CN115293241A - River bank collapse early warning method and device based on multi-source data fusion - Google Patents
River bank collapse early warning method and device based on multi-source data fusion Download PDFInfo
- Publication number
- CN115293241A CN115293241A CN202210810907.9A CN202210810907A CN115293241A CN 115293241 A CN115293241 A CN 115293241A CN 202210810907 A CN202210810907 A CN 202210810907A CN 115293241 A CN115293241 A CN 115293241A
- Authority
- CN
- China
- Prior art keywords
- bank
- early warning
- collapse
- river
- bank collapse
- 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 55
- 230000004927 fusion Effects 0.000 title claims abstract description 44
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 73
- 239000004576 sand Substances 0.000 claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000011160 research Methods 0.000 claims abstract description 18
- 238000003066 decision tree Methods 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 29
- 239000002689 soil Substances 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 15
- 238000004088 simulation Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 239000002245 particle Substances 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000009991 scouring Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000002310 reflectometry Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 210000000476 body water Anatomy 0.000 claims description 3
- 239000011148 porous material Substances 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 230000008021 deposition Effects 0.000 claims description 2
- 238000005315 distribution function Methods 0.000 claims description 2
- 230000003628 erosive effect Effects 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 239000012535 impurity Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 235000003930 Aegle marmelos Nutrition 0.000 description 1
- 240000003273 Passiflora laurifolia Species 0.000 description 1
- 235000005138 Spondias dulcis Nutrition 0.000 description 1
- 235000001667 Vitex agnus castus Nutrition 0.000 description 1
- 244000063464 Vitex agnus-castus Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004422 calculation algorithm 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
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis 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
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Revetment (AREA)
Abstract
The invention provides a river bank collapse early warning method and device based on multi-source data fusion, which comprehensively consider various influence factors of water and sand conditions and river bank boundary conditions, can comprehensively identify the bank collapse strength of a bank collapse prone area, and has high objectivity and reliability. The method comprises the following steps: step 1: determining a bank collapse prone area; step 2: calculating the bank collapse probability; and step 3: calculating the bank collapse width; and 4, step 4: calculating the width of the dike beach; and 5: calculating the housing area of residents near the river in the research area; step 6: dividing early warning limits of all indexes according to the early warning indexes of the bank collapse probability, the bank collapse width, the width of an out-of-embankment beach and the residential housing area of residents near the river; and 7: fusing index calculation results; and step 8: weighting the indexes; and step 9: determining the bank collapse early warning comprehensive grade; step 10: and giving out bank collapse early warning grade division results of main bank collapse regions of the research river reach, and drawing early warning information on a river situation map according to the bank collapse early warning grade division results to obtain a river bank collapse early warning information map.
Description
Technical Field
The invention belongs to the technical field of bank collapse monitoring and early warning, and particularly relates to a river bank collapse early warning method and device based on multi-source data fusion.
Technical Field
The bank collapse is an important component for the deformation of the fluvial river bed, but the large-scale bank collapse phenomenon not only influences the stability of the river behavior of a local river section, but also threatens the safety of important wading projects such as embankments, water intakes, bridges and the like, and increases the flood control pressure. After the three gorges project is applied, the clear water is discharged downwards to cause continuous scouring of the riverbeds at the middle and lower reaches of the Yangtze river, and the stability of the river bank is reduced.
The bank collapse phenomenon has very complex mechanism and various influence factors, and belongs to the interdisciplinary problem of river dynamics and soil mechanics. Since 1980, many researchers at home and abroad carry out bank caving research, reveal specific influences of different influencing factors on bank caving, provide a calculation method for stability of bank slopes in different collapse modes and a bank caving process simulation method in different scales, but the existing research does not clear interaction mechanisms among the factors, so that the bank caving process is still difficult to predict. In addition, the existing bank collapse early warning technology is not completely mature, bank collapse early warning indexes are not uniform, grading means are various, and grade setting has obvious difference, so that results obtained by the methods are difficult to convert mutually, and strong subjective experience exists.
Disclosure of Invention
In order to solve the technical problems, the invention provides a river bank collapse early warning method and a river bank collapse early warning device based on multi-source data fusion, wherein the river bank collapse early warning method comprises the following steps:
< method >
The invention provides a river bank collapse early warning method based on multi-source data fusion, which is characterized by comprising the following steps of:
step 1: determining a bank collapse prone area;
acquiring monitoring data of a research river reach, and primarily selecting a bank collapse and prone area according to the trend of a deep body and the historical bank collapse situation;
step 2: calculating the bank collapse probability P, comprising the following substeps:
step 2-1: according to the actually measured section terrain, whether the specific section is broken in a specific year is marked, and the bank where the bank is broken is marked as 1, otherwise, the bank is marked as 0;
step 2-2: selecting water and sand factors and river boundary condition factors, wherein the water and sand factors mainly comprise the following 13 factors: annual average flow rate Q and sand transport rate Q s Maximum daily average flow Q max To the maximum daily average sand transport rate Q s,max Flood plain duration T f River channel water-discharge rate R d Ratio of water to water slope S u And S l Relative position of, hong, L t P for bank protection, N number of soil layering layers, height difference H of beach groove and thickness H of cohesive soil layer c (ii) a The data of the 13 factors can form a data set of the specific section CS under the specific year, and is marked as S cs-year Data set S cs-year The included data are:
S cs-year ＝{Q，Q s ，Q max ，Q s,max ，T f ，R d ，S u ，S l ，L t ，P，N，H，H c }；
step 2-3: constructing a random forest model, and calculating the bank collapse probability P under the specific water sand condition, wherein the steps are as follows:
(1) Sampling: integrating actually measured water and sand and river boundary condition data of different sections and different years to form a total sample set with n S cs-year A data set; based on Bootstrap sampling method, randomly selecting m S in the S samples each time cs-year Data set forming sub-training sample set D i Each sub-training sample set D i Contains m × 13 data;
(2) Calculate the degree of purity of the kini factor by factor: each sub-training sample set D i A decision tree can be constructed, M 'influencing factors are randomly selected from M bank collapse influencing factors on each node of the decision tree, and the Gini purities (D) of the M' influencing factors at the node are respectively calculated;
(3) Determining node segmentation factors, and constructing a decision tree: selecting an influence factor corresponding to the minimum kiney impure degree as a segmentation factor of the node until the splitting depth of the decision tree reaches a preset depth, and finishing the construction of the decision tree;
(4) Calculating the bank collapse probability: will verify the set T i Putting the data into a constructed decision tree, and segmenting node by node to obtain classification results of bank collapse and non-bank collapse, wherein the proportion of the number of nodes which are judged to be in the bank collapse to the total depth is a sub-training sample set D i The calculated bank collapse probability p of the CS of a certain section under year Ti (c/v)。
(5) Repeating random sampling for r times to form r sub-training sample sets D 1 、D 2 、D 3 ……D r Building r decision trees and using verification set T i Calculating the corresponding probability p of bank collapse t (c/v)(t＝T 1 ，T 2 ……T r ) And averaging the values to obtain the final bank collapse probability P:
in the formula, c represents the forecast of collapse, v represents the total sample value, and p (c/v) represents the probability of the occurrence of the collapse under the condition of specific water and sand;
and step 3: simulating a bank collapse process, and calculating a bank collapse width B;
and 4, step 4: calculating the width W of the dike beach according to the water body index;
and 5: calculating the housing area Ar of residents near the river in the research area;
step 6: dividing early warning limits of all indexes by taking the bank collapse probability P, the bank collapse width Bd, the width W of an out-of-embankment beach and the housing area Ar of residents near the river as early warning indexes;
and 7: fusing index calculation results based on Dempster-Shafer evidence theory;
and 8: respectively weighting four indexes of the probability of bank collapse, the width of the outer beach of the embankment and the area of the house near the river i I =1,2,3,4. The weight value is calibrated according to the actual bank collapse situation.
And step 9: determining the bank collapse early warning comprehensive grade;
step 10: and giving out bank collapse early warning grade division results of main bank collapse regions of the researched river reach, and drawing early warning information on a river situation map according to the bank collapse early warning grade division results to obtain a river bank collapse early warning information map.
Preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 3, firstly, calculating the water flow elements and the riverbed scouring and silting amplitude of each section through a one-dimensional water-sand dynamics module; according to the water flow conditions obtained by calculation, the scouring degree of the slope toe of the river bank is calculated, and a seepage module is adopted to calculate the variation process of the water level in the soil body of the river bank of each section; and finally, taking parameters such as water flow conditions, riverbed scouring amplitude, soil body water content and pore water pressure as input parameters of the bank collapse module, calculating the stability degree of the soil body of the riverbank, judging whether the soil body is collapsed or not, and calculating the bank collapse width Bd.
Preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 4, firstly, a high-quality remote sensing image data set in a research area and a flood season period is obtained by downloading from a geospatial data cloud; and then, calculating an improved water body index MNDWI by utilizing the green light and short wave infrared band earth surface reflectivity images:
MNDWI＝(ρ GREEN -ρ SWIR )/(ρ GREEN +ρ SWIR )；
in the formula, ρ GREEN And rho SWIR Surface reflectance of green light and short wave infrared band respectively;
judging the water body and the river bank part in the image through the MNDWI water body index, and extracting river bank line coordinates; and then, importing the coordinates of the large embankment into a map, comparing the position of the bank line with the position of the large embankment in the flood season, and calculating to obtain the transverse distance between the bank line and the large embankment to be used as the width W of the beach outside the embankment.
Preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 6, taking the bank collapse probability P, the bank collapse width Bd, the width W of the beach outside the embankment and the residential housing area Ar near the river as pre-alarm indexes; dividing each index into four levels A to D according to the numerical value, wherein A to C correspond to I to III level early warning, and D corresponds to no early warning; dividing early warning limits of three indexes of the bank collapse probability P, the width W of the bank external beach body and the area Ar of the residential area near the river by adopting a natural discontinuity classification method;
for the bank collapse width, dividing the bank collapse with the annual average bank collapse width larger than 80m into A and the like; when the particle size is between 50 and 80m, the particle size is divided into B and the like; when the particle size is between 20 and 50m, the particle size is divided into C and the like; and less than 20m, D is obtained.
Preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 7, a class set U = { a, B, C, D }, a class P (P ∈ U) to which each index belongs is determined according to a calculated value of the index, and a probability distribution function m at the class is determined i (P) value is set to 1.0, m for the remaining ranks i (P) is set to 0.0; and m of each level of a certain index i (P) the sum is 1, i.e. the relation:
preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 9, for the composite rank P, the probability assignment function m (P) is calculated using the following equation:
and selecting the grade corresponding to the maximum probability value m (P) as the final bank collapse early warning comprehensive grade.
Preferably, the river bank collapse early warning method based on multi-source data fusion provided by the invention can also have the following characteristics: in step 9, after the bank collapse early warning comprehensive grade result is obtained, based on the actual bank collapse situation, the reasonability of the early warning comprehensive grade calculation result is judged: if the deviation is large, the weight is adjusted, and calculation and judgment are carried out again until the early warning comprehensive grade calculation result is reasonable.
< means >
Further, the present invention also provides a river bank collapse pre-alarm device based on multi-source data fusion, which automatically implements the above < method >, and is characterized by comprising:
the easy-to-send area determining part is used for acquiring monitoring data of a research river reach and preliminarily determining an easy-to-send area for bank collapse according to the trend of deep body and the historical bank collapse situation;
the bank collapse probability calculation unit calculates a bank collapse probability P by the following steps:
step 2-1: according to the actually measured section terrain, whether the specific section is broken in a specific year is marked, and the bank where the bank is broken is marked as 1, otherwise, the bank is marked as 0;
step 2-2: selecting water and sand factors and river channel boundary condition factors, wherein the water and sand factors mainly comprise the following 13 factors: annual average flow rate Q and sand transport rate Q s Maximum daily average flow Q max With maximum daily average sand transport rate Q s,max Flood plain duration T f River channel water-discharge rate R d Ratio of water to water u And S l Hong relative position L t P for bank protection, N number of soil layering layers, height difference H of beach groove and thickness H of cohesive soil layer c (ii) a The data of the 13 factors can form a data set of the specific section CS under the specific year, and is marked as S cs-year Data set S cs-year The included data are:
S cs-year ＝{Q，Q s ，Q max ，Q s,max ，T f ，R d ，S u ，S l ，L t ，P，N，H，H c }；
step 2-3: constructing a random forest model, and calculating the bank collapse probability P under the specific water sand condition, wherein the steps are as follows:
(1) Sampling: integrating actually measured water and sand with different sections and different years and river course boundary condition data to form a total sample set with n S cs-year A data set; based on Bootstrap sampling method, randomly selecting m S in the S samples each time cs-year Data set composition sub-trainingSample set D i Each sub-training sample set D i Contains m × 13 data;
(2) Calculate the degree of purity of the kini factor by factor: each sub-training sample set D i A decision tree can be constructed, M 'influencing factors are randomly selected from M bank collapse influencing factors on each node of the decision tree, and the Gini (D) purities of the M' influencing factors at the node are respectively calculated;
(3) Determining node segmentation factors, and constructing a decision tree: selecting an influence factor corresponding to the minimum kiney impure degree as a segmentation factor of the node until the splitting depth of the decision tree reaches a preset depth, and finishing the construction of the decision tree;
(4) Calculating the bank collapse probability: will verify the set T i Data are sequentially put into a constructed decision tree, classification results of bank collapse and bank non-collapse are obtained by node-by-node segmentation, and the proportion of the number of nodes which are judged to be bank collapse to the total depth is the sub-training sample set D i Calculating the bank collapse probability of CS (section) under year
(5) Repeating random sampling for r times to form r sub-training sample sets D 1 、D 2 、D 3 ……D r Building r decision trees and using verification set T i Calculating the corresponding probability p of bank collapse t (c/v)(t＝T 1 ，T 2 ……T r ) And averaging the values to obtain the final bank collapse probability P:
in the formula, c represents the prediction of collapse, v represents the total sample value, and p (c/v) represents the probability of occurrence of bank collapse under the condition of specific water sand;
the simulation calculation part simulates a bank collapse process and calculates the bank collapse width B;
a beach width calculation unit for calculating the width W of the dike out of the beach according to the water index;
a housing area calculation unit which calculates a housing area Ar of residents near the river in the study area;
the warning limit dividing part is used for dividing the warning limit of each index by taking the bank collapse probability P, the bank collapse width Bd, the width W of the beach outside the dike and the housing area Ar of residents near the river as the warning indexes;
a fusion calculation part for fusing the index calculation result based on Dempster-Shafer evidence theory;
a weight assignment part for respectively assigning weights w to four indexes of the bank collapse probability, the bank collapse width, the width of the out-of-the-bank beach and the area of the residential houses near the river i ，i＝1,2,3,4；
The early warning grade determining part is used for determining the bank collapse early warning comprehensive grade;
the early warning part is used for giving out bank collapse early warning grade division results of main bank collapse regions of the researched river reach and generating early warning information on a river situation map according to the bank collapse early warning grade division results to obtain a river bank collapse early warning information map;
and the control part is in communication connection with the easy-to-send area determining part, the land collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assigning part, the early warning grade determining part and the early warning part, and controls the operation of the easy-to-send area determining part, the land collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assigning part, the early warning grade determining part and the early warning part.
Preferably, the river bank collapse early warning device based on multi-source data fusion provided by the invention can also have the following characteristics: and the input display part is communicated and connected with the easy-to-send area determining part, the bank collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assigning part, the early warning grade determining part, the early warning part and the control part, and is used for enabling a user to input an operation instruction and displaying data and files of the corresponding part in a text, table or graphic mode according to the operation instruction.
Preferably, the river bank collapse early warning device based on multi-source data fusion provided by the invention can also have the following characteristics: the early warning part displays early warning information in corresponding areas on a river situation map by using corresponding colors according to the early warning grade dividing results of the river channel bank collapse on an early warning information map, distinguishes different early warning grades by using different colors, sends emergency bank collapse early warning information to a mobile or fixed terminal of a user in charge of the safety of the engineering building in the area within preset time when the early warning grade of the area reaches a preset threshold value, and simultaneously carries out key prompt in the area on the river situation map.
Action and Effect of the invention
The method comprises the steps of selecting a water sand factor and a river course boundary condition factor based on a large amount of actually measured data such as water sand, terrain, remote sensing images and the like, constructing a random forest model, establishing a relation between multiple factors and bank collapse phenomena, determining the probability value of bank collapse occurring in a bank collapse region within a specific year, calculating the width W of an outburst beach according to a water body index, dividing an early warning limit, fusing data of two indexes of the bank collapse strength and the bank collapse hazard degree by adopting a Dempster-Shafer evidence theory, identifying and dividing the early warning level of the river course bank collapse, and obtaining a river bank collapse early warning information map. According to the method, various influence factors of water and sand conditions and river bank boundary conditions are comprehensively considered, the bank collapse strength of the zone prone to bank collapse can be comprehensively identified, and data fusion, bank collapse early warning identification and division results mainly depend on actual measurement data, so that the method is weak in experience and high in objectivity and reliability.
Drawings
Fig. 1 is a flowchart of a river bank collapse early warning method based on multi-source data fusion according to an embodiment of the present invention;
FIG. 2 is a flow chart of calculating a bank collapse probability based on a random forest model according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a calculation result of the width W of the bank external beach body and the residential area a of the riverside residents of the embodiment of the invention, wherein the width W of the bank external beach body is a fixed cross section of the chaste tree 45R;
fig. 4 is a diagram of bank collapse early warning information in the downstream Jingjiang river section in the middle Yangtze river within 2020 years according to an embodiment of the present invention.
Detailed Description
The river bank collapse early warning method and device based on multi-source data fusion according to the present invention are described in detail below with reference to the accompanying drawings.
< example >
As shown in fig. 1, the river bank collapse early warning method based on multi-source data fusion provided by this embodiment includes the following steps:
step 1: and determining the collapse area. Investigating and researching the monitoring data of the river reach, and primarily selecting a bank collapse and easy-to-develop area according to the trend of deep body and the historical bank collapse situation.
Step 2: and calculating the bank collapse probability P.
Step 2.1: according to the actual measurement section terrain, whether the specific section is broken in a specific year is marked, and the river bank with broken bank is marked as 1, otherwise, the river bank is marked as 0.
Step 2.2: selecting water and sand factors and river channel boundary condition factors, wherein the water and sand factors mainly comprise the following 13 factors: annual average flow (Q) and sand transport rate (Q) s ) Maximum daily average flow (Q) max ) And maximum daily average sand transport rate (Q) s,max ) Flood plain duration (T) f ) River channel water-discharge rate (R) d ) The ratio of water to water (S) u And S l ) Relative position of, body (L) t ) Whether the revetment is performed or not (P), the layering number of the soil body (N), the height difference of the beach groove (H) and the thickness of the cohesive soil layer (H) c ). The data of the factors are derived from terrain monitoring data of fixed sections of midstream of the Yangtze river and conventional monitoring data of each hydrological station or water level station. The data of the 13 factors can form a data set of any section (CS) under a specific year (year), and is marked as S cs-year For example, the data set of the section of the golden apple 45R in 2018 is marked as S 45R-2018 . Data set S cs-year The included data are:
S cs-year ＝{Q，Q s ，Q max ，Q s,max ，T f ，R d ，S u ，S l ，L t ，P，N，H，H c }；
step 2.3: and (3) constructing a random forest model to calculate the probability P of bank collapse under the condition of specific water sand, wherein a schematic diagram of a calculation flow is shown in FIG. 2. The method comprises the following steps:
(1) And (6) sampling. Integrating actually measured water and sand and river boundary condition data of different sections and different years to form a total sample set with n S cs-year And (4) data groups. Selecting 80% of S cs-year The data set is training set D, and the remaining 20% data set is validation set T i . Based on Bootstrap sampling method, training set D is sampled in a place-back manner, and m S of training set D are randomly selected each time cs-year Data set forming sub-training sample set D i Each sub-training sample set D i Contains m × 13 data.
(2) The degree of purity of the kini was calculated factor by factor. Each sub-training sample set D i A decision tree can be constructed, M 'influencing factors are randomly selected from M bank collapse influencing factors on each node of the decision tree, and the Gini (D) purity of the M' influencing factors at the node is respectively calculated. Specifically, for a certain influence factor, a characteristic value can be randomly selected in the value range, and data is divided into two types according to the characteristic value. For example, assume a sub-training sample set D i In the b data groups, the value of the influence factor is larger than the value, the data groups are divided into right branches and are regarded as a 'bank collapse is the prediction result' group, and if b data groups exist in the data groups 1 The description that the river bank mark corresponding to the data group is 1 is divided correctly, and the probability of correct prediction is p k1 ＝b 1 B; is (b-b) 1 ) The mark of each data group as 0 indicates the partition error, and the probability of the prediction error is 1-p k1 . Similarly, if the value of the influence factor in (m-b) data groups is smaller than the value, the data groups are divided into groups of which the prediction result is not bank collapse and the left branch is divided into b data groups 2 The statement that the corresponding bank label for each data set is also 0 is predicted correctly with a probability of p k2 ＝b 2 V (m-b); has (m-b) 2 ) The mark of each data group is 1, the division error is shown, and the probability of the prediction error is 1-p k2 . From this, the degree of Gini (D) of the influence factor at the value of the characteristic can be calculated:
and in the value range, selecting different characteristic values for multiple times, calculating Gini (D), and selecting the value corresponding to the minimum Gini impure degree as the segmentation value of the influence factor.
(3) And determining node segmentation factors and constructing a decision tree. And comparing Gini (D) of the M' influence factors at a certain node, and selecting the influence factor corresponding to the minimum Gini impure degree as the segmentation factor of the node. And sequentially dividing the decision tree downwards until the splitting depth of the decision tree reaches a preset depth, and completing the construction of the decision tree. Generally, the number n of the decision trees is basically stable after being more than 100-120, and the depth can roughly determine a value range according to the number of training samples and the number of influence factors. Of the combinations of these two parameter values, the one that best predicts the model is selected as the final parameter. Through tests, 200 decision trees are constructed in the example, the depth of each decision tree is 20, and the requirements of prediction performance on recall rate can be met.
(4) And calculating the bank collapse probability. Will verify the set T i Data set S of cs-year Sequentially put into i In the constructed decision tree, the nodes are segmented one by one, and each node can obtain the classification result of bank collapse or bank non-collapse. Wherein the proportion of the number of nodes which are judged to be bank collapse to the total depth is the bank collapse probability of a certain section CS under a certain year for the sub-training sample set Di
(5) Repeating random sampling for r times to form r sub-training sample sets D 1 、D 2 、D 3 ……D r Building r decision trees and using verification set T i Calculating the corresponding probability p of bank collapse t (c/v)(t＝T 1 ，T 2 ……T r ) And averaging the two to obtain the final bank collapse probability P of the section CS under year of the year:
in the formula, c represents the predicted collapse, v represents the total sample value, and p (c/v) represents the probability of the occurrence of the collapse under the specific water sand condition.
Generally, the recall rate of the bank collapse and the recall rate of the bank collapse not occurring in the calculation result of the verification set are both more than 80%, and the trained model can be considered to have better prediction performance. The random forest algorithm may be implemented using code based on the python language.
And step 3: simulating the bank collapse process, and calculating the bank collapse width Bd. The specific contents of the one-dimensional water sand movement and bank collapse process coupling model can be seen in literature [1]. The calculation process can be summarized as follows: firstly, calculating the water flow elements and riverbed scouring and silting amplitudes of all sections through a one-dimensional water-sand dynamics module; calculating the scouring degree of the slope toe of the river bank according to the water flow conditions obtained by calculation, and calculating the variation process of the water level in the soil body of the river bank of each section by adopting a seepage module; and finally, taking parameters such as water flow conditions, riverbed erosion and deposition amplitude, soil body water content, pore water pressure and the like as input parameters of the bank collapse module, calculating the stability degree of the soil body of the riverbank, judging whether the bank collapse occurs or not, and calculating the bank collapse width Bd.
And 4, step 4: and calculating the width W of the dike beach. Firstly, downloading from a geographic space data cloud to obtain a high-quality (such as Landsat series satellite Level-2 Level) remote sensing image data set in a research area and in a flood season period; and then, calculating an improved water body index MNDWI by utilizing the green light and short wave infrared band earth surface reflectivity images:
MNDWI＝(ρ GREEN -ρ SWIR )/(ρ GREEN +ρ SWIR )；
in the formula, ρ GREEN And rho SWIR The earth surface reflectivities of green light and short wave infrared wave bands respectively; in Landsat5, 7, 8 satellites, green Green light bands correspond to B2, B3, respectively, and SWIR short-infrared red light bands correspond to B5, B6, respectively.
The MNDWI water body index can judge the water body and the river bank part in the image, and the river bank line coordinate is extracted. And then, the coordinates of the large dike are imported into a map, and the transverse distance between the river bank line and the large dike, namely the width W of the beach outside the dike, can be calculated by comparing the position of the river bank line with the position of the large dike in the flood season. For example, the calculated width W of the bank outer beach body is shown in fig. 3, taking the section of the chaste 45R as an example.
And 5: the zone is divided into an upper zone and a lower zone, the upper zone and the lower zone respectively extend for 2km by taking a certain fixed section in the zone easy to collapse into the bank as a center, and then the upper zone and the lower zone respectively extend for 1.5km from a river bank line to an inner land to form a rectangular range. With the rectangular area as the research area, the residential area Ar of the residents in the research area near the river is downloaded from the Globeland30 website (http:// www.globeland30.org /), and the result is shown in FIG. 3.
Step 6: and defining each early warning index and the warning limit thereof. The probability of bank collapse, the width of the beach outside the embankment and the housing area of residents near the river are taken as early warning indexes. Each index may be divided into four levels A-D by numerical size, where A-C corresponds to a level I-III warning and D corresponds to no warning. And (3) dividing early warning limits of three indexes of the bank collapse probability P, the width W of the bank external beach body and the area Ar of the residential area near the river by adopting a natural discontinuity classification method. The natural break point hierarchy may be implemented using code based on the python language.
For the bank collapse width Bd, dividing bank collapses with the annual average bank collapse width larger than 80m into A and the like; when the particle size is between 50 and 80m, the particle size is divided into B and the like; when the particle size is between 20 and 50m, the particle size is divided into C and the like; and less than 20m, D is obtained.
And 7: and fusing index calculation results based on Dempster-Shafer (DS) evidence theory. Defining a grade set U = { A, B, C, D }, judging the grade P (P belongs to U) of each index according to the calculated value of the index, and distributing a probability function m under the grade i (P) value is set to 1.0, m for the remaining ranks i (P) was set to 0.0. And m of each level of a certain index i (P) the sum is 1, i.e. the relation:
and step 8: respectively weighting four indexes of the probability of bank collapse, the width of the outer beach of the embankment and the area of the house near the river i (i =1,2,3,4), generally, 0.3, 0.2, 0.4 and 0.1 may be taken.
And step 9: and determining the bank collapse early warning comprehensive grade. And for the comprehensive grade P, calculating a probability assignment function m (P) by using the following formula, and selecting the grade corresponding to the maximum probability value m (P) as the final bank collapse early warning comprehensive grade. And (4) judging the reasonability of the early warning comprehensive grade calculation result by combining the actual bank collapse condition. If the deviation is large (for example, the prediction result is grade I and the actual bank collapse is not serious, or the prediction result is grade IV and the actual annual bank collapse width is more than 80 m), and the like), the weight is adjusted.
Step 10: and giving out bank collapse early warning grade division results of main bank collapse prone areas of the research river reach, and drawing an early warning information map on the river situation map to obtain the bank collapse early warning information map shown in the figure 4. Table 1 shows the early warning level of the part of the collapse zone of the river section of the downstream Jingjiang river in the Yangtze river, which is divided based on the prediction result, in 2020, and the result is compared with the actual investigation condition and basically matched with the actual investigation condition.
Table 1.2020 bank collapse early warning grade division result of main bank collapse prone area of Yangtze river, middle river and downstream Jingjiang in Yangtze river
Further, the embodiment also provides a river channel bank collapse early warning device based on multi-source data fusion, which can automatically realize the method, and the device comprises an easily occurring region determining part, a bank collapse probability calculating part, a simulation calculating part, a beach width calculating part, a housing area calculating part, a warning limit dividing part, a fusion calculating part, a weight assigning part, an early warning grade determining part, an early warning part, an input display part and a control part.
The prone area determining part executes the content described in the step 1, obtains monitoring data of a research river reach, and preliminarily determines a landslide prone area according to the deep body walking direction and the historical landslide situation.
The bank collapse probability calculation unit performs the above-described operation in step 2 to calculate the bank collapse probability P.
The simulation calculation section simulates the bank collapse process and executes the contents described in the above step 3 to calculate the bank collapse width B.
The beach width calculation section executes the contents described in step 4 above, and calculates the out-of-bank beach width W from the water body index.
The housing area calculation unit executes the contents described in step 5 above, and calculates the housing area Ar of the residents near the river in the study area.
And (4) executing the content described in the step (6) by the alarm limit dividing part, and dividing the alarm limit of each index by taking the bank collapse probability P, the bank collapse width Bd, the width W of the beach outside the embankment and the housing area Ar of residents near the river as the alarm indexes.
The fusion calculation unit executes the contents described in step 7 above, and fuses the index calculation results based on the Dempster-Shafer evidence theory.
The weight assignment unit executes the contents described in the above step 8 to assign weights w to the four indexes of the probability of bank collapse, the width of the out-of-bank beach and the area of the residential houses near the river i ，i＝1,2,3,4。
The early warning level determination section executes the contents described in step 9 above to determine the bank collapse early warning comprehensive level.
The early warning part executes the content described in the step 10, gives out bank collapse early warning grade division results of main bank collapse regions of the research river reach, and generates early warning information on a river map according to the results to obtain a river bank collapse early warning information map; the early warning part displays early warning information in corresponding areas on a river situation map by using corresponding colors according to the dividing results of the early warning levels of bank collapse on a river channel bank collapse early warning information map, distinguishes different early warning levels by using different colors, sends emergency bank collapse early warning information to a mobile or fixed terminal of a user in charge of the safety of engineering buildings in the area within preset time when the early warning levels of the area reach a preset threshold value, and simultaneously carries out key prompt at the area on the river situation map.
The input display part is in communication connection with the easy-to-send area determining part, the bank collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assigning part, the early warning grade determining part and the early warning part, and is used for enabling a user to input an operation instruction and displaying data and files of the corresponding part in a text, table or graphic mode according to the operation instruction.
The control part is communicated with the easily-occurring region determining part, the land collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the warning limit dividing part, the fusion calculating part, the weight assigning part, the warning grade determining part, the warning part and the input display part to control the operation of the easily-occurring region determining part, the land collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the warning limit dividing part, the fusion calculating part, the weight assigning part, the warning grade determining part, the warning part and the input display part.
The above embodiments are merely illustrative of the technical solutions of the present invention. The river bank collapse early warning method and device based on multi-source data fusion according to the present invention are not limited to the contents described in the above embodiments, but shall be subject to the scope defined by the claims. Any modification or supplement or equivalent replacement made by a person skilled in the art on the basis of this embodiment is within the scope of the invention as claimed in the claims.
Claims (10)
1. A river bank collapse early warning method based on multi-source data fusion is characterized by comprising the following steps:
step 1: determining a bank collapse prone area;
acquiring monitoring data of a research river reach, and primarily selecting a bank collapse and prone area according to the trend of a deep body and the historical bank collapse situation;
and 2, step: calculating the bank collapse probability P, comprising the following substeps:
step 2-1: according to the actually measured section terrain, whether the specific section is broken in a specific year is marked, and the bank where the bank is broken is marked as 1, otherwise, the bank is marked as 0;
step 2-2: selecting water and sand factors and river boundary condition factors, wherein the water and sand factors mainly comprise the following 13 factors: annual average flow rate Q and sand transport rate Q s Maximum daily average flow rate Q max With maximum daily average sand transport rate Q s,max Flood plain for T f River channel water-discharge rate R d Ratio of water to water u And S l Relative position of, hong, L t Whether the bank is protected or not P, the number of the soil body layering layersN, beach groove height difference H and cohesive soil layer thickness H c (ii) a The data of the 13 factors can form a data set of the specific section CS under the specific year, and is marked as S cs-year Data set S cs-year The included data are:
S cs-year ＝{Q，Q s ，Q max ，Q s,max ，T f ，R d ，S u ，S l ，L t ，P，N，H，H c }；
step 2-3: constructing a random forest model, and calculating the bank collapse probability P under the specific water sand condition, wherein the steps are as follows:
(1) Sampling: integrating actually measured water and sand and river boundary condition data of different sections and different years to form a total sample set with n S cs-year A data set; based on Bootstrap sampling method, randomly selecting m S in the S samples each time cs-year Data set forming sub-training sample set D i Each sub-training sample set D i Contains m × 13 data;
(2) Calculate the degree of purity of the kini factor by factor: each sub-training sample set D i A decision tree can be constructed, M 'influencing factors are randomly selected from M bank collapse influencing factors on each node of the decision tree, and the Gini impurity degree (D) of the M' influencing factors at the node is respectively calculated;
(3) Determining node segmentation factors, and constructing a decision tree: selecting an influence factor corresponding to the minimum kiney impure degree as a segmentation factor of the node until the splitting depth of the decision tree reaches a preset depth, and finishing the construction of the decision tree;
(4) Calculating the bank collapse probability: will verify the set T i Putting the data into a constructed decision tree, and segmenting node by node to obtain classification results of bank collapse and bank non-collapse, wherein the proportion of the number of nodes which are judged to be bank collapse to the total depth is the sub-training sample set D i Calculating the bank collapse probability of CS (section) under year
(5) Repeating random sampling for r times to form r sub-training sample sets D 1 、D 2 、D 3 ……D r R decision trees are established and the verification set T is used i Calculating the corresponding probability p of bank collapse t (c/v)(t＝T 1 ，T 2 ……T r ) And averaging the values to obtain the final bank collapse probability P:
in the formula, c represents the forecast of collapse, v represents the total sample value, and p (c/v) represents the probability of the occurrence of the collapse under the condition of specific water and sand;
and step 3: simulating a bank collapse process, and calculating a bank collapse width B;
and 4, step 4: calculating the width W of the dike beach according to the water body index;
and 5: calculating the housing area Ar of residents near the river in the research area;
step 6: dividing early warning limits of all indexes by taking the bank collapse probability P, the bank collapse width Bd, the width W of the outer beach of the embankment and the residential housing area Ar near the river as early warning indexes;
and 7: fusing index calculation results based on Dempster-Shafer evidence theory;
and step 8: respectively weighting four indexes of the probability of bank collapse, the width of the outer beach of the embankment and the area of the house near the river i ，i＝1,2,3,4；
And step 9: determining the bank collapse early warning comprehensive grade;
step 10: and giving out bank collapse early warning grade division results of main bank collapse regions of the researched river reach, and drawing early warning information on a river situation map according to the bank collapse early warning grade division results to obtain a river bank collapse early warning information map.
2. The river bank collapse early warning method based on multi-source data fusion as claimed in claim 1, wherein:
in step 3, firstly, calculating the water flow elements and the riverbed scouring and silting amplitude of each section through a one-dimensional water-sand dynamics module; calculating the scouring degree of the slope toe of the river bank according to the water flow conditions obtained by calculation, and calculating the variation process of the water level in the soil body of the river bank of each section by adopting a seepage module; and finally, taking parameters such as water flow conditions, riverbed erosion and deposition amplitude, soil body water content and pore water pressure as input parameters of the bank collapse module, calculating the stability degree of the soil body of the river bank, judging whether the soil body is collapsed or not, and calculating the bank collapse width Bd.
3. The river bank collapse early warning method based on multi-source data fusion as claimed in claim 1, wherein:
in step 4, firstly, downloading from a geospatial data cloud to obtain a high-quality remote sensing image data set in a research area and a flood season period; and then, calculating an improved water body index MNDWI by utilizing the green light and short wave infrared band earth surface reflectivity images:
MNDWI＝(ρ GREEN -ρ SWIR )/(ρ GREEN +ρ SWIR )；
in the formula, ρ GREEN And rho SWIR The earth surface reflectivities of green light and short wave infrared wave bands respectively;
judging the water body and the bank part in the image through the MNDWI water body index, and extracting the bank line coordinate; and then, importing the coordinates of the levee into a map, comparing the position of the bank line in the flood season with the position of the levee, and calculating to obtain the transverse distance between the bank line and the levee as the width W of the beach outside the levee.
4. The river bank collapse early warning method based on multi-source data fusion according to claim 1, characterized in that:
in step 6, taking the bank collapse probability P, the bank collapse width Bd, the width W of the beach outside the embankment and the housing area Ar of residents near the river as early warning indexes; dividing each index into four levels A to D according to the numerical value, wherein A to C correspond to I to III level early warning, and D corresponds to no early warning; dividing early warning limits of three indexes of the bank collapse probability P, the width W of the bank external beach body and the area Ar of the residential area near the river by adopting a natural discontinuity classification method;
for the bank collapse width, dividing the bank collapse with the annual average bank collapse width larger than 80m into A and the like; when the particle size is between 50 and 80m, the particle size is divided into B and the like; when the particle size is between 20 and 50m, the particle size is divided into C and the like; and when it is smaller than 20m, it is divided into D, etc.
5. The river bank collapse early warning method based on multi-source data fusion according to claim 1, characterized in that:
in step 7, a class set U = { a, B, C, D }, a class P (P ∈ U) to which each index belongs is determined according to a calculated value of the index, and a probability distribution function m at the class is determined i (P) value is set to 1.0, m for the remaining ranks i (P) is set to 0.0; and m of each level of a certain index i (P) the sum is 1, i.e. the relation:
6. the river bank collapse early warning method based on multi-source data fusion according to claim 1, characterized in that:
wherein, in step 9, for the composite rank P, the probability assignment function m (P) is calculated with the following formula:
and selecting the grade corresponding to the maximum probability value m (P) as the final bank collapse early warning comprehensive grade.
7. The river bank collapse early warning method based on multi-source data fusion according to claim 1, characterized in that:
in step 9, after the bank collapse early warning comprehensive grade result is obtained, the reasonability of the early warning comprehensive grade calculation result is judged based on the actual bank collapse condition: and if the deviation is larger, adjusting the weight, and calculating and judging again until the early warning comprehensive grade calculation result is reasonable.
8. River course rips bank early warning device based on multisource data fusion, its characterized in that includes:
the easy-to-send area determining part is used for acquiring monitoring data of a research river reach and preliminarily determining a bank collapse easy-to-send area according to the body trend and the historical bank collapse situation;
the bank collapse probability calculation unit calculates a bank collapse probability P by the following steps:
step 2-1: according to the actually measured section terrain, whether the specific section is broken in a specific year is marked, and the bank where the bank is broken is marked as 1, otherwise, the bank is marked as 0;
step 2-2: selecting water and sand factors and river boundary condition factors, wherein the water and sand factors mainly comprise the following 13 factors: annual average flow rate Q and sand transport rate Q s Maximum daily average flow Q max With maximum daily average sand transport rate Q s,max Flood plain duration T f River channel water-discharge rate R d Ratio of water to water u And S l Relative position of, hong, L t P for bank protection, N number of soil layering layers, height difference H of beach groove and thickness H of cohesive soil layer c (ii) a The data of the 13 factors can form a data set of the specific section CS under the specific year, and is marked as S cs-year Data set S cs-year The included data are:
S cs-year ＝{Q，Q s ，Q max ，Q s,max ，T f ，R d ，S u ，S l ，L t ，P，N，H，H c }；
step 2-3: constructing a random forest model, and calculating the bank collapse probability P under the specific water sand condition, wherein the steps are as follows:
(1) Sampling: integrating actually measured water and sand with different sections and different years and river course boundary condition data to form a total sample set with n S cs-year A data set; based on Bootstrap sampling method, randomly selecting m S in the S samples each time cs-year Data set composition sub-training sample set D i Each sub-training sample set D i Contains m × 13 data;
(2) Calculate the degree of purity of the kini factor by factor: each sub-training sample set D i A decision tree can be constructed, randomly from each node of the decision treeM 'of the M bank collapse influence factors are selected, and the Gini (D) of the M' influence factors at the node is calculated respectively;
(3) Determining node segmentation factors, and constructing a decision tree: selecting an influence factor corresponding to the minimum kini impure degree as a segmentation factor of the node until the splitting depth of the decision tree reaches a preset depth, and finishing the construction of the decision tree;
(4) Calculating the bank collapse probability: will verify the set T i Putting the data into a constructed decision tree, and segmenting node by node to obtain classification results of bank collapse and bank non-collapse, wherein the proportion of the number of nodes which are judged to be bank collapse to the total depth is the sub-training sample set D i Calculating the bank collapse probability of CS (section) under year
(5) Repeating random sampling for r times to form r sub-training sample sets D 1 、D 2 、D 3 ……D r R decision trees are established and the verification set T is used i Calculating the corresponding probability p of bank collapse t (c/v)(t＝T 1 ，T 2 ……T r ) And averaging the values to obtain the final bank collapse probability P:
in the formula, c represents the prediction of collapse, v represents the total sample value, and p (c/v) represents the probability of occurrence of bank collapse under the condition of specific water sand;
the simulation calculation part simulates the bank collapse process and calculates the bank collapse width B;
a beach width calculation unit for calculating the width W of the dike out of the beach according to the water index;
a housing area calculation unit which calculates a housing area Ar of residents near the river in the study area;
the alarm limit dividing part is used for dividing the alarm limit of each index by taking the bank collapse probability P, the bank collapse width Bd, the width W of the beach outside the embankment and the residential housing area Ar near the river as the early warning indexes;
a fusion calculation part for fusing the index calculation result based on Dempster-Shafer evidence theory;
a weight assignment part for respectively assigning weights w to the four indexes of the bank collapse probability, the bank collapse width, the width of the out-of-the-bank beach and the area of the residential houses near the river i ，i＝1,2,3,4；
The early warning grade determining part is used for determining the bank collapse early warning comprehensive grade;
the early warning part is used for giving out bank collapse early warning grade division results of main bank collapse regions of the researched river reach and generating early warning information on a river situation map according to the bank collapse early warning grade division results to obtain a river bank collapse early warning information map;
and the control part is in communication connection with the easy-to-send area determining part, the bank collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assignment part, the early warning grade determining part and the early warning part and controls the operation of the easy-to-send area determining part, the bank collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the alarm limit dividing part, the fusion calculating part, the weight assignment part, the early warning grade determining part and the early warning part.
9. The river bank collapse early warning device based on multisource data fusion of claim 8, further comprising:
and the input display part is in communication connection with the easy-to-send area determining part, the bank collapse probability calculating part, the simulation calculating part, the beach width calculating part, the housing area calculating part, the police limit dividing part, the fusion calculating part, the weight assignment part, the early warning grade determining part, the early warning part and the control part, and is used for enabling a user to input an operation instruction and displaying data and files of the corresponding parts in a text, table or graphic mode according to the operation instruction.
10. The river bank collapse early warning device based on multisource data fusion as claimed in claim 8, characterized in that:
the early warning part displays early warning information in corresponding areas on a river situation map by using corresponding colors according to the dividing results of the early warning levels of bank collapse on a river bank collapse early warning information map, distinguishes different early warning levels by using different colors, sends emergency bank collapse early warning information to a mobile or fixed terminal of a user in charge of engineering and building safety of the area within preset time when the early warning levels of the area reach a preset threshold value, and simultaneously carries out key prompt at the area on the river situation map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210810907.9A CN115293241A (en) | 2022-07-11 | 2022-07-11 | River bank collapse early warning method and device based on multi-source data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210810907.9A CN115293241A (en) | 2022-07-11 | 2022-07-11 | River bank collapse early warning method and device based on multi-source data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115293241A true CN115293241A (en) | 2022-11-04 |
Family
ID=83821845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210810907.9A Pending CN115293241A (en) | 2022-07-11 | 2022-07-11 | River bank collapse early warning method and device based on multi-source data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115293241A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541068A (en) * | 2024-01-10 | 2024-02-09 | 武汉华测卫星技术有限公司 | Unmanned ship-based bank collapse risk assessment method and system |
-
2022
- 2022-07-11 CN CN202210810907.9A patent/CN115293241A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541068A (en) * | 2024-01-10 | 2024-02-09 | 武汉华测卫星技术有限公司 | Unmanned ship-based bank collapse risk assessment method and system |
| CN117541068B (en) * | 2024-01-10 | 2024-04-02 | 武汉华测卫星技术有限公司 | Unmanned ship-based bank collapse risk assessment method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Debanshi et al. | Wetland delineation simulation and prediction in deltaic landscape | |
| CN104408900B (en) | Neutral net flood warning devices and methods therefor based on dynamic optimization | |
| CN103218522B (en) | A kind of method and device for dividing flood disaster risk grade | |
| CN104898183B (en) | Heavy rain urban waterlogging modelling evaluation method | |
| Huang et al. | Using multiple-criteria decision-making techniques for eco-environmental vulnerability assessment: a case study on the Chi-Jia-Wan Stream watershed, Taiwan | |
| CN107704592A (en) | A kind of flood forecasting service construction method based on WebGIS | |
| CN104318085B (en) | Torrential flood risk identification and extraction method of drainage basins | |
| CN113409550B (en) | Debris flow disaster early warning method and system based on runoff convergence simulation | |
| CN113470333A (en) | Risk assessment and monitoring early warning system for shallow landslide of line engineering corridor | |
| Zhou et al. | Spatiotemporal Variations of Land Use and Landscape Ecological Risk in a Resource-Based City, from Rapid Development to Recession. | |
| CN110459036A (en) | A kind of mountain torrents method for early warning based on deep learning | |
| CN103870995A (en) | High and cold sand land vegetation recovery potential estimation method | |
| CN116306340A (en) | Method for simulating urban waterlogging risk distribution under different working conditions | |
| CN115293241A (en) | River bank collapse early warning method and device based on multi-source data fusion | |
| Adnan | Quantifying the impacts of climate and land use changes on the hydrological response of a monsoonal catchment | |
| Khaddari et al. | A comparative analysis of analytical hierarchy process and fuzzy logic modeling in flood susceptibility mapping in the Assaka Watershed, Morocco | |
| HaileFekadu et al. | Landslide susceptibility assessment using GIS on rock-soil slope along zabidar mountain road corridors, Ethiopia | |
| Kwak et al. | A study on the extraction of multi-factor influencing floods from RS image and GIS data; a case study in Nackdong Basin, S. Korea | |
| Nguyen et al. | A framework for flood depth using hydrodynamic modeling and machine learning in the coastal province of Vietnam | |
| Li et al. | Analysing post-earthquake landslide susceptibility using multi-temporal landslide inventories—a case study in Miansi Town of China | |
| Kewessa | Evaluation of flood mitigation alternatives for flood prone area of upper awash sub-basin (upstream of Koka Dam) a master’s thesis | |
| Fan | Understanding the causes and effects of earthquake-induced landslide dams | |
| Kang | Geospatial analysis of specific degradation in South Korea | |
| Ibeabuchi | Mapping Seasonal Flood Inundation and Developing an Early Warning System for Lagos Metropolis (Nigeria): A study between 1990 and 2011 | |
| Ward et al. | Climate adaptation in the city of Jakarta |
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 |