CN115422782B - Flood forecasting system based on hydrological model - Google Patents
Flood forecasting system based on hydrological model Download PDFInfo
- Publication number
- CN115422782B CN115422782B CN202211365022.9A CN202211365022A CN115422782B CN 115422782 B CN115422782 B CN 115422782B CN 202211365022 A CN202211365022 A CN 202211365022A CN 115422782 B CN115422782 B CN 115422782B
- Authority
- CN
- China
- Prior art keywords
- flood
- data
- rainfall
- flow data
- module
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 claims abstract description 82
- 238000001514 detection method Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 65
- 239000002689 soil Substances 0.000 claims description 35
- 238000011144 upstream manufacturing Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 25
- 239000011541 reaction mixture Substances 0.000 claims description 23
- 238000001228 spectrum Methods 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000001556 precipitation Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 13
- 229920006395 saturated elastomer Polymers 0.000 claims description 12
- 230000008020 evaporation Effects 0.000 claims description 8
- 238000001704 evaporation Methods 0.000 claims description 8
- 230000035515 penetration Effects 0.000 claims description 8
- 239000002352 surface water Substances 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 6
- 230000033228 biological regulation Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 5
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 239000003795 chemical substances by application Substances 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 230000004907 flux Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000006424 Flood reaction Methods 0.000 claims description 2
- 239000003365 glass fiber Substances 0.000 claims 1
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000004043 responsiveness Effects 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 239000000523 sample Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000003054 catalyst Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Alarm Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a flood forecasting system based on a hydrological model, which is applied to the field of information processing; the technical scheme is that the flood forecasting system based on the hydrological model comprises a man-machine interaction module, a rainfall radar detection station, a flood simulation module, a data receiving and processing module, a flood simulation database, a GIS subsystem and a wireless communication network; the method can provide the flood information with predictability, responsiveness and initiative, can simulate the flood flow through the TOPKAPI hydrological model, can work at the minimum cost, adopts the AdaBoost classifier to classify the features of the flood flow data, and greatly improves the flood flow data prediction precision of the flood forecasting system.
Description
Technical Field
The present invention relates to the field of information processing, and more particularly to a flood forecasting system based on a hydrological model.
Background
Natural flooding is one of the most frequent disasters. Unlike the occasional stagnant water discharge in poorly planned cities, major flood events invariably cause considerable damage to property and often result in loss of life. In different areas, areas with improper land use do not effectively discharge accumulated precipitation, and therefore more frequent flooding inevitably occurs.
Conventional meteorological readings, such as precipitation, temperature, humidity, etc., take a long time to measure, process, record, and transmit to the relevant tissues. Analysis based on past precipitation is known to be associated with several drawbacks. For example, they result in flood predictions that are inaccurate and often outdated. The limited sample size, insufficient computational power, inefficient prediction methods, all of which undermine the true potential of the scheme. A typical practice proposed in the prior art is to train a modern machine learning model with real-time rainfall, runoff, and other data. However, it is not clear at present how the predicted outcome is compared to the actual events obtained from crowdsourcing.
Disclosure of Invention
In order to solve the problems, the invention discloses a flood forecasting system based on a hydrological model, which uses the hydrological model based on Terrain Motion Approximation and Integration (TOPKAPI) to realize the analysis and processing of flood flow big data and predict the flood forecasting alarm information in real time.
In order to achieve the technical effects, the invention adopts the following technical scheme:
a hydrologic model based flood forecasting system comprising:
the man-machine interaction module is used for controlling the flood flow of the flood discharge facility so as to carry out flood regulation calculation on the flood flow;
the rainfall radar detection station is used for detecting meteorological targets of the location of the flood in real time;
the flood simulation module is used for simulating and collecting flood flow data and rainfall flow data through the TOPKAPI hydrological model;
the data receiving and processing module is used for receiving flood flow data and rainfall flow data and analyzing and processing the received flood flow data and rainfall flow data by adopting an AdaBoost classifier;
the flood simulation database is used for storing and defining the flood flow data and the rainfall flow data through the hierarchical model database;
the GIS subsystem is used for displaying the unit grid flood flow data and rainfall flow data of each detection period by a graphic table;
the user terminal is used for transmitting the data information received by the data receiving and processing module to the public network in a GPRS wireless communication mode to inform the user terminal;
the rainfall radar detection station is unidirectionally connected to the data receiving and processing module, the flood simulation module is unidirectionally connected to the data receiving and processing module and the flood simulation database, the data receiving and processing module is bidirectionally connected with the human-computer interaction module, the human-computer interaction module is unidirectionally connected to the GIS subsystem, and the GIS subsystem is unidirectionally connected to the wireless communication network.
As a further technical scheme of the invention, the rainfall radar detection station consists of a radar station and four raindrop spectrum monitoring stations, wherein the radar station consists of a transmitter, a receiver, a signal processor, a servo system, a power supply and distribution system, a radar control terminal and a data processing terminal and is used for realizing real-time detection of surrounding cloud, raindrop, hail and other meteorological targets, and the radar station and the central station carry out data transmission and command interaction through a wired network; the raindrop spectrum monitoring station consists of a laser raindrop spectrometer, a data acquisition device and a solar power supply system, and is used for monitoring a rainfall velocity spectrum and a particle size spectrum, calibrating radar monitoring data according to the rainfall velocity spectrum and the particle size spectrum, and monitoring rainfall.
As a further technical scheme of the invention, the flood forecasting system comprises an intelligent early warning module, a time period of 1 hour is set, basic monitoring information is collected and is transmitted by a file transfer protocol to be uniformly output to a data receiving and processing module, the collected information is collected and analyzed, the received data information is compared with standard data information of a database, the running state is judged to be normal, alarm and error report is displayed on a GIS subsystem, meanwhile, alarm reminding is carried out on a background, and error report information is processed by operation and maintenance personnel.
As a further technical solution of the present invention, the flood simulation module includes an upstream flood simulation module and a downstream flood simulation module; the upstream flood simulation module is used for simulating rainfall input water quantity and flood surface flowing water quantity, and the downstream flood is used for simulating flood underground flowing water quantity;
the upstream flood simulation module consists of a flow detection module, a penetration detection module, a rainfall speed detection module and a stock calculation module;
the downstream flood simulation module consists of an evaporation capacity detection module, a penetration detection module, a relief water loss detection module and a flow rate detection module.
As a further technical scheme of the invention, the flood simulation module simulates flood flow through a TOPKAPI hydrological model, and in the upstream flood simulation module part, the grid unit defined by the bottom DEM describes the topography of the flood basin, and the flood flow is supposed to be concentrated on the first layeriAnd each DEM grid unit, the basic equations for expressing the flood flow phenomenon are a continuity equation and a flow equation, and the expression function is as follows:
in the formula (1), the acid-base catalyst,Hthe average soil moisture content on the vertical axis is shown,tit is shown that the acquisition period is,Xrepresents the size of the terrain space of the flood basin,y r the water content of the residual soil is shown,y s which represents the water content of the saturated soil,Lthe thickness of the surface soil layer is shown,qrepresenting the horizontal flow width flux in the soil,
the slope of the surface is indicated as,k s it is shown that the water conductivity is saturated,prepresenting the precipitation intensity; the actual total water content function of the soil on the vertical axis of the DEM grid unit is expressed as:
in the formula (2), the reaction mixture is,ηindicating the actual total water content of the soil on the vertical axis, subscriptrIndicating residual English word abbreviations, subscriptssRepresenting the saturated english word abbreviation, substituted into equation (1), the local conductance is:
in the formula (3), the reaction mixture is,Crepresenting a local conductivity coefficient; the topographic space size in the flood basin is realized by the formula (3)XTo (1) aiThe integral equation obtained on each DEM unit is as follows:
in the formula (4), the reaction mixture is,Vs i is stored iniVolume per unit width in individual DEM grid cells, volume of water stored in each DEM grid cell and total water contentηCorrelation, as shown in equation (5):
substituting the formula (5) into the formula (4), simplifying to obtain a general unit, writing a nonlinear reservoir equation, wherein the total inflow of the upstream flood simulation module into the DEM grid unit is shown as the formula (6):
in the formula (6), the reaction mixture is,Qrepresenting the total inflow from the upstream flood simulation module into the DEM grid unit; in the downstream flood simulation module part, according to the simulation program of the upstream flood in the formulas (1) - (6), assuming that the surface water depth is constant, and integrating on the longitudinal dimension to obtain the firstiThe nonlinear reservoir equation of each DEM grid unit is shown as the formula (7):
in the formula (7), the reaction mixture is,Vo i is the firstiVolume, subscript, of surface water in individual DEM grid cellsoRepresenting a surface word abbreviation and representing a surface word abbreviation,r 1 is the saturation excess produced by soil water; for a tree-shaped channel network with a rectangular cross section and a width increasing with the increase of the drainage area, the non-linear reservoir equation of a general channel section can be written as formula (8):
in the formula (8), the reaction mixture is,Vc i is thatiThe amount of water, subscript, stored in the river coursecThe method represents the word abbreviation of the river reach,r 2 is used for the input of the side drainage,Wis the width of the river reach of the river channel,Qcis the total flow of the downstream flood simulation modules according to the TOPKAPI hydrological modelComputingQ c +QAnd obtaining the total flow of the flood simulation output.
As a further technical solution of the present invention, on a single DEM grid element within the integral domain, the amount of air precipitation simulated over a 1 hour period is fixed and all precipitation reaching the soil will penetrate unless the soil in this DEM grid element is already saturated.
As a further technical scheme of the present invention, the flood forecasting system is transmitted to a public network user terminal through a GPRS wireless communication manner, the user terminal is divided into a general user terminal and an administrator terminal, the general user terminal browses map data and geographical rainfall information of a flood basin, and forecasts a flood forecasting message including an accumulated rainfall and a precipitation probability through a flood observation API and a rainfall forecasting API; the management terminal is an authorized agent of the operation service, checks the flood situation after receiving the flood forecast message, acquires the big data flood situation through the internet of things technology, updates the flood situation and the flood data, learns the crowd-sourced flood situation after the flood situation, and approves the message and updates the flood forecast.
As a further technical scheme of the invention, the AdaBoost classifier classifies the characteristics of the flood flow data into a strong classifier and a weak classifier, adaBoost performs iterative training on the weak classifier, and the weak classifier trained in each stage participates in the iteration of the weak classifier of the next round, and finally becomes the strong classifier; suppose AdaBoost classifier totalsNAnd the characteristic parameters are arranged from large to small, and are obtained by distinguishing:
in the formula (9), the reaction mixture is,Rrepresenting the flood flow data concentration,Tbefore showingkThe dispersion of the flood flow data,w k is shown askThe individual flood flow data weights are used to determine,g k to identify flood flow data type values; if it is the firstkThe flood water flow data is positive flood flow dataThen, theng k =1; if it is firstkThe individual flood water flow data is the negative flood water flow data, otherwiseg k = —1；
In the AdaBoost classifier processing process, the strong classifier initializes the flood flow data weight towCalculating the firstjWeighted error rate of strong classifierPAs shown in equation (10):
in the formula (10), the compound represented by the formula (10),xrepresenting a strong classifier;
the meaning of the function isjThe flood flow data classification result of each strong classifier adjusts the target weight value of each flood flow data according to the optimal strong and weak classification result, as shown in formula (11):
and updating the classification target flood flow data parameters according to the calculation result, distinguishing the flood flow data parameters, and finishing the deep processing of the flood flow data.
The invention has the beneficial and positive effects that:
different from the conventional technology, the method can provide the flood information with predictability, reactivity and initiative, can simulate the flood flow through the TOPKAPI hydrological model, can work at the minimum cost, and can greatly improve the flood flow data prediction precision of the flood forecasting system by classifying the features of the flood flow data through the AdaBoost classifier.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive exercise, wherein:
FIG. 1 illustrates a block diagram of a flood forecasting system based on a hydrological model;
figure 2 shows a schematic diagram of TOPKAPI hydrological model upstream flood flow simulation;
figure 3 shows a schematic diagram of TOPKAPI hydrological model downstream flood flow simulation;
fig. 4 shows a user terminal forecasting flowchart of the flood forecasting system;
fig. 5 shows a comparison graph of the prediction accuracy of three flood forecasting systems.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, it being understood that the embodiments described herein are merely illustrative and explanatory of the invention, and are not restrictive thereof;
as shown in fig. 1, a flood forecasting system based on a hydrological model includes a human-computer interaction module, a rainfall radar detection station, a flood simulation module, a data receiving and processing module, a flood simulation database, a Geographic Information System (GIS) and a wireless communication network. The man-machine interaction module is used for controlling the flood flow of the flood discharge facility so as to carry out flood regulation calculation on the flood flow; the rainfall radar detection station is used for detecting meteorological targets of the location of the flood in real time; the flood simulation module is used for simulating and collecting flood water flow data and rainfall flow data through a Terrain Motion Approximation and Integration (TOPKAPI) hydrological model; the data receiving and processing module is used for receiving flood flow data and rainfall flow data, analyzing and processing the received flood flow data and rainfall flow data by adopting an AdaBoost classifier, and analyzing and processing the received flood flow data and rainfall flow data by adopting the AdaBoost classifier; the flood simulation database is used for storing flood flow data and rainfall flow data and defining identification through the hierarchical model database; the GIS subsystem is used for displaying the unit grid flood flow data and rainfall flow data of each detection period by a graphic table; the wireless communication network is used for transmitting to a public network user terminal in a General Packet Radio Service (GPRS) wireless communication mode. The rainfall radar detection station is unidirectionally connected to the data receiving and processing module, the flood simulation module is unidirectionally connected to the data receiving and processing module and the flood simulation database, the data receiving and processing module is bidirectionally connected with the human-computer interaction module, the human-computer interaction module is unidirectionally connected to the GIS subsystem, and the GIS subsystem is unidirectionally connected to the wireless communication network.
In a specific embodiment, the topological structure of each hydrological unit of the forecast drainage basin can be extracted by using the initial longitude and latitude of the forecast drainage basin. And then carrying out weighted average on the historical meteorological hydrological data of the forecast basin according to the nodes in the topological structure of each hydrological unit to obtain the historical meteorological hydrological data of each hydrological unit. The historical meteorological hydrological data can include air temperature, precipitation and measured data of each observation station of the forecast drainage basin. And comparing the rainfall of the historical meteorological hydrological data under each hydrological unit with the corresponding actual meteorological hydrological data, determining the historical meteorological hydrological data matched with the rainfall, and weighting the historical meteorological hydrological data with the runoff obtained by the simulation calculation to obtain the forecast result of each hydrological unit. The rainfall change and the water level change trend in the rainfall-matched historical meteorological hydrological data can be used as a reference of the current rainfall change and the water level change trend under the corresponding hydrological unit. That is, the current rainfall and water level trend may be similar to the historical trend. Furthermore, a set of actual weather hydrological data may be matched with a plurality of sets of historical weather hydrological data, and these matched sets of historical weather hydrological data may be used as references. The result of the hydrological model simulation calculation is runoff, and the runoff is obtained by inputting precipitation and evaporation data of a corresponding basin in the hydrological model, combining an initial value, considering basin characteristics and assisting with the hydrological model parameter calculation.
In a specific embodiment, the result of the hydrological model simulation calculation is runoff, and is obtained by inputting precipitation and evaporation data of a corresponding watershed in the hydrological model, combining an initial value, considering watershed characteristics and calculating parameters of the hydrological model. And if the certainty coefficient of the forecast result of each hydrological unit and the corresponding actual meteorological hydrological data is larger than or equal to the effective reading value, calculating the flood elements of each hydrological unit by using the rainfall of each hydrological unit and the parameters adopted by the simulation calculation under each hydrological unit. The effective threshold may be set according to practical situations, and may be set to 70% in general. The parameters adopted by the simulation calculation can comprise an excess seepage flow parameter, an earth surface regulation coefficient, a soil medium flow regulation coefficient, a groundwater replenishment coefficient, an evaporation coefficient, a base flow Ma Sijing root coefficient, a soil water storage capacity and a stable seepage rate, wherein the rainfall of each hydrological unit can be real-time rainfall, or the calculated flood element is real-time if the predicted future rainfall is implemented, and if the predicted future rainfall is future rainfall, the calculated flood element is future. The flood elements may include flood peak values, flood peak flow rates, flood peak arrival times, and the like.
In a specific embodiment, the rainfall radar detection station consists of a radar station, four raindrop spectrum monitoring stations, a set of data receiving and processing system and a set of service application system. The radar station comprises a transmitter, a receiver, a signal processor, a servo system, a power supply and distribution system, a radar control terminal, a data processing terminal and the like, is used for realizing real-time detection of surrounding meteorological targets such as clouds, raindrops, hailstones and the like, and performs data transmission and command interaction with the central station through a wired network. The raindrop spectrum monitoring station comprises a laser raindrop spectrum meter, a data acquisition device, a solar power supply system and the like, and is used for monitoring a rainfall velocity spectrum and a particle size spectrum, calibrating radar monitoring data according to the rainfall velocity spectrum and the particle size spectrum, and realizing high-precision rainfall monitoring. The data of the raindrop spectrum monitoring station is transmitted to the central station in a wireless mode such as GPRS (general packet radio service). And the central station data receiving and processing system analyzes and processes the radar detection data and the raindrop spectrum data to finally obtain the grid rain value of the radar monitoring area. The business application system accumulates the grid point rainfall based on each detection period, displays the grid point rainfall on the GIS system in a graphic form, and performs flood forecast analysis, mountain torrent early warning analysis and urban waterlogging analysis, sponge urban analysis and application and the like according to needs.
In a specific embodiment, the flood forecasting system comprises an intelligent early warning module, a time period of 1 hour is set, basic monitoring information is collected and is uniformly output to a data receiving and processing module through file transfer protocol transmission, the collected information is collected and analyzed, the received data information is compared with database standard data information, the running state is judged to be normal, alarm and error report, the running state is displayed in a GIS subsystem, meanwhile, alarm reminding is carried out on a background, and operation and maintenance personnel process the error report information.
In a specific embodiment, the flood simulation module comprises an upstream flood simulation module and a downstream flood simulation module; the upstream flood simulation module is used for simulating rainfall input water quantity and flowing water quantity on the surface of flood, and the downstream flood is used for simulating flowing water quantity under the flood.
The upstream flood simulation module consists of a flow detection module, a penetration detection module, a rainfall speed detection module and a stock calculation module; the downstream flood simulation module consists of an evaporation capacity detection module, a penetration detection module, a relief water loss detection module and a flow rate detection module.
In a specific embodiment, for example, in the simulation of the upstream flood simulation module, the flow detection module is configured to detect upstream flow information, and in the specific simulation, the data information in the environment such as the upstream rainfall input water volume and the flood surface flowing water volume may be simulated through various scenes such as flow velocity and water volume, for example, in the test, the regional environment may be set artificially, for example, channels in different regions of a mountain area may be simulated through a pipeline, and light may be used or water vapor may be absorbed. In a further embodiment, a part of the information characteristics, the flow rate, the infiltration amount, the rainfall speed, the flow rate inventory in a day or a period of time, and the like of the flood data information are selected by selecting the characteristics of the field area environment or the area water area, such as in a mountain area or a flood frequently occurring area. During detection, simulation or application of different information such as flood flow can be realized through a flow sensor, a penetration detection sensor, a rainfall speed sensor, a storage quantity calculation sensor or the like, or a special water quantity detection tool.
In a specific embodiment, the downstream flood simulation module detects different data information such as a flood evaporation capacity of a certain water area, a penetration detection capacity of the certain water area, a loss amount of the surface water of the certain water area, a flow rate of the certain water area and the like through the evaporation capacity detection module, and performs data information evaluation through the data information to improve data information simulation and simulation capability, wherein the different data information can reflect flood data information from the side.
In a specific embodiment, the flood simulation module simulates flood flow through a TOPKAPI hydrological model, as shown in fig. 2, in an upstream flood simulation module part, a flood basin terrain is described through grid cells defined by a bottom layer Digital Elevation Model (DEM), assuming that flood flow is concentrated on the first placeiThe basic equations for representing the flood flow phenomenon are continuity equation and flow equation, which are expressed in the approximate form of equation (1):
in the formula (1), the acid-base catalyst,Hthe average soil moisture content on the vertical axis is shown,twhich is indicative of the period of acquisition,Xrepresents the size of the terrain space of the flood basin,y r the water content of the residual soil is shown,y s which represents the water content of the saturated soil,Lthe thickness of the surface soil layer is shown,qindicating the horizontal flow width flux in the soil,
the slope of the surface is indicated as,k s it is indicated that the water conductivity is saturated,prepresenting the precipitation intensity; the actual total water content function of the soil on the vertical axis of the DEM grid unit is expressed as:
in the formula (2), the reaction mixture is,ηindicating the actual total water content of the soil on the vertical axis, subscriptrIndicating residual English word abbreviations, subscriptssRepresenting saturated english word abbreviations. The method comprises the steps of analyzing GIS data and DEM data of a forecast drainage basin, dividing the forecast drainage basin into each DEM grid unit, adopting respective corresponding parameters during simulation calculation aiming at each DEM grid unit, and conducting flood forecast according to flood elements of each DEM grid unit, wherein the flood elements obtained through simulation calculation of the respective corresponding parameters are more in line with the characteristics of each DEM grid unit compared with the fact that the only one set of parameters of the whole forecast drainage basin are adopted during simulation calculation of the existing hydrological model, and the accuracy and the precision are higher. Substituting equation (2) into equation (1), the local conductivity is:
in the formula (3), the reaction mixture is,Cthe local conductivity is expressed, and the influence of specific soil parameters of the DEM grid unit on the hydraulic conductivity and the gradient of the DEM grid unit is included, and the storage capacity of the DEM grid unit is inversely proportional to the hydraulic conductivity and the gradient of the DEM grid unit; the size of the terrain space in the flood basin isXTo (1) aiOn each DEM unit, integrating equation (4) in the soil to obtain:
in the formula (4), the reaction mixture is,Vs i is stored iniUnit width volume in each DEM grid cell; in the TOPKAPI hydrological model, water is inclined downwards along a tree-shaped grid cell network in four directions until reaching a basin outlet, and the volume of water stored in each DEM grid cell and the total water content are assumed to be negligible in each cell along the cell, assuming that the vertical water content variation in each cell is negligibleηCorrelation, e.g. of formula(5) Shown in the figure:
substituting the formula (5) into the formula (4), and simplifying to obtain a general unit to write a nonlinear reservoir equation. And comparing the historical meteorological hydrological data under each DEM grid unit with the corresponding actual meteorological hydrological data to determine the historical meteorological hydrological data matched with rainfall, thereby providing help and scientific support for experiential flood forecasting. And comparing the weighted forecast result of each DEM grid unit with the corresponding actual meteorological hydrological data, and if the certainty coefficient of the two is greater than or equal to the effective threshold value, namely the weighted forecast result of each DEM grid unit is close to the corresponding actual meteorological hydrological data, indicating that the parameters adopted by the simulation calculation under each DEM grid unit are accurate and reasonable, and calculating the flood element of the corresponding DEM grid unit by combining the accurate and reasonable parameters with the rainfall under each DEM grid unit. The method determines whether the parameters adopted by the simulation calculation are accurate and reasonable by judging whether the certainty coefficient exceeds the effective threshold value, and avoids the problem that the flood elements obtained by unreasonable parameter calculation are inaccurate. In summary, the total inflow of the upstream flood simulation module into the DEM grid cells is shown in equation (6):
in the formula (6), the reaction mixture is,Qrepresenting the total inflow into the DEM grid cells from the upstream flood simulation module, in an embodiment the total inflow Q into the DEM grid cells from the upstream flood simulation module comprises the inflow from the upland soilQ c Side inflow of branchQoAnd side inflow of branchQs。
In the downstream flood simulation module section, as shown in FIG. 3, the surface water depth is assumed to be constant and integrated over the longitudinal dimension to yield the second time period, according to the simulation program for upstream floodsiNonlinear reservoir method of DEM grid unitCheng Ru, as shown in equation (7):
in the formula (7), the reaction mixture is,Vo i is the firstiVolume, subscript, of surface water in individual DEM grid cellsoRepresenting a surface word abbreviation and representing a surface word abbreviation,r 1 is the saturation excess produced by soil water; for a tree-shaped channel network with a rectangular cross section and a width increasing with the increase of the drainage area, the non-linear reservoir equation of a general channel section can be written as formula (8):
in the formula (8), the reaction mixture is,Vc i is thatiThe amount of water stored in river reach, subscriptcThe method represents the word abbreviation of the river reach,r 2 is used for the input of the side drainage,Wis the width of the river reach of the river channel,Qcis the total flow of the downstream flood simulation module, and is calculated according to the TOPKAPI hydrological modelQ c +QAnd obtaining the total flow of the flood simulation output. The execution process of judging whether the forecast result is accurate is to compare the size of the flood peak in the forecast result with the actual and real flood size. And when the size of the flood peak in the forecast result is different from the actual and real flood size, correspondingly modifying the parameters of the hydrological model, and recalculating the forecast result by using the hydrological model after the parameters are modified. And calculating parameters of a hydrological model adopted for obtaining an accurate forecasting result by calculation to obtain the runoff, and weighting the runoff and the matched historical meteorological hydrological data to forecast the flood. By adopting the technical scheme, the embodiment of the invention excavates the historical meteorological hydrological data, intelligently matches the meteorological hydrological data acquired in real time, determines the matched historical meteorological hydrological data, and provides help and scientific support for experiential flood forecasting.
In a specific embodiment, the amount of air precipitation simulated over a 1 hour period is fixed on a single DEM grid element within the integral domain, and all precipitation that reaches the soil will penetrate unless the soil in this DEM grid element is already saturated.
In a specific embodiment, as shown in fig. 4, the flood forecasting system transmits the information to a public network user terminal through a GPRS wireless communication manner, the user terminal is divided into a general user terminal and an administrator terminal, the general user terminal browses map data and rainfall information of a geographical flood basin, and forecasts a flood forecasting message including an accumulated rainfall and a precipitation probability through a flood observation Application Program Interface (API) and a rainfall forecasting API; the management terminal is an authorized agent of the operation service, checks the flood situation after receiving the flood forecast message, acquires the big data flood situation through the internet of things technology, updates the flood situation and the flood data, learns the crowd-sourced flood situation after the flood situation, and approves the message and updates the flood forecast.
In a specific embodiment, the AdaBoost classifier classifies the flood flow data features into a strong classifier and a weak classifier, the AdaBoost performs iterative training on the weak classifier, and the weak classifier trained in each stage participates in the iteration of the weak classifier in the next round to finally become the strong classifier; suppose AdaBoost classifier totalsNAnd the characteristic parameters are arranged from large to small, and are obtained by distinguishing:
in the formula (9), the reaction mixture is,Rrepresenting the flood flow data concentration,Tbefore showingkThe dispersion of the flood flow data,w k is shown askThe data weight of the individual flood flows,g k to identify flood flow data type values; if it is firstkIf the individual flood flow data is positive flood flow data, theng k =1; if it is firstkThe individual flood water flow data is the negative flood water flow data, otherwiseg k = -1; in the using process of the sample training set, the Adaboost algorithm is usedThe key classification feature set is selected for multiple times, component weak classifiers are trained step by step, the best weak classifier is selected by using a proper threshold value, and finally the best weak classifier selected by each iterative training is constructed into a strong classifier. The design mode of the cascade classifier is that the output rate of the images which are not of interest is reduced while the output rate of the images which are of interest is guaranteed as much as possible, all the images which are not of interest cannot pass through the cascade classifier along with the continuous increase of the iteration times, and the samples which are of interest always keep passing through the cascade classifier as far as possible.
In the AdaBoost classifier processing process, the strong classifier initializes the flood flow data weight towCalculating the firstjWeighted error rate of strong classifierPAs shown in equation (10):
in the formula (10), x represents a strong classifier;
the meaning of the function isjFlood flow data classification results of the strong classifiers. The description process of the Adaboost algorithm shows that the sample weight is initialized according to the size of the training set in the implementation process of the Adaboost algorithm, so that the sample weight is uniformly distributed, and the weight of the sample after the iteration of the algorithm is changed and normalized through a formula in the subsequent operation. Misclassification of samples results in an increase in weight values, whereas the weight values decrease accordingly, which means that the misclassified training sample set includes a higher weight. This will make the training sample set focus more on the samples that are difficult to identify on the next round, and further learning for the misclassified samples will result in the next weak classifier until the samples are correctly classified. When a specified number of iterations or expected error rate is reached, then the strong classifier construction is complete. And (3) according to the optimal strength classification result, adjusting the target weight value of each flood flow data, as shown in a formula (11):
and updating the classification target flood flow data parameters according to the calculation result, distinguishing the flood flow data parameters, and finishing the deep processing of the flood flow data.
In a specific embodiment, a larger training Hong Shuiliu quantity data set is required to obtain higher flood flow data detection accuracy, in each iteration process, one weak classifier is trained to correspond to each flood flow data in the flood flow data set, each flood flow data has many features, and therefore the calculation amount of the optimal weak classifier obtained by training from the huge features is increased. The search mechanism adopted by the typical Adaboost algorithm is a backtracking method, and although the greedy algorithm is used to obtain the local optimal weak classifier each time when the weak classifier is trained, it cannot be ensured that the weighted weak classifier is the overall optimal one. After the weak classifier with the minimum error is selected, the weight of each flood flow data is updated, the weight corresponding to the wrongly classified flood flow data is increased, and the weight of the correctly classified flood flow data is relatively reduced. And the execution effect depends on the selection of the weak classifier, and the search time is increased, so the training process causes the used time of the whole system to be very large, and the wide application of the algorithm is limited. On the other hand, in the algorithm implementation process, the cascade classifier is constructed by gradually approaching the expected value from the two aspects of the detection rate and the false recognition rate of the flood water flow data, and the construction process can be implemented only after a large number of weak classifiers are generated by iterative training. Training a classifier to thereby deduce a loop approximation takes more time.
In the specific embodiment, the improved deep learning algorithm model adopted by the invention is subjected to simulation comparison, the judgment result in the voice analysis process is analyzed in an investigation mode to complete recording, the flood flow data prediction precision operation of the whole system model is carried out on the judgment result, and the result is expressed in the form of a simulation curve, so that the simulation and the analysis are completed. The hardware configuration CPU of the computer used in the simulation process is Intercore i7-9700H, the operation memory is 3200MHz 8 multiplied by 2GB, and the size of the hard disk is 1TB. The simulation comparison adopts the method to compare with a scheme I (a flood forecasting system based on a self-organizing mapping algorithm model) and a scheme II (a flood forecasting system based on a multi-thread multi-mode technology), extracts characteristic vectors for 26GB flood flow data, verifies the effectiveness of the research according to a microcomputer calculation data result, and summarizes experimental results into a data table as shown in Table 1.
TABLE 1 results of the experiment
In a specific embodiment, a comparison experiment is further completed by comparing the information identification precision of each monitoring system, simulation of the comparison process is realized according to MTALAB software, a comparison graph of the prediction precision of the three types of flood forecasting systems is obtained as shown in FIG. 5, in the specific embodiment, the comparison in FIG. 5 shows that the prediction precision of the three types of flood forecasting systems has certain fluctuation, but the maximum prediction precision of the flood forecasting system based on the hydrological model is 97.744%, which is far higher than that of the other two scheme methods, so that the processing requirement on complex flood forecasting information is met, and the forecasting precision is improved.
Although specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are merely illustrative and that various omissions, substitutions and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention; for example, it is within the scope of the present invention to combine the steps of the above-described methods to perform substantially the same function in substantially the same way to achieve substantially the same result; accordingly, the scope of the invention is to be limited only by the following claims.
Claims (7)
1. A flood forecasting system based on hydrologic model is characterized in that: the flood forecasting system based on the hydrological model comprises:
the man-machine interaction module is used for controlling the flood flow of the flood discharge facility so as to carry out flood regulation calculation on the flood flow;
the rainfall radar detection station is used for detecting meteorological targets of the location of the flood in real time;
the flood simulation module is used for simulating and acquiring flood flow data and rainfall flow data through a TOPKAPI hydrological model;
the data receiving and processing module is used for receiving flood flow data and rainfall flow data and analyzing and processing the received flood flow data and rainfall flow data by adopting an AdaBoost classifier;
the flood simulation database is used for storing and defining the flood flow data and the rainfall flow data through the hierarchical model database;
the GIS subsystem is used for displaying the unit grid flood flow data and rainfall flow data of each detection period by a graphic table;
the user terminal is used for transmitting the data information received by the data receiving and processing module to the public network in a GPRS wireless communication mode to inform the user terminal;
the rainfall radar detection station is unidirectionally connected to the data receiving and processing module, the flood simulation module is unidirectionally connected to the data receiving and processing module and the flood simulation database, the data receiving and processing module is bidirectionally connected with the human-computer interaction module, the human-computer interaction module is unidirectionally connected to the GIS subsystem, and the GIS subsystem is unidirectionally connected to the wireless communication network;
the flood simulation module simulates flood flow through a TOPKAPI hydrological model, in the upstream flood simulation module part, the grid unit defined by the bottom DEM describes the terrain of a flood basin, and the flood flow is supposed to be concentrated on the firstiAnd each DEM grid unit, the basic equations for expressing the flood flow phenomenon are a continuity equation and a flow equation, and the expression function is as follows:
in the formula (1), the reaction mixture is,Hthe average soil moisture content on the vertical axis is shown,tit is shown that the acquisition period is,Xrepresenting the terrain space of a flood basinThe size of the glass fiber is measured,y r the water content of the residual soil is shown,y s which represents the water content of the saturated soil,Lthe thickness of the surface soil layer is shown,qrepresenting the horizontal flow width flux in the soil,
the slope of the surface is indicated as,k s it is shown that the water conductivity is saturated,prepresenting the precipitation intensity; the actual total water content function of the soil on the vertical axis of the DEM grid unit is expressed as:
in the formula (2), the reaction mixture is,
indicating the actual total water content of the soil on the vertical axis, subscriptrIndicating residual English word abbreviations, subscriptssRepresenting the saturated english word abbreviation, substituted into equation (1), the local conductance is:
in the formula (3), the reaction mixture is,Crepresenting a local conductivity coefficient; the topographic space size in the flood basin is realized by the formula (3)XTo (1) aiThe integral equation obtained on each DEM unit is as follows:
in the formula (4), the reaction mixture is,Vs i is stored iniVolume per unit width in individual DEM grid cells, volume of water stored in each DEM grid cell and total water content
Correlation, as shown in equation (5):
substituting the formula (5) into the formula (4), simplifying to obtain a general unit, writing a nonlinear reservoir equation, wherein the total inflow of the upstream flood simulation module into the DEM grid unit is shown as the formula (6):
in the formula (6), the reaction mixture is,Qrepresenting the total inflow from the upstream flood simulation module into the DEM grid unit; in a downstream flood simulation module part, according to simulation programs of upstream floods in formulas (1) to (6), assuming that the surface water depth is constant, and integrating on the longitudinal dimension to obtain the firstiThe nonlinear reservoir equation of each DEM grid unit is shown as the formula (7):
in the formula (7), the reaction mixture is,Vo i is the firstiVolume, subscript, of surface water in individual DEM grid cellsoRepresenting a surface word abbreviation and representing a surface word abbreviation,r 1 is the saturation excess produced by soil water; for a tree-shaped channel network with a rectangular cross section and a width increasing with the increase of the drainage area, the non-linear reservoir equation of a general channel section can be written as formula (8):
in the formula (8), the reaction mixture is,Vc i is thatiThe amount of water, subscript, stored in the river coursecThe method represents the word abbreviation of the river reach,r 2 is used for the input of the side drainage,Wis a river reachThe width of (a) is greater than (b),Qcis the total flow of the downstream flood simulation module, and is calculated according to the TOPKAPI hydrological modelQ c +QAnd obtaining the total flow of the flood simulation output.
2. A hydrologic model based flood forecasting system according to claim 1, characterized in that: the rainfall radar detection station consists of a radar station and four raindrop spectrum monitoring stations, wherein the radar station consists of a transmitter, a receiver, a signal processor, a servo system, a power supply and distribution system, a radar control terminal and a data processing terminal and is used for realizing real-time detection of surrounding meteorological targets such as clouds, raindrops and hailstones, and the radar station and the central station carry out data transmission and command interaction through a wired network; the raindrop spectrum monitoring station consists of a laser raindrop spectrum meter, a data acquisition device and a solar power supply system, and is used for monitoring a rainfall velocity spectrum and a rainfall particle size spectrum, calibrating radar monitoring data according to the rainfall velocity spectrum and the rainfall particle size spectrum, and monitoring rainfall.
3. A hydrologic model based flood forecasting system according to claim 1, characterized in that: the flood forecasting system comprises an intelligent early warning module, a time period of 1 hour is set, basic monitoring information is collected and is transmitted by a file transfer protocol to be uniformly output to a data receiving and processing module, the collected information is collected and analyzed, the received data information is compared with database standard data information, the running state is judged to be normal, warning and error reporting are carried out, the running state is displayed on a GIS subsystem, meanwhile, warning and reminding are carried out on a background, and error reporting information is processed by operation and maintenance personnel.
4. A hydrologic model based flood forecasting system according to claim 1, characterized in that: the flood simulation module comprises an upstream flood simulation module and a downstream flood simulation module; the upstream flood simulation module is used for simulating rainfall input water quantity and flood surface flowing water quantity, and the downstream flood is used for simulating flood underground flowing water quantity;
the upstream flood simulation module consists of a flow detection module, a penetration detection module, a rainfall speed detection module and a stock calculation module;
the downstream flood simulation module consists of an evaporation capacity detection module, a penetration detection module, a relief water loss detection module and a flow rate detection module.
5. A hydrologic model based flood forecasting system according to claim 1, characterized in that: on a single DEM grid cell within the integral domain, the amount of air precipitation simulated over a 1 hour period is fixed and all precipitation reaching the soil will penetrate unless the soil in this DEM grid cell is already saturated.
6. A hydrologic model based flood forecasting system according to claim 1, characterized in that: the flood forecasting system is transmitted to a public network user terminal in a GPRS wireless communication mode, the user terminal is divided into a common user terminal and an administrator terminal, the common user terminal browses map data and geographical flood basin rainfall information, and flood forecasting information comprising accumulated rainfall and rainfall probability is forecasted through a flood observation API and a rainfall forecast API; the management terminal is an authorized agent of the operation service, checks the flood situation after receiving the flood forecast message, acquires the big data flood situation through the internet of things technology, updates the flood situation and the flood data, learns the crowd-sourced flood situation after the flood situation, and approves the message and updates the flood forecast.
7. A hydrologic model based flood forecasting system according to claim 1, characterized in that: the AdaBoost classifier classifies the features of the flood flow data into a strong classifier and a weak classifier, adaboost performs iterative training on the weak classifier, and the weak classifier trained in each stage participates in the iteration of the weak classifier in the next round to finally become the strong classifier; suppose AdaBoost classifier totalsNAnd the characteristic parameters are arranged from large to small, and are obtained by distinguishing:
in the formula (9), the reaction mixture is,Rrepresenting the flood flow data concentration,Tbefore showingkThe dispersion of the flood flow data,w k is shown askThe individual flood flow data weights are used to determine,g k to identify flood flow data type values; if it is firstkIf the individual flood flow data is positive flood flow data, theng k =1; if it is firstkThe individual flood water flow data is the negative flood water flow data, otherwiseg k = —1；
In the AdaBoost classifier processing process, the strong classifier initializes the flood flow data weight towCalculating the firstjWeighted error rate of strong classifierPAs shown in equation (10):
in the formula (10), the reaction mixture is,xrepresenting a strong classifier;
the meaning of the function isjThe flood flow data classification result of each strong classifier adjusts the target weight value of each flood flow data according to the optimal strong and weak classification result, as shown in formula (11):
and updating the classification target flood flow data parameters according to the calculation result, distinguishing the flood flow data parameters, and finishing the deep processing of the flood flow data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211365022.9A CN115422782B (en) | 2022-11-03 | 2022-11-03 | Flood forecasting system based on hydrological model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211365022.9A CN115422782B (en) | 2022-11-03 | 2022-11-03 | Flood forecasting system based on hydrological model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115422782A CN115422782A (en) | 2022-12-02 |
| CN115422782B true CN115422782B (en) | 2023-01-13 |
Family
ID=84208348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211365022.9A Active CN115422782B (en) | 2022-11-03 | 2022-11-03 | Flood forecasting system based on hydrological model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115422782B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809743B (en) * | 2022-12-28 | 2024-04-16 | 应急管理部国家自然灾害防治研究院 | Situation awareness and emergency evaluation method and system for flood-breaking disaster |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298841A (en) * | 2013-07-16 | 2015-01-21 | 杭州贵仁科技有限公司 | Flood forecasting method and system based on historical data |
| CN105139093A (en) * | 2015-09-07 | 2015-12-09 | 河海大学 | Method for forecasting flood based on Boosting algorithm and support vector machine |
| CN106529739A (en) * | 2016-11-30 | 2017-03-22 | 福建四创软件有限公司 | Gridding-based flood prediction method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AR109623A1 (en) * | 2018-02-16 | 2019-01-09 | Pescarmona Enrique Menotti | PROCESS AND SYSTEM OF ANALYSIS AND HYDROLOGICAL MANAGEMENT FOR BASINS |
-
2022
- 2022-11-03 CN CN202211365022.9A patent/CN115422782B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298841A (en) * | 2013-07-16 | 2015-01-21 | 杭州贵仁科技有限公司 | Flood forecasting method and system based on historical data |
| CN105139093A (en) * | 2015-09-07 | 2015-12-09 | 河海大学 | Method for forecasting flood based on Boosting algorithm and support vector machine |
| CN106529739A (en) * | 2016-11-30 | 2017-03-22 | 福建四创软件有限公司 | Gridding-based flood prediction method |
Non-Patent Citations (1)
| Title |
|---|
| 基于洪水模拟和预报的三维仿真***设计";王浩等;《中国防汛抗旱》;20140630;第 24 卷(第 3 期);第24-27页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115422782A (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7228235B2 (en) | System and method for enhanced measure-correlate-predict for a wind farm location | |
| Pozdnoukhov et al. | Spatio-temporal avalanche forecasting with Support Vector Machines | |
| Singla et al. | Predictability of soil moisture and river flows over France for the spring season | |
| CN115422782B (en) | Flood forecasting system based on hydrological model | |
| KR20200048232A (en) | Method of assessing stream drying and apparatuses performing the same | |
| Avanzi et al. | Information content of spatially distributed ground-based measurements for hydrologic-parameter calibration in mixed rain-snow mountain headwaters | |
| Requena et al. | Flood frequency analysis at ungauged sites based on regionally estimated streamflows | |
| CN114399193A (en) | Method for detecting runoff events in data-deficient areas based on depth time sequence point process and LSTM | |
| Wang et al. | Evaluation of multi‐source precipitation data in a watershed with complex topography based on distributed hydrological modeling | |
| Henao Salgado et al. | Assessing flood early warning systems for flash floods | |
| Huang et al. | Tropical cyclone full track simulation in the western North Pacific based on random forests | |
| CN114372631A (en) | Data-lacking area runoff prediction method based on small sample learning and LSTM | |
| Haddjeri et al. | Exploring the sensitivity to precipitation, blowing snow, and horizontal resolution of the spatial distribution of simulated snow cover | |
| Ma et al. | Extreme wind speed prediction in mountainous area with mixed wind climates | |
| Kheyruri et al. | Quantification of the meteorological and hydrological droughts links over various regions of Iran using gridded datasets | |
| Zahraie et al. | SST clustering for winter precipitation prediction in southeast of Iran: Comparison between modified K-means and genetic algorithm-based clustering methods | |
| Lu et al. | Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions | |
| Blanchet et al. | Explaining rainfall accumulations over several days in the French Alps using low-dimensional atmospheric predictors based on analogy | |
| Liu et al. | GNSS-derived PWV and meteorological data for short-term rainfall forecast based on support vector machine | |
| Nguyen et al. | Water level prediction at tich-bui river in vietnam using support vector regression | |
| Zanella et al. | Internet of things for hydrology: Potential and challenges | |
| Yariyan et al. | Evaluating novel hybrid models based on GIS for snow avalanche susceptibility mapping: A comparative study | |
| Zhu et al. | Long lead-time radar rainfall nowcasting method incorporating atmospheric conditions using long short-term memory networks | |
| Oliaye et al. | A new approach to weather radar adjustment for heavy rainfall events using ANFIS-PSO | |
| Pavía Santolamazza | Event-based flood estimation using a random forest algorithm for the regionalization in small catchments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |