of many industrial facilities at a certain location or detrimental to local homeowners of the geographic cell concerned. Even, in many cases, the responsible may discover only after an occurring event impacting a damage that their standard damage covers, and risk-transfers do not cover damages caused by flooding. It is to be mentioned that flooding can occur due to or in the wake of various physical natural disasters, for example occurring earthquakes, landslides, tsunamis, volcanic eruptions, hurricanes, cyclones, storm surges, glacial melting, or other natural disasters. Furthermore, few risk-transfer systems provide flood damage coverage due to the hazard of flood typically being confined to a few areas. As a result, it is an unacceptable risk due to the inability to spread the risk to a wide enough group of objects in order to technically absorb the potential catastrophic nature of the hazard.
- Additional mechanisms for assessing flood risks use measured flood levels through detection chambers that assess floods based on a determined flood level measured by air-based pressure measuring devices and/or remote sensing techniques, as e.g. satellite based determination of floods. Further, the measured flood levels are used to automate signaling and triggering of cover for a physical impact, typically measured as loss or damage at the impacted object, for example by a flood damage cover payout.
- risk transfer mechanisms capture event data of occurred flood and maps data to a digital map along with data related to risk transfer of portfolio.
- the portfolio is mapped by geographic area and value so that an exposure and risk to the portfolio induced by a flood event is determined.
- Yet another mechanism for assessing flood risks by simulating movement of water in case of floods is to determine potential for water damage to surface of a structure. This mechanism provides automated expert advices relating to whether to apply flood risk-transfer/insurance for risk-exposed structure based on simulation of water movement in relation to the structure.
- Parametric insurance/cover is a type of risk-transfer that is provided to the individual based on one or more pre-agreed measure (the measuring or triggering “parameter” or “index”).
- the parametric risk cover is levelled by an adjustable degree or threshold value of a predicted risk measure based on, for example, geographic location, exposure threshold etc.
- Such values can e.g. be generated using prior art hazard mapping applications such as CatNet.
- the exemplary, proprietary hazard mapping application CatNet is a global, web-based natural hazard analysis and mapping software-based engine, which enables the user to assess and visualize natural hazard exposure for a certain location in the world.
- Such prior art data-processing engines as data-link to the application, typically comprise Application Programming Interface (API) providing access to the proprietary risk modeling structures (as e.g. Cat Server API) or any probabilistic flood modeling techniques.
- API Application Programming Interface
- a parametric expertise may be determined to tailor a product design. This may involve introducing index definition including double trigger functionalities, quoting, and pricing, combining parametric and indemnity risk-transfer. Further, parametric transfer structures may be determined using natural catastrophe (NatCaT) pricing tool for parametric damage and damage exposure cover.
- a modular computer-supported platform can be provided that provides an end-to-end solution from automated front-end and underwriting to automated natural catastrophe impact covering, e.g. by automated electronic monetary transfer.
- the platform may be used as front-end for users, for event tracking, for automated activation or electronic triggering of electronic alarm devices e.g. based on forecasted event progressing, measured and/or forecasted event impact and/or physical damage parameters, maintaining proof of loss, generating automatic claims payment, and sustaining policy administration.
- a pricing measure for a cover based on the chosen limit value (payout cover) and a measured and/or forecasted exposure value (e.g. related to the amount severity and/or extend of flooding to an area).
- the extent of flooded area is generated by assessing an Area of Interest (AOI) using automated systems such as Synthetic Aperture Radar or Drones and by dividing the area into grid cells.
- the AOI can e.g. be defined client- or user-specific.
- the grid cells cover the entire AOL Later, with using technology such as SAR, it can e.g. be determined how much of the AOI is flooded (in percent area or number of grid cells)
- the size of the grid cells can e.g. be predefined and can be different for different risk-transfer structures and user to be covered.
- the grid size can, thus, be predefined or automatically negotiated between a user and the inventive system, or it can by automatically and/or dynamically adjusted by the system based on a desired resolution within a selected area.
- the resolution can also be varied by the system e.g. in dependence to the severity of the impact in a certain area, e.g. the severity of flooding.
- the resolution can also be increased automatically and/or dynamically at the border of the affected area to achieve a more precise quantitative measure for the actual affected or impacted area.
- the flood measuring and trigger system for triggering a dynamic parametric flood impact cover for physical objects being measurably impacted by an occurrence of a flood event by using an adaptive damage-cover structure of an automated electronic damage-cover system based on physical flood event measurements
- the flood measuring and trigger system comprises a central measuring engine with a predefined data structure for capturing a geographic area to be covered, the data structure at least comprising definable area parameters capturing geographic location and/or geographic extent of said geographic area
- predefined data structure comprises grid parameters for splitting the geographic area to be covered by the spatial grid with equidistant grid cells of definable size
- the flood measuring and trigger system comprises flood detection devices and/or flood sensors for measuring an occurrence of a flood event by measuring floodings within grid cells of the spatial grid, wherein flood measuring parameters of the flood detection devices and/or flood sensors are transmitted to the central measuring engine and wherein, based on the transmitted flood measuring parameters, grid cells measured as flooded are contributing to the area measured as
- the grid cells are measured as flooded when each grid cell of the measured affected area is flooded.
- the grid cells are defined as two dimensional m ⁇ n blocks.
- the m ⁇ n blocks can e.g. be of approx. 8.72*10 ⁇ 5 radian or 0.005 ⁇ 0.005 deg allowing a good resolution of flood measurements.
- Flood determination per grid cell can e.g. be binary at the centroid. However, it can also be determined dependent on the flood depth, i.e. more refined.
- the grid cells measured as flooded can e.g. be determined using an artificial intelligence-based or machine-learning based engine, such as a neural network data processing structure, and the affected area can e.g. be measured using on-air imaging devices.
- the variant with the proposed grid-cell-based floodplain mapping is an inventive remote sensing intensive process that can e.g. be implemented all over the defined area. It can e.g. comprise a Digital Elevation Modelling (DEM) structure, with the predefined or adaptive measuring accuracy based on the selected grid size.
- DEM Digital Elevation Modelling
- the DEM structures allow the inventive system to derive the slope and terrain characteristics of the selected area. Is there a river, and if so is there a flat expanse of plain around that river?
- the inventive system can e.g. use remote sensing.
- measuring devices for aerial or space-based photography and/or LiDAR devices and Synthetic Aperture Radar (SAR) devices to produce the required high-accuracy DEMs.
- Aerial imagery can be used with multiple images to generate a DEM being captured using e.g. a plane or UAS.
- the quality of aerial imagery can e.g. be affected by lighting conditions and clouds.
- LiDAR which shoots pulses of light and records their response, is an active system. That means it is less affected by lighting conditions, but can measure through light haze and clouds.
- SAR is able to measure through clouds at any time day or night, but is one of the most complicated remote sensing systems to be integrated.
- inventive DEMs which can also be improved by other imagery sources such as satellite, or UAS imagery, features of importance can be monitored and/or detected in relation to how they relate to possible floodplains.
- the present system allows to classify land cover into many different areas of interest, such as low-lying plains, forests, sandy deltas, and urban areas, and then use those classifications to feed into the floodplain modeling structure.
- the system can e.g. also automatically identify buildings and detect where they lie within the possible floodplains, i.e. assign floodplain-related measuring parameter values. These multiple inputs create a map that shows areas where flooding is measured with a higher probability value.
- the automated mapping can also be used for predictive modelling, cover or flood impact mitigation, and flood preparation or automated alarm signaling for activation of automated alarm systems.
- the system is automated to electronically disperse payments or transfer monetary parameter values to achieve the desired automatic cover covering the physical damage or impact caused by the natural event, e.g. the flooding event.
- the payments are dispersed via an electronic payment transfer module based on the generated parametric coverage monetary pay-out parameter.
- a premium vale is automatically generated based on the selected payout coverage and the forecasted exposure measure, i.e. the forecasted probability measurand for a future time window based on the measured occurrence frequencies and strength.
- Each risk-transfer can be parameterized as an exchange of risk to cover an actual physical impact to an object for a typically monetary transfer.
- Each impact by a risk event can be realized by a claim equivalent value, which represents the variable cost factors of a risk-transfer system.
- the variable cost factor is difficult to determine compared to variable cost factors in other fields. For example, in the case of a production line, the variable costs, such as raw materials, are quite certain, which makes it easier to minimize it.
- variable cost factors are often measured to be a probabilistic distribution. Therefore, it is technically challenging to minimize it.
- Al/ML data processing structures are used to process the flood measuring data.
- linear regression and/or generalized linear model could be used for processing the measuring data and forecast the appropriate prediction parameter value for the future exposure measurands.
- the inventive AI-based underwriting measures risk measurands (i.e. the forecasted exposure probability values) with a much higher precision.
- the measuring data of the inventive system are rich compared to prior art system, as it is linked to and comprises a plurality of IoT-measuring devices.
- the inventive system is able to assess the forecasted risk measurands more precisely. Uncertainty of variable cost values diminishes for the inventive system adopting the proposed technologies. Thus, the system makes it easy to determine and optimize automatically and self-sufficiently pricing values for the risk-transfer based on the measured flood parameter values. Further, the geographic area is of unvarying landscape representative of area covered by dry land and wetland.
- the herein proposed technical loopback mechanism is especially shaped for the flood detection providing an inventive loopback flood detection method and system.
- a source maintenance end point at the flood area sends a loopback message to the target maintenance point at the central measuring engine, wherein the loopback message comprises a flow identity corresponding to one specific transmission path in a plurality of equal transmission paths to the target maintenance point.
- the target maintenance point After receiving the loopback message, the target maintenance point sends a loopback replay message to the source maintenance end point, wherein the loopback replay message comprises a flow identity corresponding to a reverse common transmission path to the source maintenance end point.
- the source maintenance end point After receiving the loopback replay message and detecting to be correct, the source maintenance end point returns an announce of successful loopback detection.
- the working mechanism of prior art loopback detection is expanded, and loopback detection can be performed on one specific path in a plurality of equal paths, thus allowing and providing high-speed transmission and detection of occurring flood by flood measurements in real-time or quasi-real-time.
- FIG. 1 is a block diagram illustrating exemplary an architecture of the inventive flood measuring and trigger system 1 and method for triggering a dynamic parametric flood impact cover for physical objects 3 / 31 being measurably impacted by an occurrence of a flood event 4 by using an adaptive damage-cover structure 1031 of an electronic damage-signaling and/or damage-cover system 103 based on physical flood event measurements.
- FIG. 2 is a schematic diagram, which exemplarily illustrates a possible overall operation of one embodiment of the method of the present invention.
- FIG. 3 is a chart, which shows a structure scheme presenting an impact of flood event.
- FIG. 4 is a chart, which shows a payout scheme used during occurrence of flood event in relation to topography and exposure distribution.
- FIG. 5 schematically illustrates an exemplary parametric risk-transfer relying on the measurement of a natural physical measuring parameter or index (parameter). Automated cover by a payout transfer given by a predefined amount is made when a predefined threshold of parameter/index is exceeded (e.g. amount of rainfall, flood at location).
- a predefined threshold of parameter/index e.g. amount of rainfall, flood at location.
- FIG. 6 schematically illustrates an exemplary parametric excess rainfall risk-transfer (as a proxy for flood).
- An aggregated amount of rolling observation window e.g. 2-days must exceed pre-defined rainfall levels. It is to be noted that rainfall ⁇ floods on the ground.
- FIG. 7 schematically illustrates an exemplary flood map generation through multi-source measuring parameter processing.
- FIG. 8 schematically illustrates an exemplary processing of flood event footprints, where satellite data are measured, an object level of a high spatial resolution up to 1 ⁇ 1 meter is achieved, daily observations with any non-permanent water for >12 hours is detected and delivered near real time, and radar technology allows monitoring through clouds and at night.
- FIG. 9 schematically illustrates an exemplary parametric flood risk-transfer structure triggered by the inventive flood measuring footprints based on maximum flood extent.
- FIG. 10 schematically illustrates an exemplary identification of critical sites or objects 3 and generating a grid over a geographic area 2 of interest at which a flood is measured.
- a flood extent mapping is provided by the system 1 within 24 hours after peak flood.
- the system 1 automatically detects if pre-determined sites were flooded. Cover with defined payout amounts for all affected sites and/or objects 3 can e.g. be provided within days, thereby optimizing financial resilience and enable an immediate response.
- FIG. 11 schematically illustrates an exemplary flood map or digital elevation map from satellite imagery classification.
- Physical objects 3 as e.g. buildings or other constructions, can e.g. be automatically located using LiDAR which, inter alia, allows the system 1 to detect how close a physical object 3 lies or within which flood zones.
- FIG. 12 shows schematically a machine-learning setup.
- the geographic area 2 is divided in 50 ⁇ 50 grid cell 1003 raster each simulated by its own machine-learning structure.
- Input layer seven input hydrographs.
- Output layer flood inundation extent in each grid 1002 and/or grid cell 1003 .
- FIG. 13 shows schematically grid cells 1003 based stream-flow measurements which can e.g. be an important measuring parameter that also impacts many other aspects as e.g. the river's hydrology and water quality.
- FIG. 14 shows schematically an exemplary flood grid 1002 measuring flood depth, where the darker areas represent greater flood depths
- FIG. 15 shows schematically exemplary dynamically adjusted grid cells 1003 , wherein the cells 1003 are chosen to be dynamically adapted by the system 1 , where areas closer to the flooding and/or river etc. are applied with a high measuring resolution than areas further away. This allows a more precise measurement of flooded areas 21 than achieved by the prior art systems.
- FIG. 16 shows schematically exemplary measurements of the geographic area 2 by satellite measurements detecting flooded grid cells 1003 and not flooded grid cells 1003 .
- the influence of clouds is eliminated by comparing and/or calibrating dry and wet measuring signals (left diagram). Water has a lower brightness temperature measured than land (right diagram).
- FIG. 17 shows schematically exemplary measurements a flood event 4 / 41 , 42 , 43 in a the geographic area 2 based on grid cell measurements.
- FIG. 1 shows an exemplary architecture for a flood measuring and trigger system 1 and an automated method for providing a dynamic parametric flood impact cover 1031 for physical objects 3 / 31 being measurably impacted by an occurrence 41 / 42 / 43 of a flood event 4 by using an adaptive damage-cover structure 1041 of a damage-cover system 104 based on physical flood event measurements.
- the flood measuring and trigger system 1 comprises a central measuring engine 10 with a predefined data structure 1005 for capturing a geographic area 2 to be covered, the data structure 1005 at least comprising definable area parameters 10041 capturing geographic location 100511 and/or geographic extent 100512 of said geographic area 2 .
- Predefined data structure 1005 comprises grid parameters 10033 for splitting the geographic area 2 to be covered by the spatial grid 1002 with equidistant or variable grid cells 1003 of definable or automatically adaptable size 10033 by means of a dynamic grid splitter 1001 .
- the grid cells 1003 can e.g. be defined as two dimensional blocks of m ⁇ n size 10033 .
- the two dimensional m ⁇ n blocks 1003 can e.g. be of approx.
- the dimensional m ⁇ n blocks 1003 can e.g. be of approx. 0.005*0.005 deg size 10033 .
- Grid shape 10034 (curvilinear/structured or triangular/unstructured) and the selected grid size 10033 affect the output of the damage signaling or damage cover system 104 .
- structured, unstructured and/or hybrid grids 1002 can be applied.
- the measuring grid cells 1003 can e.g. be realized as a digital raster dataset that defines geographic space as an array of equally or adjustably sized square cells 1003 arranged in rows and columns. The value in each cell represents the magnitude in that location of the flooding characteristic represented by that particular grid.
- grids 1002 can be produced to reflect water surface elevations and/or depths and/or velocities and/or percent-annual-chances of flooding and/or other measuring values.
- the grids 1002 can e.g. be chosen based on the topography of a geographic area 2 , e.g. being unique to coastal areas and dams.
- the grid cell resolution it should e.g. be taken into account when selecting the cell size 10033 for the grids 1002 , that the depth and measuring grid cells 1003 have an inherent relationship to the underlying topographic data used during the development of the flood hazard delineations, which can e.g. be depicted on the flood risk rate map.
- the raster cell size (resolution) 10033 of all raster datasets measured should be based on the density of the ground elevation data used and the appropriate precision that can be supported by the measurements. Normally, all the gird measuring datasets can e.g. use the same grid cell size 10033 . However, the cell size 10033 for the grids 1002 can e.g. be no larger than 3 ⁇ 3 m.
- a two dimensional horizontal modeling structure can e.g. be applied to get the detailed and accurate map of water levels and/or flood patterns and/or potential flood exposed areas.
- a two dimensional horizontal modeling structure can e.g. be applied to get the detailed and accurate map of water levels and/or flood patterns and/or potential flood exposed areas.
- also structured curvilinear grids 1002 can e.g. be used for the hydraulic forecast processing, where the curvilinear grid cells 1003 provide a precise forecast output signaling by allowing cell stretching along river main channels while orthogonality stays within reasonable bounds.
- the use of curvilinear grid cells can e.g. result in a high resolution in sharp inner bends since grid lines are focused on the bends.
- the measuring grid cells 1003 are chosen to be dynamically adapted by the system 1 (see FIG. 15 ), where areas closer to the flooding show a high resolution than areas further away. This allows a more precise measurement of flooded areas 21 than achieved by the prior art systems.
- the flood measuring and trigger system 1 comprises flood detection devices and/or flood sensors 102 for measuring an occurrence of a flood event 4 by measuring floodings within grid cells 1003 of the spatial grid 1002 , wherein flood measuring parameters 1021 of the flood detection devices and/or flood sensors 102 are transmitted to the central measuring engine 10 and wherein, based on the transmitted flood measuring parameters 1021 , grid cells 1003 measured as flooded are contributing to the area 21 measured as affected while grid cells measured as not flooded are not contributing to the area 22 measured as affected.
- the geographic area 2 can e.g. comprise surveyed landscape representative of area covered by dry land 24 and wetland 25 .
- the geographic area 2 can e.g. comprise at least parts definable as automatically excluded from the dynamic parametric flood impact cover 1031 .
- the occurrence of the flood event 4 can e.g. be detected using loopback signaling 1022 for the signaling of the flood detection devices and/or flood sensors 102 .
- the herein proposed technical loopback mechanism is especially shaped for the flood detection providing an inventive loopback flood detection method and system.
- a source maintenance end point at the flood area sends a loopback message to the target maintenance point at the central measuring engine, wherein the loopback message comprises a flow identity corresponding to one specific transmission path in a plurality of equal transmission paths to the target maintenance point.
- the target maintenance point After receiving the loopback message, the target maintenance point sends a loopback replay message to the source maintenance end point, wherein the loopback replay message comprises a flow identity corresponding to a reverse common transmission path to the source maintenance end point.
- the source maintenance end point After receiving the loopback replay message and detecting to be correct, the source maintenance end point returns an announce of successful loopback detection.
- the inventive loopback detection method the working mechanism of prior art loopback detection is expanded, and loopback detection can be performed on one specific path in a plurality of equal paths, thus allowing and providing high-speed transmission and detection of occurring flood by flood measurements in real-time or quasi-real-time.
- the present inventive measuring system 1 can e.g. in an embodiment variant also be used as flood warning system 1 .
- Monitoring is important: While some areas are more exposed to flooding than others, situating measuring devices and flood sensors 102 near waterway or body of water provides critical and precises in-loco measuring data.
- the affected area 21 can e.g. be measured using gages and telemetry equipment 1025 .
- the present inventive system 1 is based on the regular measuring of local rainfall, stream level, and streamflow data in each grid cell 1003 . This can be real-time monitoring with telemetry allowing for the fastest possible response to a flood event. It is clear that a real-time flood warning system 12 / 121 , . . . , 123 can reduce risks involved with flooding.
- the affected area 21 can e.g. be measured using at least partially air-based and/or space-based optical measuring devices 1023 / 1024 using digital image recognition processing (see FIG. 16 ).
- the present system 1 forecasts floods using the below described model structures for forecasting how rivers and streams respond to varying levels of measured rainfall and snowmelt. These forecast processing are based on already measured data records of flood level and/or stream stage and/or discharge, the generation for which are outlined below.
- the gages perform two primary tasks: sensing and communicating.
- the gages employs sensors to detect changes to measuring parameters, e.g. precipitation volume and/or water level.
- the used gages may also be equipped with temperature and wind speed sensors. Some gages can also provide site-specific measuring data regarding the health or technical status of the measuring unit.
- the gage can e.g. be designed to detect a particular “event”, e.g. 1 millimeter of rainwater entering the gage's tipping bucket through the top of its funnel. When the bucket tips, it pours out any water within, engaging a switch that transmits alert data and resetting the bucket. Any other sensors on the gage will also activate the alert data transmitter after detecting said specific event. On days without rain, the gages can e.g. transmit a “no rain” report to show that the device 102 is still working. In the embodiment variant with automated flood warning 12 / 121 , 122 , 123 the system 1 can e.g.
- the system 1 can also specifically operate alarm signals using radio frequencies and/or satellite and/or cellular telemetry.
- stream-flow can e.g. be an important measuring parameter that impacts many other aspects of a river's hydrology and water quality (see FIG. 13 ).
- the grid cells 1003 measured as flooded 10031 can e.g. be determined using at least an artificial intelligence based data-processing structure and/or a machine-learning-based data-processing structure.
- the present inventive system generally can also be operated applying one or more types of numerical modeling structures for predictive flood parameter generation.
- a hydrological rainfall run-off modeling structure can e.g. be used to forecast distributed river discharges.
- a one-dimensional (1D) drainage modeling structure can e.g. be applied based on the one-dimensional Saint-Venant flow forecasting to predict surcharges or drainages.
- a two-dimensional (2D) Saint-Venant flow forecast can e.g.
- a 1D-2D coupling structure can be applied. All proposed embodiment variant relies on sensory and/or field measurements for capturing the inventive input parameters and their specific technical selection. However in a preferred embodiment variant, the system relies on a data-driven approach for establish a reliable flood forecast structure based on flood measurements. Unlike the numerical structure, the inventive data-driven, physical-based measuring and forecast system requires measuring input/output data only. The inventive data-driven structure has shown its high performance especially for the technical nonlinear flood forecast problems.
- ANN-based forecast structures can be applied, however the technical problem of over-fitting or under-fitting the measuring data, and insufficient length of the data sets can lead to erroneous forecast output results.
- SVM support vector machine
- ANN support vector regression and/or artificial neural network
- artificial neural network showed to be a reliable technique for the inventive flood prediction, as for forecasting water levels by applying ANN forecast structures to conventional hydrological modeling in flood-prone catchments.
- the water level forecast results along a river uses backpropagation and/or conjugate gradient and/or cascade correlation.
- One possibility is to combine a Levenberg-Marquardt Backpropagation with cross-validation to prevent the under-fitting and overfitting in daily reservoir inflow forecasting.
- the maximum flood inundation in a geographic area is determined by machine-learning based structure applying a backpropagation networks based on multiple inflow measuring data for a grid resolution of m ⁇ n.
- This ANN technique allows for a geographic area to provide high-resolution flood inundation maps from river flooding. For the prediction of maximum flood inundation, only the real-time discharges of the upstream catchments or flood level measurements are needed.
- the procession consists of two phases: the training phase collects a part of the measuring data from the existing database, tuning the model by changing the weights on input arcs to minimize the bias on the output layer; the recalling phase produces the new outputs for the testing inputs. The rest individuals in the training dataset are used for evaluating the behavior of the network structure.
- the total bias between the output of ANN and the observed values is defined as the error function.
- the weights are modified automatically by the system 1 .
- the learning rate is used for automatedly scaling the gradient in each iteration of the weight update.
- the system can be sensitive to select up the correct value, since a large learning rate can miss the optimal point, while a small learning rate can slow the training process.
- the gradient descent algorithm can be used by the system 1 to generate the update of the weights values.
- resilient backpropagation can e.g. be applied in the present case for treating the update of weight values differently depending on the derivative of the error function.
- larger alternative learning rate can e.g. be set for speeding up the iterations if the error gradient remains in the same direction in neighboring time-steps and smaller alternative learning rate when approaching the optimal weights.
- the geographic area 2 can e.g. be subdivided into 50 ⁇ 50 cell-squared grids 1002 , each grid 1002 having its own independent ANN structure (the output layer having 1400 elements). It is to be noted that with the same inventive technical approach, instead of measuring the real-time discharges of the upstream catchments for the prediction of maximum flood inundation, rainfall measurements and/or flood level measurements can be selected as input measuring values for the machine-learning-based structure. To optimize the ANN processing technically further, clustering can be applied to the training measuring dataset.
- the size of the training measuring dataset can optimize and reduced while still keeping the main representative events. As such the training time can be reduced and the overfitting effects minimized.
- the mean squared error (MSE) of each grid can e.g. be used. It is assumed that the flood maps from the events used are the observed values. As each grid 1002 has its own independent training network, the MSE can e.g. be measured using all the grid cells 1003 in each grid 1002 .
- the central measuring engine 10 comprises a flood threshold measurand 1032 , wherein the flood threshold measurand 1032 is selected from a percentage 23 of the geographic area 2 given by the area 21 measured as affected to the total geographic area 2 .
- the adaptive damage-cover structure 1041 can e.g. only be triggered if the flood threshold measurand 1032 is measured to exceed a predefined flood threshold value 1033 . In another embodiment variant, the adaptive damage-cover structure 1041 can e.g. be triggered to provide a damage cover 1031 directly dependent on the measured flood threshold measurand 1032 .
- the central measuring engine 10 comprises an electronic flood trigger 103 for triggering the adaptive damage-cover structure 1041 covering physical damages or loss associated with the measured occurrence of the flood event 4 , the occurrence measurably impacting physical objects 3 / 31 situated in the affected area 21 and/or grid cells 1011 measured as affected 10111 , wherein the adaptive damage-cover structure 1041 is adapted by the damage-cover system 104 based on the flood threshold measurand 1032 providing the dynamic parametric flood impact cover 1031 .
- the adaptive damage-cover structure 1041 of the damage-cover system 104 can e.g.
- the adaptive damage-cover structure 1041 is adapted by the damage-cover system 104 based on the flood threshold measurand 1032 transmitted by the electronic steering signals.
- the triggering the adaptive damage-cover structure 1041 for covering physical damages or loss 32 associated with the measured occurrence of the flood event 4 can e.g. comprises generating a parametric coverage 1031 based on the adaptive damage-cover structure 1041 , and transferring, by an electronic payment transfer module, based on the generated parametric coverage 1031 monetary pay-out parameter values by electronic payment transfer to cover the physical damages or loss 32 associated with the measured occurrence.
- a premium value can e.g. automatically and optimized generated based on a specific selection of the parametric flood impact cover 1031 .
- the triggering the adaptive damage-cover structure 1041 for covering physical damages or loss 32 associated with the measured occurrence of the flood event 4 can e.g. comprise generating a parametric coverage 1031 based on a cover activation signaling or electronic payout function 1046 , and transferring, by an electronic payment transfer module, based on the output of the cover activation signaling or electronic payout function 1046 a monetary pay-out by electronic payment transfer to cover the physical damages or loss 32 associated with the measured occurrence.
- the cover activation signaling or electronic payout function 1046 can e.g. comprise a linear payout function 10461 and/or a stepped payout function 10462 and/or a deductibles-based payout function 10463 .
- the cover activation signaling or electronic payout function 1046 can e.g. be selectable based on topography and/or exposure distribution.
- the cover activation signaling or electronic payout function 1046 can further e.g. be user-specific definable.
- FIG. 2 shows an exemplary schematic process of the present invention, which illustrates an overall operation of an embodiment of an automated system providing a dynamic parametric flood impact cover for an object physically impacted by the flood and/or to an individual assigned to the impacted object.
- An automated system 1 is disclosed for providing a dynamic parametric flood impact cover to flood impact exposed physical objects 3 and/or a flood risk exposed individual in case of an occurrence of a flood event 4 .
- the dynamic parametric cover 1031 is provided by using an adaptive risk-transfer structure 1041 based on physical flood event measurements.
- a trigger is generated by a trigger module and the trigger is activated upon occurrence of the flood event.
- the trigger may provide measuring data 1021 corresponding to such as flood extent, flood depth.
- FIG. 2 of the present invention The generation and measurement of measuring data 1021 related to the flood event 4 is explained in detail in conjunction with FIG. 2 of the present invention.
- FIG. 52 an embodiment variant with a payout function 1046 is shown, where the payout function 1046 is activated (at reference number 52 and triggers the payout calculation function (at reference number 53 ).
- the payout generated is dependent on occurrence of the flood event, regardless of actual loss incurred in the flooding event.
- the payout function is explained in detail in conjunction with FIG. 3 of the present application.
- an independent third party system or an electronic reporting agent or broker or a third party calculation agent, at reference number 54 determines an intensity of the flood event.
- the independent third party/reporting agent provides the information to the object 3 or exposed individual (at reference number 54 ) to initiate payout generation and automatically triggering payout transfer (at reference number 53 ) and also informs to the individual (at reference number 55 ).
- an automated module may be used to generate the payout, and automatically intimate the insured and initiate the payment.
- the exposed individual (at reference number 55 ) is the one who may purchase a cover specifying a maximum payout from the system 1 (at reference number 56 ). The maximum payout cover is based on extend of the flooded area 21 .
- the premium (at reference number 57 ) is transferred to the system (at reference number 51 ) depends on the chosen limit as well as on the area 21 affected by the flood 4 (at reference number 55 ). In one embodiment, the premium is generated using probabilistic modelling structures, upon numerous reviews.
- the trigger data may be obtained from highly reputed independent third party agency that are mutually in agreement with the individual.
- the third party agency may be, for example, use on-air imaging device such as Synthetic Aperture Radar (SAR) satellite imagery and drone based imagery that provide multiple images to capture flood depth and flood extend.
- SAR Synthetic Aperture Radar
- the automated system (at reference number 1 ) first measures an Area of Interest (AOI).
- the AOI is an extended flooded area of a total area cover of the region.
- the generated AOI is then divided into a plurality of grid cells (at reference number 1003 of a spatial grid 1002 .
- the grid cells 1003 defining the desired resolution may be determined randomly or dynamically, for example, the grid cells may be defined as two dimensional m ⁇ n blocks such as 500 m ⁇ 500n (0.005 ⁇ 0.005 deg.) blocks of approx. 8.72*10 ⁇ 5 radian.
- an affected area (AA) is determined, by calculating the number of grid cells that are totally flooded.
- the grid cells measured as flooded are determined using, for example, a neural network approach, a double grid approach, and the like.
- the grid cells measured as not flooded do not contribute to the measured affected area of the AOI.
- the percentage (at reference number 53 of affected area 21 is generated with the relation of AA/AOI.
- the payout is based on the pre-defined trigger depending upon the percentage of affected area 21 . It is to be noted that this predefined trigger can vary from risk-transfer to risk-transfer depending on specific user requirements.
- an exemplary payout structure 1046 can e.g. be used during occurrence of the flood event 2 in relation to topography and exposure distribution is shown via graph.
- the payout function can be linear 10461 (straight linear), stepped or with 10462 deductibles (franchise deductibles 10463 ).
- the automated system selects payout functions based on topography and exposure distribution.
- the payout function 1046 may cater to different terrain and exposure distribution with respect to a geographic area.
- the payout function provides different payout functions to the individual, and the individual is free to select one of the payout function.
- the payout function may further include suggestions from the individual or risk-exposed insured.
- a parametric coverage for the measured affected area 21 may be generated by covering a possible loss associated with occurrence of the flood event and impacting a geographic area measured by the affected area.
- the possible loss incurred due to occurrence of the flood event may be determined as per an adjustable risk-transfer structure, a threshold measure.
- the possible loss incurred may be triggered by a threshold-trigger that is selected from the percentage of the affected area given by the measured affected area to the geographic area (for example, the AOI).
- the geographic area may include unvarying landscape that represents area covered by dry land and wetland.
- the payout may vary from 0% to 100%.
- the measured affected area is around 75% and a limit of around USD 100 m is determined under the payout scheme.
- the insured may receive around 0.75 ⁇ USD 100 m or around USD 75 m.
- an electronic payment transfer may be made to the individual by an electronic payment transfer module.
- the electronic payment transfer may be done based on generated parametric coverage monetary pay-out parameter values.
- the electronic payment transfer to be made to the individual is limited and may be pre-defined based on prior discussion or agreement with the insured.
- the individual may provide information related to the geographic area to be excluded for coverage under the payout scheme.
- the risk-assessment parameters used to determine occurrence of the flood event may be accessed using a machine learning (ML) approach.
- the MI approach may connect flood related measurements of various geographic areas for assessing and/or predicting overall risks by a risk transfer module.
- the MI approach may be used to predict a future risk pertaining to occurrence of the flood event, and/or allowing to associate varied losses incurred in the multiple geographic areas due to occurrence of the flood event leading to generation of risk factors for an associated reinsurance module. While a number of features are described herein with respect to embodiments of the inventions; features described with respect to a given embodiment also may be employed in connection with other embodiments.
- the following description and the annexed drawings set forth certain illustrative embodiments of the inventions. These embodiments are indicative, however, of but a few of the various ways in which the principles of the inventions may be employed.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Environmental & Geological Engineering (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Hydrology & Water Resources (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Astronomy & Astrophysics (AREA)
Abstract
The invention relates to automated method and flood measuring and trigger system for providing a dynamic parametric flood impact cover for physical objects being measurably impacted by an occurrence of a flood event by using an adaptive damage-cover structure of a damage-cover system based on physical flood event measurements, wherein by flood detection devices and/or flood sensors, an occurrence of a flood event is measured by measuring floodings within the grid cells of the spatial grid, wherein flood measuring parameters of the flood detection devices and/or flood sensors are transmitted to the central measuring engine and wherein, based on the transmitted flood measuring parameters, grid cells measured as flooded are contributing to the area measured as affected while grid cells measured as not flooded are contributing to the area measured as not affected.
Description
- The present application is a continuation application of International Patent Application No. PCT/EP2022/080593, filed Nov. 2, 2022, which is based upon and claims the benefits of priority to Swiss Application No. 070500/2021, filed Nov. 3, 2021. The entire contents of all of the above applications are incorporated herein by reference.
- The field of the invention is directed towards automated systems providing parametric flood event impact cover to one or more objects based on forward-looking and/or predictive measurements of occurrences and occurrence rates of measurable physical impacts of catastrophic events, in particular measurably impacting flood events. The measurements related to measurands depending on the physical, location-dependent event strength, location (as geographic area-based, cell-based, event strength line based, or geographic or topographic coordinate based (as latitude and longitude)), and measured time window, in particular to measurable impacts associated with the occurrence of flood events. Further, the invention is directed to automated parametric mitigation or transfer of the measured forward-looking impact to a specific object by an automated risk-transfer or risk-absorption system, where the impact e.g. is measured in units of expected damage rate, percentage or other quantifying and/or measuring units associated with the measured forward-looking impact the specific object. This invention further relates to automated methods and systems for automated location-dependent recognition of flood occurrence probabilities (denoted as flood risks or flood hazards), where flood states are automatically measured or captured, and location-dependent forward-looking probability values for flood hazards are automatically forecasted (e.g. by stochastic structures or machine-learning structures), measured or generated based on the direct measuring link to the physical environment. Finally, the invention relates to digital, modular platforms for automated mitigation of impacted physical damages to physical objects on a certain geographic location and future time window.
- Today reliable automated flood impact and impact response or mitigation systems are painfully lacking. For many countries, it is hardly possible to do a technically correct flood impact occurrence rating and/or determination based on predictive forward-looking impact measures. A glance at the loss history shows that physical damages and associated losses caused by flood events are equally high or higher than those of other natural catastrophic events as earthquakes, windstorms, or other perils. For many of those other perils various prediction and/or rating and/or early warning systems based on actual measuring parameter values already exist. Large physical part of industrial facilities, industrial power and time are lost by occurring flood events having a physical impact to such objects. Additionally, with the trend of increasing risk-transfer penetration for floods, the insurance and re-insurance industry is affected ever more by hardly to measure and predict flood events causing physical damages and losses. To extend the early warning capabilities and flood damage cover, however, the threat of immense data amounts has to be coped with. One new approach is the present inventive measuring system, inter alia, allowing to extrapolate the actual physical measuring parameters to future time windows and geographic cells.
- Further, in many countries, a large number of industrial facilities and homes have a significant and measurably predictable probability (risk) for being impacted by flood events, and reasonably should be covered by flood mitigation and risk-transfer processes. However, many prior art systems are not capable to reliably hedge against the technically difficult to predict perils of flood events, inter alia, due to the prevalence of moral hazard and adverse selection phenomena, for example, in entering risk-transfers for objects most affected by the specific peril of flood. In such cases, traditional risk-transfer is not available. Whereas for other damage risks, risk-transfer systems can be based on the use of the law of large numbers to precisely determine a relatively small premium amount to large numbers of objects in order to cover the occurring damages of the small numbers of impacted objects who have suffered a loss due to the event-based impact to their objects. In flood event covers, typically the numbers of impacted objects is larger than the available number of individuals interested in protecting their property/objects from the peril using risk covers, which means that most prior art insurance systems do not provide risk-transfers to occurring flood events since the probability of operating the system in a sound profit range are regarded as being remote. Additionally, while there are risk-transfer systems that are enabled to provide primary flood risk covers for high value homes, the underwriting and provision of such mitigation processes does not account for many flood risks.
- The lack of flood reliably automatable risk mitigation, risk-transfer and risk covering systems can be detrimental to the operation of many industrial facilities at a certain location or detrimental to local homeowners of the geographic cell concerned. Even, in many cases, the responsible may discover only after an occurring event impacting a damage that their standard damage covers, and risk-transfers do not cover damages caused by flooding. It is to be mentioned that flooding can occur due to or in the wake of various physical natural disasters, for example occurring earthquakes, landslides, tsunamis, volcanic eruptions, hurricanes, cyclones, storm surges, glacial melting, or other natural disasters. Furthermore, few risk-transfer systems provide flood damage coverage due to the hazard of flood typically being confined to a few areas. As a result, it is an unacceptable risk due to the inability to spread the risk to a wide enough group of objects in order to technically absorb the potential catastrophic nature of the hazard.
- In summary, natural disasters such as floods cause severe damage in various parts of the world. The occurrence of most of such disaster events is difficult, if not impossible, to predict over the long term by prior art measuring systems. Conventional flood mitigation techniques determine, assess and estimate pricing of flood risks using parametric risk-transfer structures so as to mitigate flood risks by gathering information related to base flood elevation data, flood depth by using mitigation devices and survey information. In addition, digital marketplace techniques list online policies that guarantee a pre-agreed payout based on pre-determined parameters in case of a flood hazard. The digital marketplace techniques determine a water-elevation function factoring in high water probability data, leading to saving both risk-transfer providers' and customers' time and cost spent on building, inspection, and damage estimation. Additional mechanisms for assessing flood risks use measured flood levels through detection chambers that assess floods based on a determined flood level measured by air-based pressure measuring devices and/or remote sensing techniques, as e.g. satellite based determination of floods. Further, the measured flood levels are used to automate signaling and triggering of cover for a physical impact, typically measured as loss or damage at the impacted object, for example by a flood damage cover payout.
- Other available risk transfer mechanisms capture event data of occurred flood and maps data to a digital map along with data related to risk transfer of portfolio. The portfolio is mapped by geographic area and value so that an exposure and risk to the portfolio induced by a flood event is determined. Yet another mechanism for assessing flood risks by simulating movement of water in case of floods is to determine potential for water damage to surface of a structure. This mechanism provides automated expert advices relating to whether to apply flood risk-transfer/insurance for risk-exposed structure based on simulation of water movement in relation to the structure.
- Parametric insurance/cover is a type of risk-transfer that is provided to the individual based on one or more pre-agreed measure (the measuring or triggering “parameter” or “index”). The parametric risk cover is levelled by an adjustable degree or threshold value of a predicted risk measure based on, for example, geographic location, exposure threshold etc. Such values can e.g. be generated using prior art hazard mapping applications such as CatNet. The exemplary, proprietary hazard mapping application CatNet is a global, web-based natural hazard analysis and mapping software-based engine, which enables the user to assess and visualize natural hazard exposure for a certain location in the world. Such prior art data-processing engines, as data-link to the application, typically comprise Application Programming Interface (API) providing access to the proprietary risk modeling structures (as e.g. Cat Server API) or any probabilistic flood modeling techniques.
- Based on the degree of risk accessed, a parametric expertise may be determined to tailor a product design. This may involve introducing index definition including double trigger functionalities, quoting, and pricing, combining parametric and indemnity risk-transfer. Further, parametric transfer structures may be determined using natural catastrophe (NatCaT) pricing tool for parametric damage and damage exposure cover. In addition, based on the inventive parametric structure, a modular computer-supported platform can be provided that provides an end-to-end solution from automated front-end and underwriting to automated natural catastrophe impact covering, e.g. by automated electronic monetary transfer. The platform may be used as front-end for users, for event tracking, for automated activation or electronic triggering of electronic alarm devices e.g. based on forecasted event progressing, measured and/or forecasted event impact and/or physical damage parameters, maintaining proof of loss, generating automatic claims payment, and sustaining policy administration.
- The above-disclosed mechanisms/techniques do not discuss about providing a modular system that determines, assess and evaluate price risks that arise due to occurrence of floods. In addition, these mechanisms/techniques fail to provide parametric risk transfer structures that facilitate to mitigate the risks associated with occurrence of the floods. There is therefore a need in the art for an improved, automatable system and method for providing a customizable impact cover structure for a flood area risk based on measurable and reliable prediction and assessment of location- and time-window-dependent physical impact damage during the occurrence of flood events.
- It is one object of the present invention to provide an automated system and method for reliable forward-looking measurements and ratings of physical impacts of occurring location-dependent catastrophic events, as flood events, to a specific object, and in automated conduct and provision/generation of appropriate covers and/or hedging against the impacted damage to the specific object. It is further an object of this invention to provide a new and better automated system and method for providing a dynamic parametric cover, which does not have the above-mentioned disadvantages of the prior art. In particular, it is an object of the present invention to provide a risk-transfer cover based on an extend of a flooded area. Further it is an object, to generate a pricing measure for a cover based on the chosen limit value (payout cover) and a measured and/or forecasted exposure value (e.g. related to the amount severity and/or extend of flooding to an area). The extent of flooded area is generated by assessing an Area of Interest (AOI) using automated systems such as Synthetic Aperture Radar or Drones and by dividing the area into grid cells. The AOI can e.g. be defined client- or user-specific. Ideally the grid cells cover the entire AOL Later, with using technology such as SAR, it can e.g. be determined how much of the AOI is flooded (in percent area or number of grid cells)
- The size of the grid cells can e.g. be predefined and can be different for different risk-transfer structures and user to be covered. The grid size can, thus, be predefined or automatically negotiated between a user and the inventive system, or it can by automatically and/or dynamically adjusted by the system based on a desired resolution within a selected area. The resolution can also be varied by the system e.g. in dependence to the severity of the impact in a certain area, e.g. the severity of flooding. The resolution can also be increased automatically and/or dynamically at the border of the affected area to achieve a more precise quantitative measure for the actual affected or impacted area.
- In particular, these aims are achieved by the inventive flood measuring and trigger system for triggering a dynamic parametric flood impact cover for physical objects being measurably impacted by an occurrence of a flood event by using an adaptive damage-cover structure of an automated electronic damage-cover system based on physical flood event measurements, in particular in that the flood measuring and trigger system comprises a central measuring engine with a predefined data structure for capturing a geographic area to be covered, the data structure at least comprising definable area parameters capturing geographic location and/or geographic extent of said geographic area, in that predefined data structure comprises grid parameters for splitting the geographic area to be covered by the spatial grid with equidistant grid cells of definable size, in that the flood measuring and trigger system comprises flood detection devices and/or flood sensors for measuring an occurrence of a flood event by measuring floodings within grid cells of the spatial grid, wherein flood measuring parameters of the flood detection devices and/or flood sensors are transmitted to the central measuring engine and wherein, based on the transmitted flood measuring parameters, grid cells measured as flooded are contributing to the area measured as affected while grid cells measured as not flooded are not contributing to the area measured as affected, in that the central measuring engine comprises a flood threshold measurand, wherein the flood threshold measurand is selected from a percentage of the geographic area given by the area measured as affected to the geographic area, and in that the central measuring engine comprises an electronic flood trigger for triggering the adaptive damage-cover structure covering physical damages or loss associated with the measured occurrence of the flood event, the occurrence measurably impacting physical objects situated in the affected area and/or grid cells measured as affected, wherein the adaptive damage-cover structure is adapted by the damage-cover system based on the flood threshold measurand providing the dynamic parametric flood impact cover.
- In another embodiment of the invention, the grid cells are measured as flooded when each grid cell of the measured affected area is flooded. The grid cells are defined as two dimensional m×n blocks. The m×n blocks can e.g. be of approx. 8.72*10−5 radian or 0.005×0.005 deg allowing a good resolution of flood measurements. Flood determination per grid cell can e.g. be binary at the centroid. However, it can also be determined dependent on the flood depth, i.e. more refined.
- The grid cells measured as flooded can e.g. be determined using an artificial intelligence-based or machine-learning based engine, such as a neural network data processing structure, and the affected area can e.g. be measured using on-air imaging devices. The variant with the proposed grid-cell-based floodplain mapping is an inventive remote sensing intensive process that can e.g. be implemented all over the defined area. It can e.g. comprise a Digital Elevation Modelling (DEM) structure, with the predefined or adaptive measuring accuracy based on the selected grid size. The DEM structures allow the inventive system to derive the slope and terrain characteristics of the selected area. Is there a river, and if so is there a flat expanse of plain around that river? What might be below sea level that is near the mouth of a delta? To get the highest accuracy possible for these DEMs, the inventive system can e.g. use remote sensing. In particular measuring devices for aerial or space-based photography and/or LiDAR devices and Synthetic Aperture Radar (SAR) devices to produce the required high-accuracy DEMs. Aerial imagery can be used with multiple images to generate a DEM being captured using e.g. a plane or UAS. However, the quality of aerial imagery can e.g. be affected by lighting conditions and clouds. LiDAR, which shoots pulses of light and records their response, is an active system. That means it is less affected by lighting conditions, but can measure through light haze and clouds. Also SAR is able to measure through clouds at any time day or night, but is one of the most complicated remote sensing systems to be integrated. With the inventive DEMs, which can also be improved by other imagery sources such as satellite, or UAS imagery, features of importance can be monitored and/or detected in relation to how they relate to possible floodplains. Using remote sensing, the present system allows to classify land cover into many different areas of interest, such as low-lying plains, forests, sandy deltas, and urban areas, and then use those classifications to feed into the floodplain modeling structure. With LiDAR, the system can e.g. also automatically identify buildings and detect where they lie within the possible floodplains, i.e. assign floodplain-related measuring parameter values. These multiple inputs create a map that shows areas where flooding is measured with a higher probability value. The automated mapping can also be used for predictive modelling, cover or flood impact mitigation, and flood preparation or automated alarm signaling for activation of automated alarm systems.
- As an embodiment variant, the system is automated to electronically disperse payments or transfer monetary parameter values to achieve the desired automatic cover covering the physical damage or impact caused by the natural event, e.g. the flooding event. The payments are dispersed via an electronic payment transfer module based on the generated parametric coverage monetary pay-out parameter. In particular, it is an object of the present invention to provide an automated method and system for providing dynamic parametric cover to an individual in case of an occurrence of a flood event by using an adaptive risk-transfer structure based on physical flood event measurements.
- In another embodiment of the invention, wherein a premium vale is automatically generated based on the selected payout coverage and the forecasted exposure measure, i.e. the forecasted probability measurand for a future time window based on the measured occurrence frequencies and strength. Each risk-transfer can be parameterized as an exchange of risk to cover an actual physical impact to an object for a typically monetary transfer. Each impact by a risk event can be realized by a claim equivalent value, which represents the variable cost factors of a risk-transfer system. It is to be noted that the variable cost factor is difficult to determine compared to variable cost factors in other fields. For example, in the case of a production line, the variable costs, such as raw materials, are quite certain, which makes it easier to minimize it. In technical field of risk-transfer, on the other hand, variable cost factors are often measured to be a probabilistic distribution. Therefore, it is technically challenging to minimize it. In the present invention, Al/ML data processing structures are used to process the flood measuring data. In a simplified embodiment variant, also linear regression and/or generalized linear model (GLM) could be used for processing the measuring data and forecast the appropriate prediction parameter value for the future exposure measurands. However, the inventive AI-based underwriting measures risk measurands (i.e. the forecasted exposure probability values) with a much higher precision. In addition, the measuring data of the inventive system are rich compared to prior art system, as it is linked to and comprises a plurality of IoT-measuring devices. Therefore, the inventive system is able to assess the forecasted risk measurands more precisely. Uncertainty of variable cost values diminishes for the inventive system adopting the proposed technologies. Thus, the system makes it easy to determine and optimize automatically and self-sufficiently pricing values for the risk-transfer based on the measured flood parameter values. Further, the geographic area is of unvarying landscape representative of area covered by dry land and wetland.
- Further, the occurrence of the flood event can e.g. be detected using loopback signaling. The herein proposed technical loopback mechanism is especially shaped for the flood detection providing an inventive loopback flood detection method and system. A source maintenance end point at the flood area sends a loopback message to the target maintenance point at the central measuring engine, wherein the loopback message comprises a flow identity corresponding to one specific transmission path in a plurality of equal transmission paths to the target maintenance point. After receiving the loopback message, the target maintenance point sends a loopback replay message to the source maintenance end point, wherein the loopback replay message comprises a flow identity corresponding to a reverse common transmission path to the source maintenance end point. After receiving the loopback replay message and detecting to be correct, the source maintenance end point returns an announce of successful loopback detection. According to the inventive loopback detection method, the working mechanism of prior art loopback detection is expanded, and loopback detection can be performed on one specific path in a plurality of equal paths, thus allowing and providing high-speed transmission and detection of occurring flood by flood measurements in real-time or quasi-real-time.
- According to the present invention, these objects are achieved particularly through the features of the independent claims. Additional features and advantages will become apparent to those skilled in the art upon consideration of the following detailed description of illustrative embodiments exemplifying the best mode of carrying out the method as presently perceived.
- The present disclosure will be described hereafter with reference to the attached drawings, which are given as non-limiting examples only, in which:
-
FIG. 1 is a block diagram illustrating exemplary an architecture of the inventive flood measuring andtrigger system 1 and method for triggering a dynamic parametric flood impact cover forphysical objects 3/31 being measurably impacted by an occurrence of aflood event 4 by using an adaptive damage-cover structure 1031 of an electronic damage-signaling and/or damage-cover system 103 based on physical flood event measurements. -
FIG. 2 is a schematic diagram, which exemplarily illustrates a possible overall operation of one embodiment of the method of the present invention. -
FIG. 3 is a chart, which shows a structure scheme presenting an impact of flood event. -
FIG. 4 is a chart, which shows a payout scheme used during occurrence of flood event in relation to topography and exposure distribution. -
FIG. 5 schematically illustrates an exemplary parametric risk-transfer relying on the measurement of a natural physical measuring parameter or index (parameter). Automated cover by a payout transfer given by a predefined amount is made when a predefined threshold of parameter/index is exceeded (e.g. amount of rainfall, flood at location). -
FIG. 6 schematically illustrates an exemplary parametric excess rainfall risk-transfer (as a proxy for flood). Daily average rainfall amounts over Central America measured by satellite measuring data. An aggregated amount of rolling observation window (e.g. 2-days) must exceed pre-defined rainfall levels. It is to be noted that rainfall≠floods on the ground. -
FIG. 7 schematically illustrates an exemplary flood map generation through multi-source measuring parameter processing. -
FIG. 8 schematically illustrates an exemplary processing of flood event footprints, where satellite data are measured, an object level of a high spatial resolution up to 1×1 meter is achieved, daily observations with any non-permanent water for >12 hours is detected and delivered near real time, and radar technology allows monitoring through clouds and at night. -
FIG. 9 schematically illustrates an exemplary parametric flood risk-transfer structure triggered by the inventive flood measuring footprints based on maximum flood extent. -
FIG. 10 schematically illustrates an exemplary identification of critical sites orobjects 3 and generating a grid over ageographic area 2 of interest at which a flood is measured. A flood extent mapping is provided by thesystem 1 within 24 hours after peak flood. Thesystem 1 automatically detects if pre-determined sites were flooded. Cover with defined payout amounts for all affected sites and/orobjects 3 can e.g. be provided within days, thereby optimizing financial resilience and enable an immediate response. -
FIG. 11 schematically illustrates an exemplary flood map or digital elevation map from satellite imagery classification.Physical objects 3, as e.g. buildings or other constructions, can e.g. be automatically located using LiDAR which, inter alia, allows thesystem 1 to detect how close aphysical object 3 lies or within which flood zones. -
FIG. 12 shows schematically a machine-learning setup. Thegeographic area 2 is divided in 50×50grid cell 1003 raster each simulated by its own machine-learning structure. Input layer: seven input hydrographs. Output layer: flood inundation extent in eachgrid 1002 and/orgrid cell 1003. -
FIG. 13 shows schematicallygrid cells 1003 based stream-flow measurements which can e.g. be an important measuring parameter that also impacts many other aspects as e.g. the river's hydrology and water quality. -
FIG. 14 shows schematically anexemplary flood grid 1002 measuring flood depth, where the darker areas represent greater flood depths -
FIG. 15 shows schematically exemplary dynamically adjustedgrid cells 1003, wherein thecells 1003 are chosen to be dynamically adapted by thesystem 1, where areas closer to the flooding and/or river etc. are applied with a high measuring resolution than areas further away. This allows a more precise measurement of floodedareas 21 than achieved by the prior art systems. -
FIG. 16 shows schematically exemplary measurements of thegeographic area 2 by satellite measurements detecting floodedgrid cells 1003 and not floodedgrid cells 1003. The influence of clouds is eliminated by comparing and/or calibrating dry and wet measuring signals (left diagram). Water has a lower brightness temperature measured than land (right diagram). -
FIG. 17 shows schematically exemplary measurements aflood event 4/41, 42, 43 in a thegeographic area 2 based on grid cell measurements. -
FIG. 1 shows an exemplary architecture for a flood measuring andtrigger system 1 and an automated method for providing a dynamic parametricflood impact cover 1031 forphysical objects 3/31 being measurably impacted by an occurrence 41/42/43 of aflood event 4 by using an adaptive damage-cover structure 1041 of a damage-cover system 104 based on physical flood event measurements. - The flood measuring and
trigger system 1 comprises acentral measuring engine 10 with apredefined data structure 1005 for capturing ageographic area 2 to be covered, thedata structure 1005 at least comprising definable area parameters 10041 capturing geographic location 100511 and/orgeographic extent 100512 of saidgeographic area 2.Predefined data structure 1005 comprisesgrid parameters 10033 for splitting thegeographic area 2 to be covered by thespatial grid 1002 with equidistant orvariable grid cells 1003 of definable or automaticallyadaptable size 10033 by means of adynamic grid splitter 1001. Thegrid cells 1003 can e.g. be defined as two dimensional blocks of m×nsize 10033. The two dimensional m×n blocks 1003 can e.g. be of approx. 8.72*10−5radian size 10033. The dimensional m×n blocks 1003 can e.g. be of approx. 0.005*0.005deg size 10033. Grid shape 10034 (curvilinear/structured or triangular/unstructured) and the selectedgrid size 10033 affect the output of the damage signaling ordamage cover system 104. For thepresent system 1, e.g. dependent on the topology or geographic characteristics or desired resolution, structured, unstructured and/orhybrid grids 1002 can be applied. - To capture flood exposure or risk measuring data and to automatically trigger actions or alarm systems, detailed flood
measuring parameters values 1021 are measured on depth of flooding and/or probability of flooding and/or other flooding characteristics, transmitted to thecentral measuring engine 10 and stored as grid measuring datasets (seeFIG. 14 , where the darker areas represent greater flood depths). Themeasuring grid cells 1003 can e.g. be realized as a digital raster dataset that defines geographic space as an array of equally or adjustably sizedsquare cells 1003 arranged in rows and columns. The value in each cell represents the magnitude in that location of the flooding characteristic represented by that particular grid. Within a flood measuring parameter database,grids 1002 can be produced to reflect water surface elevations and/or depths and/or velocities and/or percent-annual-chances of flooding and/or other measuring values. Thegrids 1002 can e.g. be chosen based on the topography of ageographic area 2, e.g. being unique to coastal areas and dams. - In one embodiment variant, for the grid cell resolution, it should e.g. be taken into account when selecting the
cell size 10033 for thegrids 1002, that the depth and measuringgrid cells 1003 have an inherent relationship to the underlying topographic data used during the development of the flood hazard delineations, which can e.g. be depicted on the flood risk rate map. The raster cell size (resolution) 10033 of all raster datasets measured should be based on the density of the ground elevation data used and the appropriate precision that can be supported by the measurements. Normally, all the gird measuring datasets can e.g. use the samegrid cell size 10033. However, thecell size 10033 for thegrids 1002 can e.g. be no larger than 3×3 m. This will allow for a more accurate depiction and retrieval of the measuring values from that grid dataset. In thepresent system 1, a two dimensional horizontal modeling structure can e.g. be applied to get the detailed and accurate map of water levels and/or flood patterns and/or potential flood exposed areas. Instead of equalsized grid cells 1003, also structuredcurvilinear grids 1002 can e.g. be used for the hydraulic forecast processing, where thecurvilinear grid cells 1003 provide a precise forecast output signaling by allowing cell stretching along river main channels while orthogonality stays within reasonable bounds. However, the use of curvilinear grid cells can e.g. result in a high resolution in sharp inner bends since grid lines are focused on the bends. A technically not required high resolution can strongly increase computational and processing time. In a preferred embodiment variant, themeasuring grid cells 1003 are chosen to be dynamically adapted by the system 1 (seeFIG. 15 ), where areas closer to the flooding show a high resolution than areas further away. This allows a more precise measurement of floodedareas 21 than achieved by the prior art systems. - The flood measuring and
trigger system 1 comprises flood detection devices and/or flood sensors 102 for measuring an occurrence of aflood event 4 by measuring floodings withingrid cells 1003 of thespatial grid 1002, whereinflood measuring parameters 1021 of the flood detection devices and/or flood sensors 102 are transmitted to thecentral measuring engine 10 and wherein, based on the transmittedflood measuring parameters 1021,grid cells 1003 measured as flooded are contributing to thearea 21 measured as affected while grid cells measured as not flooded are not contributing to thearea 22 measured as affected. Thegeographic area 2 can e.g. comprise surveyed landscape representative of area covered by dry land 24 andwetland 25. Thegeographic area 2 can e.g. comprise at least parts definable as automatically excluded from the dynamic parametricflood impact cover 1031. The occurrence of theflood event 4 can e.g. be detected using loopback signaling 1022 for the signaling of the flood detection devices and/or flood sensors 102. The herein proposed technical loopback mechanism is especially shaped for the flood detection providing an inventive loopback flood detection method and system. A source maintenance end point at the flood area sends a loopback message to the target maintenance point at the central measuring engine, wherein the loopback message comprises a flow identity corresponding to one specific transmission path in a plurality of equal transmission paths to the target maintenance point. After receiving the loopback message, the target maintenance point sends a loopback replay message to the source maintenance end point, wherein the loopback replay message comprises a flow identity corresponding to a reverse common transmission path to the source maintenance end point. After receiving the loopback replay message and detecting to be correct, the source maintenance end point returns an announce of successful loopback detection. According to the inventive loopback detection method, the working mechanism of prior art loopback detection is expanded, and loopback detection can be performed on one specific path in a plurality of equal paths, thus allowing and providing high-speed transmission and detection of occurring flood by flood measurements in real-time or quasi-real-time. - It is to be noted that the present
inventive measuring system 1 can e.g. in an embodiment variant also be used asflood warning system 1. Monitoring is important: While some areas are more exposed to flooding than others, situating measuring devices and flood sensors 102 near waterway or body of water provides critical and precises in-loco measuring data. The affectedarea 21 can e.g. be measured using gages and telemetry equipment 1025. The presentinventive system 1 is based on the regular measuring of local rainfall, stream level, and streamflow data in eachgrid cell 1003. This can be real-time monitoring with telemetry allowing for the fastest possible response to a flood event. It is clear that a real-time flood warning system 12/121, . . . , 123 can reduce risks involved with flooding. The affectedarea 21 can e.g. be measured using at least partially air-based and/or space-based optical measuring devices 1023/1024 using digital image recognition processing (seeFIG. 16 ). Thepresent system 1 forecasts floods using the below described model structures for forecasting how rivers and streams respond to varying levels of measured rainfall and snowmelt. These forecast processing are based on already measured data records of flood level and/or stream stage and/or discharge, the generation for which are outlined below. - There are a broad variety of automated stream gages that can transmit stream level data via telemetry. Gages developed according to the NWS ALERT protocol are among the most common. However, it's to be noted that many other gages designed to measure precipitation and water level operate under similar principles, and this guide may be applicable to certain aspects of other systems. The gages, used herein, perform two primary tasks: sensing and communicating. The gages, as used herein, employs sensors to detect changes to measuring parameters, e.g. precipitation volume and/or water level. As an embodiment variant, the used gages may also be equipped with temperature and wind speed sensors. Some gages can also provide site-specific measuring data regarding the health or technical status of the measuring unit. For example, for the present
inventive system 1, the gage can e.g. be designed to detect a particular “event”, e.g. 1 millimeter of rainwater entering the gage's tipping bucket through the top of its funnel. When the bucket tips, it pours out any water within, engaging a switch that transmits alert data and resetting the bucket. Any other sensors on the gage will also activate the alert data transmitter after detecting said specific event. On days without rain, the gages can e.g. transmit a “no rain” report to show that the device 102 is still working. In the embodiment variant with automated flood warning 12/121,122,123 thesystem 1 can e.g. use radio, cellular, or satellite telemetry to communicate with an alarm host computer or alarm network. Thesystem 1 can also specifically operate alarm signals using radio frequencies and/or satellite and/or cellular telemetry. For thepresent system 1, it is to be noted that while streams and rivers can be monitored for many mearing qualities and parameters that they share with lakes, ponds and basins, streams and rivers possess one quality that differentiates them from other freshwater bodies, namely their movement. For the forecast processing by the present system, stream-flow can e.g. be an important measuring parameter that impacts many other aspects of a river's hydrology and water quality (seeFIG. 13 ). - As an embodiment variant, the
grid cells 1003 measured as flooded 10031 can e.g. be determined using at least an artificial intelligence based data-processing structure and/or a machine-learning-based data-processing structure. It is to be noted that the present inventive system generally can also be operated applying one or more types of numerical modeling structures for predictive flood parameter generation. For example, a hydrological rainfall run-off modeling structure can e.g. be used to forecast distributed river discharges. Also a one-dimensional (1D) drainage modeling structure can e.g. be applied based on the one-dimensional Saint-Venant flow forecasting to predict surcharges or drainages. Further, also a two-dimensional (2D) Saint-Venant flow forecast can e.g. be used for simulating the surface inundation, and obtain a forecasted maximum flood extents, maximum depths, and flow velocity on defined points on the surface. Furthermore, a 1D-2D coupling structure can be applied. All proposed embodiment variant relies on sensory and/or field measurements for capturing the inventive input parameters and their specific technical selection. However in a preferred embodiment variant, the system relies on a data-driven approach for establish a reliable flood forecast structure based on flood measurements. Unlike the numerical structure, the inventive data-driven, physical-based measuring and forecast system requires measuring input/output data only. The inventive data-driven structure has shown its high performance especially for the technical nonlinear flood forecast problems. In particular, ANN-based forecast structures can be applied, however the technical problem of over-fitting or under-fitting the measuring data, and insufficient length of the data sets can lead to erroneous forecast output results. To expand the data-driven forecast structures for short and long term flood forecasts, combined use of neuro-fuzzy structures and/or support vector machine (SVM) and/or support vector regression and/or artificial neural network (ANN) are also possible. More particularly, artificial neural network showed to be a reliable technique for the inventive flood prediction, as for forecasting water levels by applying ANN forecast structures to conventional hydrological modeling in flood-prone catchments. In another embodiment variant, the water level forecast results along a river uses backpropagation and/or conjugate gradient and/or cascade correlation. One possibility is to combine a Levenberg-Marquardt Backpropagation with cross-validation to prevent the under-fitting and overfitting in daily reservoir inflow forecasting. - Finally, in another preferred embodiment variant, the maximum flood inundation in a geographic area is determined by machine-learning based structure applying a backpropagation networks based on multiple inflow measuring data for a grid resolution of m×n. This ANN technique allows for a geographic area to provide high-resolution flood inundation maps from river flooding. For the prediction of maximum flood inundation, only the real-time discharges of the upstream catchments or flood level measurements are needed. The procession consists of two phases: the training phase collects a part of the measuring data from the existing database, tuning the model by changing the weights on input arcs to minimize the bias on the output layer; the recalling phase produces the new outputs for the testing inputs. The rest individuals in the training dataset are used for evaluating the behavior of the network structure. The total bias between the output of ANN and the observed values is defined as the error function. In order to reduce the error function in each iteration, the weights are modified automatically by the
system 1. Herein, the learning rate is used for automatedly scaling the gradient in each iteration of the weight update. It is to be noted that the system can be sensitive to select up the correct value, since a large learning rate can miss the optimal point, while a small learning rate can slow the training process. For example, the gradient descent algorithm can be used by thesystem 1 to generate the update of the weights values. To speed up the convergence of the iteration, resilient backpropagation can e.g. be applied in the present case for treating the update of weight values differently depending on the derivative of the error function. For optimization, larger alternative learning rate can e.g. be set for speeding up the iterations if the error gradient remains in the same direction in neighboring time-steps and smaller alternative learning rate when approaching the optimal weights. - Due to the total number data of measuring grid cells 1003 (resolution of m×n), a single hidden layer can exceed 365 thousand elements. To technically optimize the storage requirement and the ANN structure training time, the
geographic area 2 can e.g. be subdivided into 50×50 cell-squaredgrids 1002, eachgrid 1002 having its own independent ANN structure (the output layer having 1400 elements). It is to be noted that with the same inventive technical approach, instead of measuring the real-time discharges of the upstream catchments for the prediction of maximum flood inundation, rainfall measurements and/or flood level measurements can be selected as input measuring values for the machine-learning-based structure. To optimize the ANN processing technically further, clustering can be applied to the training measuring dataset. Like this, the size of the training measuring dataset can optimize and reduced while still keeping the main representative events. As such the training time can be reduced and the overfitting effects minimized. Further, to measure the technical performance of the prediction processing of maximum flood inundation by the applied ML structure, the mean squared error (MSE) of each grid can e.g. be used. It is assumed that the flood maps from the events used are the observed values. As eachgrid 1002 has its own independent training network, the MSE can e.g. be measured using all thegrid cells 1003 in eachgrid 1002. - The
central measuring engine 10 comprises aflood threshold measurand 1032, wherein theflood threshold measurand 1032 is selected from apercentage 23 of thegeographic area 2 given by thearea 21 measured as affected to the totalgeographic area 2. The adaptive damage-cover structure 1041 can e.g. only be triggered if theflood threshold measurand 1032 is measured to exceed a predefined flood threshold value 1033. In another embodiment variant, the adaptive damage-cover structure 1041 can e.g. be triggered to provide adamage cover 1031 directly dependent on the measuredflood threshold measurand 1032. - The
central measuring engine 10 comprises anelectronic flood trigger 103 for triggering the adaptive damage-cover structure 1041 covering physical damages or loss associated with the measured occurrence of theflood event 4, the occurrence measurably impactingphysical objects 3/31 situated in the affectedarea 21 and/orgrid cells 1011 measured as affected 10111, wherein the adaptive damage-cover structure 1041 is adapted by the damage-cover system 104 based on theflood threshold measurand 1032 providing the dynamic parametricflood impact cover 1031. The adaptive damage-cover structure 1041 of the damage-cover system 104 can e.g. be triggered by transmitting electronic steering signals from to the automatedly steered electronic first and/or second resource-pooling system 1042/1043, wherein the adaptive damage-cover structure 1041 is adapted by the damage-cover system 104 based on theflood threshold measurand 1032 transmitted by the electronic steering signals. Further, the triggering the adaptive damage-cover structure 1041 for covering physical damages orloss 32 associated with the measured occurrence of theflood event 4 can e.g. comprises generating aparametric coverage 1031 based on the adaptive damage-cover structure 1041, and transferring, by an electronic payment transfer module, based on the generatedparametric coverage 1031 monetary pay-out parameter values by electronic payment transfer to cover the physical damages orloss 32 associated with the measured occurrence. As an embodiment variant, a premium value can e.g. automatically and optimized generated based on a specific selection of the parametricflood impact cover 1031. - The triggering the adaptive damage-
cover structure 1041 for covering physical damages orloss 32 associated with the measured occurrence of theflood event 4 can e.g. comprise generating aparametric coverage 1031 based on a cover activation signaling orelectronic payout function 1046, and transferring, by an electronic payment transfer module, based on the output of the cover activation signaling or electronic payout function 1046 a monetary pay-out by electronic payment transfer to cover the physical damages orloss 32 associated with the measured occurrence. The cover activation signaling orelectronic payout function 1046 can e.g. comprise alinear payout function 10461 and/or a steppedpayout function 10462 and/or a deductibles-basedpayout function 10463. The cover activation signaling orelectronic payout function 1046 can e.g. be selectable based on topography and/or exposure distribution. The cover activation signaling orelectronic payout function 1046 can further e.g. be user-specific definable. -
FIG. 2 shows an exemplary schematic process of the present invention, which illustrates an overall operation of an embodiment of an automated system providing a dynamic parametric flood impact cover for an object physically impacted by the flood and/or to an individual assigned to the impacted object. Anautomated system 1, is disclosed for providing a dynamic parametric flood impact cover to flood impact exposedphysical objects 3 and/or a flood risk exposed individual in case of an occurrence of aflood event 4. The dynamicparametric cover 1031 is provided by using an adaptive risk-transfer structure 1041 based on physical flood event measurements. In one embodiment, atreference number 51, a trigger is generated by a trigger module and the trigger is activated upon occurrence of the flood event. The trigger may provide measuringdata 1021 corresponding to such as flood extent, flood depth. The generation and measurement of measuringdata 1021 related to theflood event 4 is explained in detail in conjunction withFIG. 2 of the present invention. Atreference number 52, an embodiment variant with apayout function 1046 is shown, where thepayout function 1046 is activated (atreference number 52 and triggers the payout calculation function (at reference number 53). The payout generated is dependent on occurrence of the flood event, regardless of actual loss incurred in the flooding event. The payout function is explained in detail in conjunction withFIG. 3 of the present application. Further, in another embodiment, an independent third party system or an electronic reporting agent or broker or a third party calculation agent, at reference number 54) determines an intensity of the flood event. The independent third party/reporting agent provides the information to theobject 3 or exposed individual (at reference number 54) to initiate payout generation and automatically triggering payout transfer (at reference number 53) and also informs to the individual (at reference number 55). In another embodiment, an automated module may be used to generate the payout, and automatically intimate the insured and initiate the payment. The exposed individual (at reference number 55) is the one who may purchase a cover specifying a maximum payout from the system 1 (at reference number 56). The maximum payout cover is based on extend of the floodedarea 21. The premium (at reference number 57) is transferred to the system (at reference number 51) depends on the chosen limit as well as on thearea 21 affected by the flood 4 (at reference number 55). In one embodiment, the premium is generated using probabilistic modelling structures, upon numerous reviews. - In
FIG. 3 , an exemplary structure scheme is shown presenting an impact of the flood event in a specific region. The trigger data may be obtained from highly reputed independent third party agency that are mutually in agreement with the individual. The third party agency may be, for example, use on-air imaging device such as Synthetic Aperture Radar (SAR) satellite imagery and drone based imagery that provide multiple images to capture flood depth and flood extend. - In one embodiment, the automated system (at reference number 1) first measures an Area of Interest (AOI). The AOI is an extended flooded area of a total area cover of the region. The generated AOI is then divided into a plurality of grid cells (at
reference number 1003 of aspatial grid 1002. Thegrid cells 1003 defining the desired resolution, may be determined randomly or dynamically, for example, the grid cells may be defined as two dimensional m×n blocks such as 500 m×500n (0.005×0.005 deg.) blocks of approx. 8.72*10−5 radian. Upon occurrence of the flood event, an affected area (AA) is determined, by calculating the number of grid cells that are totally flooded. In one embodiment, the grid cells measured as flooded are determined using, for example, a neural network approach, a double grid approach, and the like. In addition, the grid cells measured as not flooded do not contribute to the measured affected area of the AOI. Thereafter, the percentage (atreference number 53 of affectedarea 21 is generated with the relation of AA/AOI. The payout is based on the pre-defined trigger depending upon the percentage of affectedarea 21. It is to be noted that this predefined trigger can vary from risk-transfer to risk-transfer depending on specific user requirements. - With respect to
FIG. 4 , anexemplary payout structure 1046 can e.g. be used during occurrence of theflood event 2 in relation to topography and exposure distribution is shown via graph. In one embodiment, the payout function can be linear 10461 (straight linear), stepped or with 10462 deductibles (franchise deductibles 10463). The automated system selects payout functions based on topography and exposure distribution. Thepayout function 1046 may cater to different terrain and exposure distribution with respect to a geographic area. The payout function provides different payout functions to the individual, and the individual is free to select one of the payout function. The payout function may further include suggestions from the individual or risk-exposed insured. - For determining the payout scheme, a parametric coverage for the measured affected
area 21 may be generated by covering a possible loss associated with occurrence of the flood event and impacting a geographic area measured by the affected area. The possible loss incurred due to occurrence of the flood event may be determined as per an adjustable risk-transfer structure, a threshold measure. The possible loss incurred may be triggered by a threshold-trigger that is selected from the percentage of the affected area given by the measured affected area to the geographic area (for example, the AOI). By way of an example, the geographic area may include unvarying landscape that represents area covered by dry land and wetland. In one exemplary embodiment, the payout may vary from 0% to 100%. As shown, the measured affected area is around 75% and a limit of around USD 100 m is determined under the payout scheme. The insured may receive around 0.75×USD 100 m or around USD 75 m. In another embodiment, an electronic payment transfer may be made to the individual by an electronic payment transfer module. The electronic payment transfer may be done based on generated parametric coverage monetary pay-out parameter values. The electronic payment transfer to be made to the individual is limited and may be pre-defined based on prior discussion or agreement with the insured. In some scenarios, the individual may provide information related to the geographic area to be excluded for coverage under the payout scheme. - In yet another embodiment, the risk-assessment parameters used to determine occurrence of the flood event may be accessed using a machine learning (ML) approach. The MI approach may connect flood related measurements of various geographic areas for assessing and/or predicting overall risks by a risk transfer module. In addition, the MI approach may be used to predict a future risk pertaining to occurrence of the flood event, and/or allowing to associate varied losses incurred in the multiple geographic areas due to occurrence of the flood event leading to generation of risk factors for an associated reinsurance module. While a number of features are described herein with respect to embodiments of the inventions; features described with respect to a given embodiment also may be employed in connection with other embodiments. The following description and the annexed drawings set forth certain illustrative embodiments of the inventions. These embodiments are indicative, however, of but a few of the various ways in which the principles of the inventions may be employed.
-
-
- 1 Flood measuring and trigger system
- 10 Central measuring engine
- 100 Data aggregation and preprocessing module
- 1001 Dynamic grid splitter
- 1002 Topographic or geographic grid
- 10021, . . . , 1002 i Measuring parameters for grid cell i
- 1003 Measuring grid cells
- 10031 Grid cells measured as floated/affected
- 10032 Grid cells measured as not floated/affected
- 10033 Grid cell size
- 10034 Grid shape
- 1004 Persistence storage
- 1005 Predefined data structure
- 10051 Area parameter
- 100511 Geographic location
- 100512 Geographic extend
- 1006 Machine-learning based or Al-based module
- 102 Flood measuring devices/Flood measuring sensors
- 1021 Flood measuring parameters
- 1022 Loopback signaling
- 1023 Air-based optical measuring devices
- 1024 Space-based optical measuring devices
- 1025 Flood measuring gages with telemetry equipment
- 1026
- 103 Electronic flood trigger
- 1031 Dynamic parametric flood impact cover
- 1032 Flood threshold measurands
- 1033 Flood threshold value
- 104 Damage-signaling and/or damage-cover system
- 1041 Adaptive damage-cover structure
- 1042 First resource-pooling system
- 10421 First resources
- 1043 Second resource pooling system
- 10431 Second resources
- 1044 Electronic cover activation signaling and triggering
- 1045 Risk transfer parameter value optimization
- 1046 Cover activation function/Electronic payout function (signaling)
- 10461 Linear payout function
- 10462 Stepped payout function
- 10463 Payout function with deductibles (franchise deductibles)
- 100 Data aggregation and preprocessing module
- 11 Data Transmission network
- 12 Alarm signaling devices
- 121 Steering signaling to automated flood-alarm driven devices
- 122 Acoustic alarm signal devices
- 123 Digital alarm messaging system
- 10 Central measuring engine
- 2 Geographic area
- 21 Affected area
- 22 Not affected area
- 23 Measured percentage value of affected area vs total geographic area
- 24 Dry land area
- 25 Wet land area
- 3 Physical Objects in the geographic area (Flood exposed object)
- 31 Physical object in a grid cell
- 32 Physical damage or loss to the object impacted and caused by the occurring flood event
- 4 Flood event
- 41 Temporal occurrence
- 42 Geographic/topographic location
- 43 Event Strength
- 5 Process Flow
- 51 Central measuring engine with cover activation signaling and triggering
- 52 Damage cover activation by resource transfer/Payout function
- 53 Payout parameter value generation and payout Trigger
- 54 Electronic reporting/Independent third party system
- 55 Flood exposed object/Risk exposed individual
- 56 Damage-cover system/Risk-transfer system
- 57 Automated pricing/Premium transfer
- 1 Flood measuring and trigger system
Claims (19)
1. An automated method, implemented by a flood measuring and trigger system, for providing a dynamic parametric flood impact cover for physical objects being measurably impacted by an occurrence of a flood event by using an adaptive damage-cover structure of a damage-cover system based on physical flood event measurements, comprising:
capturing, by a predefined data structure of a central measuring engine, a geographic area to be covered, the data structure at least comprising definable area parameters capturing geographic location and/or geographic extent of said geographic area;
splitting, by the central measuring engine, the geographic area to be covered by a spatial grid with equidistant or adjusted grid cells of definable or adjustably determined size;
measuring, by flood detection devices and/or flood sensors, an occurrence of a flood event by measuring floodings within the grid cells of the spatial grid, wherein flood measuring parameters of the flood detection devices and/or flood sensors are transmitted to the central measuring engine and wherein, based on the transmitted flood measuring parameters, grid cells measured as flooded are contributing to the area measured as affected while grid cells measured as not flooded are contributing to the area measured as not affected;
measuring a flood threshold measurand, wherein the flood threshold measurand is selected from a percentage of the geographic area given by the area measured as affected to the total geographic area; and
triggering the adaptive damage-cover structure to cover physical damages or losses associated with the measured occurrence of the flood event, the occurrence measurably impacting physical objects situated in the affected area and/or grid cells measured as affected, wherein the adaptive damage-cover structure is adapted by the damage-cover system based on the flood threshold measurand providing the dynamic parametric flood impact cover.
2. The method according to claim 1 , wherein the adaptive damage-cover structure is only triggered if the flood threshold measurand is measured to exceed a predefined flood threshold value.
3. The method according to claim 1 , wherein the adaptive damage-cover structure is triggered to provide a damage cover directly dependent on the measured flood threshold measurand.
4. The method according to claim 1 , wherein the adaptive damage-cover structure of the damage-cover system is triggered by transmitting electronic steering signals from to the automatedly steered electronic first and/or second resource-pooling system, wherein the adaptive damage-cover structure is adapted by the damage-cover system based on the flood threshold measurand transmitted by the electronic steering signals.
5. The method according to claim 1 , wherein the triggering the adaptive damage-cover structure for covering physical damages or loss associated with the measured occurrence of the flood event comprises generating a parametric coverage based on the adaptive damage-cover structure, and transferring, by an electronic payment transfer module, based on the generated parametric coverage monetary pay-out parameter values by electronic payment transfer to cover the physical damages or loss associated with the measured occurrence.
6. The method according to claim 1 , wherein the grid cells are defined as two dimensional blocks of m×n size.
7. The method according to claim 6 , wherein the two dimensional m×n blocks are of approximately 8.72*10−5 radian size.
8. The method according to claim 6 , wherein the dimensional m×n blocks are of approximately 0.005*0.005 deg size.
9. The method according to claim 1 , wherein the geographic area comprising surveyed landscape representative of area covered by dry land and wetland.
10. The method according to claim 1 , wherein the occurrence of the flood event is detected using loopback signaling.
11. The method according to claim 1 , wherein the grid cells measured as flooded are determined using at least an artificial intelligence based data-processing structure and/or a machine-learning-based data-processing structure.
12. The method according to claim 1 , wherein the affected area is measured using at least partially air-based and/or space-based optical measuring devices.
13. The method according to claim 1 , further comprising generating a premium value based on a specific selection of the parametric flood impact cover.
14. The method according to claim 1 , wherein the triggering the adaptive damage-cover structure for covering physical damages or loss associated with the measured occurrence of the flood event comprises generating a parametric coverage based on a cover activation signaling or electronic payout function, and transferring, by an electronic payment transfer module, based on the output of the cover activation signaling or electronic payout function a monetary pay-out by electronic payment transfer to cover the physical damages or loss associated with the measured occurrence.
15. The method according to claim 14 , wherein the cover activation signaling or electronic payout function comprises a linear payout function and/or a stepped payout function and/or a deductibles-based payout function.
16. The method according to claim 14 , wherein the cover activation signaling or electronic payout function is selectable based on topography and/or exposure distribution.
17. The method according to claim 14 , wherein the cover activation signaling or electronic payout function is user-specific definable.
18. The method according to claim 14 , wherein the geographic area comprises at least parts definable as automatically excluded from the dynamic parametric flood impact cover.
19. A flood measuring and trigger system for triggering a dynamic parametric flood impact cover for physical objects being measurably impacted by an occurrence of a flood event by using an adaptive damage-cover structure of an electronic damage-signaling and/or damage-cover system based on physical flood event measurements, the flood measuring and trigger system comprising:
a central measuring engine with a predefined data structure for capturing a geographic area to be covered, the data structure at least comprising definable area parameters capturing geographic location and/or geographic extent of said geographic area,
wherein
the predefined data structure comprises grid parameters for splitting the geographic area to be covered by the spatial grid with equidistant or variable grid cells of definable or automatically adaptable size by means of a dynamic grid splitter,
the flood measuring and trigger system comprises flood detection devices and/or flood sensors for measuring an occurrence of a flood event by measuring floodings within grid cells of the spatial grid, wherein flood measuring parameters of the flood detection devices and/or flood sensors are transmitted to the central measuring engine and wherein, based on the transmitted flood measuring parameters, grid cells measured as flooded are contributing to the area measured as affected while grid cells measured as not flooded are not contributing to the area measured as affected;
the central measuring engine comprises a flood threshold measurand, wherein the flood threshold measurand is selected from a percentage of the geographic area given by the area measured as affected to the total geographic area, and
the central measuring engine comprises an electronic flood trigger for triggering the adaptive damage-cover structure covering physical damages or loss associated with the measured occurrence of the flood event, the occurrence measurably impacting physical objects situated in the affected area and/or grid cells measured as affected, wherein the adaptive damage-cover structure is adapted by the damage-cover system based on the flood threshold measurand providing the dynamic parametric flood impact cover.
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CH0705002021 | 2021-11-03 | ||
CH070500/2021 | 2021-11-03 | ||
PCT/EP2022/080593 WO2023078956A1 (en) | 2021-11-03 | 2022-11-02 | Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/080593 Continuation WO2023078956A1 (en) | 2021-11-03 | 2022-11-02 | Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
US20230385941A1 true US20230385941A1 (en) | 2023-11-30 |
Family
ID=84361581
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/229,310 Pending US20240077646A1 (en) | 2021-11-03 | 2023-08-02 | Automated optical-based system providing dynamic parametric flood impact cover and method thereof |
US18/232,011 Pending US20230385941A1 (en) | 2021-11-03 | 2023-08-09 | Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof |
US18/455,940 Pending US20230401651A1 (en) | 2021-11-03 | 2023-08-25 | Airborne and/or spaceborne optical flood and flood damage sensory system and method thereof |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/229,310 Pending US20240077646A1 (en) | 2021-11-03 | 2023-08-02 | Automated optical-based system providing dynamic parametric flood impact cover and method thereof |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/455,940 Pending US20230401651A1 (en) | 2021-11-03 | 2023-08-25 | Airborne and/or spaceborne optical flood and flood damage sensory system and method thereof |
Country Status (2)
Country | Link |
---|---|
US (3) | US20240077646A1 (en) |
WO (3) | WO2023078956A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116911699B (en) * | 2023-09-14 | 2023-12-19 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for fine dynamic evaluation of toughness of urban flood disaster response |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006002687A2 (en) * | 2004-06-30 | 2006-01-12 | Swiss Reinsurance Company | Method and system for automated location-dependent recognition of flood risks |
US10296981B2 (en) * | 2016-09-14 | 2019-05-21 | Swiss Reinsurance Company Ltd. | Method and system for automated location-dependent recognition of storm risks and exposure-based parametric risk-transfer |
US11107025B2 (en) * | 2016-12-13 | 2021-08-31 | STREAM METHODS, Inc. | System and method for producing and distributing information relevant to water events |
-
2022
- 2022-11-02 WO PCT/EP2022/080593 patent/WO2023078956A1/en active Application Filing
- 2022-11-03 WO PCT/EP2022/080742 patent/WO2023079038A1/en active Application Filing
- 2022-11-03 WO PCT/EP2022/080753 patent/WO2023079043A1/en active Application Filing
-
2023
- 2023-08-02 US US18/229,310 patent/US20240077646A1/en active Pending
- 2023-08-09 US US18/232,011 patent/US20230385941A1/en active Pending
- 2023-08-25 US US18/455,940 patent/US20230401651A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
WO2023079043A1 (en) | 2023-05-11 |
WO2023078956A1 (en) | 2023-05-11 |
US20240077646A1 (en) | 2024-03-07 |
WO2023079038A1 (en) | 2023-05-11 |
US20230401651A1 (en) | 2023-12-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10296981B2 (en) | Method and system for automated location-dependent recognition of storm risks and exposure-based parametric risk-transfer | |
McGrath et al. | A comparison of simplified conceptual models for rapid web-based flood inundation mapping | |
Dong et al. | Bayesian modeling of flood control networks for failure cascade characterization and vulnerability assessment | |
Li et al. | Urban flood susceptibility mapping based on social media data in Chengdu city, China | |
US20230259798A1 (en) | Systems and methods for automatic environmental planning and decision support using artificial intelligence and data fusion techniques on distributed sensor network data | |
Chaudhuri et al. | Track and intensity forecast of tropical cyclones over the North Indian Ocean with multilayer feed forward neural nets | |
US20090303056A1 (en) | Trigger system for monitoring and/or control devices and/or early warning systems for nascent and/or occurring cyclones | |
Hadian et al. | Multi attributive ideal-real comparative analysis (MAIRCA) method for evaluating flood susceptibility in a temperate Mediterranean climate | |
US20230385941A1 (en) | Automated parametric modular system or digital platform for forward-looking measurements and ratings of measurable impacts of occurring flood events and modular automated risk-transfer structure providing an adjustable flood impact cover and method thereof | |
CN109997164A (en) | Measurement based on interarrival time and the measuring system and method for the imminent natural disaster sexual behavior part of prediction are provided | |
Liu et al. | The danger of mapping risk from multiple natural hazards | |
Nguyen et al. | Regional-scale landslide risk assessment on Mt. Umyeon using risk index estimation | |
CA3172010A1 (en) | Machine learning architecture for quantifying and monitoring event-based risk | |
de Arruda Gomes et al. | Hydrologic models coupled with 2D hydrodynamic model for high-resolution urban flood simulation | |
Delalay et al. | Methodology for future flood assessment in terms of economic damage: Development and application for a case study in Nepal | |
Mokhtari et al. | Satellite-based streamflow simulation using CHIRPS satellite precipitation product in Shah Bahram Basin, Iran | |
Wahba et al. | Building information modeling integrated with environmental flood hazard to assess the building vulnerability to flash floods | |
Bannayan et al. | Predicting realizations of daily weather data for climate forecasts using the non‐parametric nearest‐neighbour re‐sampling technique | |
Yuan et al. | Predicting road flooding risk with machine learning approaches using crowdsourced reports and fine-grained traffic data | |
Acierto et al. | Development of a hydrological telemetry system in Bago River | |
CN114118628A (en) | Disaster early warning method based on recurrent neural network model and related equipment | |
Niño et al. | A risk index due to natural hazards based on the expected annual loss | |
Atchyuth et al. | Near real-time flood inundation and hazard mapping of Baitarani River Basin using Google Earth Engine and SAR imagery | |
Manomy et al. | Flood Prediction and Tracking Trapped | |
Saha et al. | Flash flood potential risk zonation mapping using GIS-based spatial multi-index model: a case study of Sunamganj District, Bangladesh |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SWISS REINSURANCE COMPANY LTD., SWITZERLAND Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SUNDERMANN, LUKAS;REEL/FRAME:064538/0537 Effective date: 20230613 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |