CN117251973B - Flood disaster avoidance route determination method - Google Patents
Flood disaster avoidance route determination method Download PDFInfo
- Publication number
- CN117251973B CN117251973B CN202311498557.8A CN202311498557A CN117251973B CN 117251973 B CN117251973 B CN 117251973B CN 202311498557 A CN202311498557 A CN 202311498557A CN 117251973 B CN117251973 B CN 117251973B
- Authority
- CN
- China
- Prior art keywords
- flood
- node
- risk
- network
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 20
- 238000012546 transfer Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000010586 diagram Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000003062 neural network model Methods 0.000 claims abstract description 7
- 238000011160 research Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 239000013598 vector Substances 0.000 claims description 2
- 230000008447 perception Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000006424 Flood reaction Methods 0.000 description 6
- 238000012876 topography Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/265—Personal security, identity or safety
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Geometry (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Mathematical Optimization (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Analysis (AREA)
Abstract
The invention discloses a flood disaster avoidance route determining method, which is used for collecting related data such as river basin geographic information, landform type, water system distribution, population cultivated land distribution, water conservancy facility distribution, road network distribution and the like, and carrying out visual display on river basin geographic basic information and human information space distribution conditions according to the related data; determining the connection relation between key nodes of a risk network and nodes, and drawing a river basin flood risk network diagram; constructing a drainage basin flood map neural network model by applying a map neural network algorithm according to the flood risk network map; historical flood disaster observation and flood data in an input stream domain are used for training the model; setting a typical flood model, calculating flood risks of each node by using the model, and drawing an optimal flood disaster avoidance route; according to the invention, flood risk transfer and transfer processes of different areas in the flow area can be fully considered from the system angle, a scientific flood disaster avoidance route is formulated, and the method has very important significance for flood disaster treatment.
Description
Technical Field
The invention relates to a flood disaster coping technology, in particular to a flood disaster avoiding route determining method.
Background
When flood disasters occur, the rapid and accurate determination of the disaster avoidance route is a key for guaranteeing the life and property safety of people, and the existing technical scheme is based on experience and personal judgment, lacks scientificity and systemicity, and is difficult to meet actual demands. In addition, the prior art scheme often ignores consideration of various factors such as flood speed, submerging depth, road condition and the like, and cannot provide a comprehensive and accurate route for disaster avoidance personnel. There is therefore a need for a flood disaster avoidance route determination method.
Disclosure of Invention
The invention aims to provide a flood disaster avoiding route determining method.
In order to achieve the above purpose, the invention is implemented according to the following technical scheme:
the invention comprises the following steps:
s1, collecting drainage basin and humane data, including drainage basin water system distribution, digital elevation model, hydraulic engineering facilities, population cultivated land data, road network data and traffic infrastructure data in the drainage basin;
s2, visually displaying the river basin water system, the populated areas, the water conservancy facilities, the house distribution and the road network distribution according to the river basin geographic basic information and the humane data;
s3, determining connection relations between key nodes of the risk network and nodes, and drawing a river basin flood risk network diagram;
s4, constructing a drainage basin flood map neural network model according to the node flood inundation risks of the drainage basin flood risk network map;
s5, historical flood disaster observation and flood data in an input stream domain are used for training the model;
s6, setting a typical flood model, calculating flood risks of each node by using the model, and drawing an optimal flood disaster avoiding route.
Further, in step S1, preprocessing is performed on the drainage basin and the human data, where the preprocessing includes removing duplicate data, removing abnormal data, integrating data, converting data, and normalizing data.
Further, in step S6, if the node flood risk value in the route is greater than 0.5, defining the route as an infeasible route, and selecting a route with the smallest risk accumulation value from other routes as an optimal escape route.
Wherein R represents a risk value of a preferred disaster avoidance route,representing the risk value of the ith disaster avoidance line, < ->Representing the risk value of the i-th node in the route.
Further, in step S4, the risk transfer calculation formula of the node flooding risk includes:
（4）
wherein the method comprises the steps ofRepresenting the risk transmissibility of the target node u and node v at time t, +.>Is a nonlinear activation function [ - ]]Representing a concatenation of vectors, +.>Representing the learnable parameters of the spatial aware aggregator at time t.
Further, the watershed flood map neural network model is constructed by adopting a multi-layer feedforward network model based on a BP algorithm, layer weight adjustment is determined by learning rate, error signals output by a layer and input signals y of the layer, wherein the output layer error signals are related to the difference between expected output and actual output of the network, output errors are directly reflected, the error signals of hidden layers are related to the error signals of previous layers, the input signals are reversely transmitted layer by layer from the output layer, each node receives the input signals and carries out nonlinear transformation on the input signals, in the training process, the weight of the neural network is updated according to the errors of the network, the neural network calculates the errors between the output layer and the expected output, and the errors are reversely transmitted back to the network to update the weight of each layer.
Further, after the flood risk network graph is built by the graph neural network algorithm, model training can be performed by the graph neural network algorithm, and association relations among nodes in the network and characteristic information of each node are learned.
Further, the method for determining the node comprises the following steps: combining flood inundation risk data distribution characteristic conditions, and preliminarily selecting nodes by taking node influence factors as constraint conditions; the method comprises the following steps:
the first step: screening all candidate nodes meeting the conditions in the research area according to the node selection principle,
and a second step of: under the condition of no road resistance, selecting nodes according to time constraint conditions, namely: follow the approach
The transfer personnel can reach the node efficiently and quickly,
let d be the migration range radius, define as the distance threshold, then the time constraint condition under no road resistance is:
wherein:xi to avoid dangerous units in the dangerous area, yi As a candidate node it is possible to select,
and a third step of: under the condition of road resistance, selecting nodes according to time constraint conditions, namely: to transfer personnel
The node can be reached quickly and efficiently in a limited time, t is set as a time threshold, and the time constraint condition under the condition of the road resistance is as follows:
wherein the method comprises the steps ofTi In order for the risk avoidance unit to reach the node,
fourth step: selecting nodes according to the capacity constraint condition of the nodes, wherein the occupied area of each node is generally more than 3m < 2 > in order to ensure the normal life of node placement personnel; let v be the capacity threshold, then the node capacity constraint is:
in the method, in the process of the invention,Vi for the number of people accommodated by the node,Vi area of Placement area occupied by people
Fifth step: selecting nodes according to node security level constraint conditions, and selecting security with high security coefficient
The node is arranged in the area, but is not too high, s is set as the lowest safety coefficient under the premise of meeting the safety, and the node safety level
The constraint conditions of (2) are:
wherein:Si is the security level of the node; the security level representation method comprises the following steps: 1. representing general security, 2 representing comparative security, and 3 representing very security.
The beneficial effects of the invention are as follows:
according to the invention, flood risk transfer and transfer processes of different areas in the flow area can be fully considered from the system angle, a scientific flood disaster avoidance route is formulated, and the method has very important significance for flood disaster treatment.
Drawings
FIG. 1 is a flow chart of a flood disaster avoidance route determination method of the present invention;
FIG. 2 is a schematic diagram of basic information of a river basin in a flood disaster avoidance line determination method of the present invention;
FIG. 3 is a generalized diagram of a research area road network of the flood disaster avoidance route determination method of the present invention;
FIG. 4 is a generalized map of flood risk transfer in a research area of the flood avoidance line determination method of the present invention;
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific embodiments, wherein the exemplary embodiments and descriptions of the invention are for purposes of illustration, but are not intended to be limiting.
As shown in fig. 1, the present invention includes the steps of:
s1, collecting drainage basin and humane data, including drainage basin water system distribution, digital elevation model, hydraulic engineering facilities, population cultivated land data, road network data and traffic infrastructure data in the drainage basin;
s2, visually displaying the river basin water system, the populated areas, the water conservancy facilities, the house distribution and the road network distribution according to the river basin geographic basic information and the humane data; as shown in fig. 2, fig. 1 depicts a basic information diagram of a river basin, including river water system distribution, hydraulic engineering facilities and population farmland distribution of the river basin, and water flow direction is drawn according to water system conditions, DEM data and geological data, wherein the coverage area of blue lines in fig. 2 represents river flow direction, red arrows represent river flow direction, red triangles represent resident gathering areas, and blue rectangles represent farmlands.
S3, determining connection relations between key nodes of the risk network and nodes, and drawing a river basin flood risk network diagram;
as shown in fig. 3, a study area road network distribution map is plotted, in which green represents a smooth road and yellow represents a slow road.
S4, constructing a drainage basin flood map neural network model according to the node flood inundation risks of the drainage basin flood risk network map;
the node influencing factors are selected as the shortest withdrawal distance, the shortest withdrawal time, the node capacity and the node security
4 influencing factors such as the whole situation.
The node initial selection method comprises the following steps: combining flood inundation risk data distribution characteristic conditions, and causing node influence factor
The sub is taken as a constraint condition preliminary selection node; the detailed analysis steps are as follows:
the first step: and screening all candidate nodes meeting the conditions in the research area according to the node selection principle.
And a second step of: under the condition of no road resistance, selecting nodes according to time constraint conditions, namely: follow the approach
The transfer personnel can reach the node efficiently and quickly.
Let d be the migration range radius, define as the distance threshold, then the time constraint condition under no road resistance is:
wherein:xi to avoid dangerous units in the dangerous area, yi Is a candidate node.
And a third step of: under the condition of road resistance, selecting nodes according to time constraint conditions, namely: to transfer personnel
The node can be reached quickly and efficiently within a defined time. Let t be the time threshold, then the time constraint condition under the condition of having the road resistance is:
wherein the method comprises the steps ofTi The time required for the risk avoidance unit to reach the node.
Fourth step: and selecting the node according to the capacity constraint condition of the node. In order to ensure normal life of node placement personnel, the occupied area of each node is generally more than 3m < 2 >; let v be the capacity threshold, then the node capacity constraint is:
in the method, in the process of the invention,Vi the number of people is accommodated for the node.Vi Area of Placement area person occupancyArea of
Fifth step: and selecting the nodes according to the node security level constraint conditions. Should select a safety factor with high safety factor
The region should not be too high. Let s be the lowest security coefficient satisfying the security precondition, then the node security level
The constraint conditions of (2) are:
wherein:Si is the security level of the node;
the security level representation method comprises the following steps: 1. representing general security, 2 representing comparative security, and 3 representing very security.
Integrating the river basin foundation information and road network information, combing and integrating the information from flood source ends (water systems, hydraulic engineering and water collecting areas), flood affected ends (crowd gathering areas, industrial areas, houses and farmlands) and disaster avoiding ends (road networks), and drawing a river basin flood risk network transfer diagram. As shown in the example of fig. 4, blue circles represent flood source nodes such as rivers, red triangles represent flood affected nodes such as houses or farms, and yellow lines represent road networks.
S5, historical flood disaster observation and flood data in an input stream domain are used for training the model; and collecting historical flood peak inundation statistical data of the research area, training a model, calibrating and verifying the model, and calculating the flood inundation value of each node.
The flood risk factor information is determined by different frequency flood processes at different breach, and mainly comprises the following categories: flooding scope, flooding depth, flood flow rate, flood arrival time, flood flooding duration.
The flooding range and the flooding depth distribution characteristics of the floods at a certain moment can be obtained by counting the water depth values of all floods at the same moment; and (3) calculating the submerged water depth values of all the submerged areas at different moments, and solving the maximum value to obtain the maximum submerged water depth distribution characteristics of the floodwater of any submerged area.
And calculating the flow velocity values of all the floods at the same moment, so that the flow velocity distribution characteristics of floods at a certain moment can be obtained. And (3) calculating flood flow velocity values at different moments in all the submerged areas, and obtaining the maximum value to obtain the maximum flood flow velocity distribution characteristics of any submerged area.
The flood front arrival time distribution characteristics of the floods at a certain moment can be obtained by counting the flood front arrival time values of all floods at the same moment; and counting the earliest arrival time of flood fronts of all the inundated areas, and obtaining the shortest arrival time distribution characteristic of flood of any inundated area.
By counting the flooding time values at different flood flooding areas at the same time, the flooding duration distribution characteristics at different flood flooding areas at a certain time can be obtained. And (3) counting flood inundation calendar values at the final simulation moment of all inundation areas, and obtaining the total inundation duration distribution characteristics of the flooding in any inundation area.
S6, setting a typical flood model, calculating flood risks of each node by using the model, and drawing an optimal flood disaster avoiding route;
and calculating the risk sum of each disaster avoidance risk route, defining an infeasible route if the node flood risk value in the routes is larger than 0.5, and selecting the route with the smallest risk accumulation value from other routes as the optimal escape route.
Wherein R represents a risk value of a preferred disaster avoidance route,representing the risk value of the ith disaster avoidance line, < ->Representing the risk value of the i-th node in the route.
And applying a graph neural network algorithm on the basis of fig. 4, providing a node flood inundation risk calculation method, constructing a drainage basin graph neural network model, and adopting a risk transfer calculation formula as shown in formula 1.
（4）
Wherein R represents a risk value of a preferred disaster avoidance route,representing the risk value of the ith disaster avoidance line, < ->Representing the risk value of the i-th node in the route.
Constructing a typical flood model taking into account various factors such as rainfall, topography, river flow, reservoir level, etc., this model may be constructed using knowledge of the disciplines such as hydrology, hydraulics, and hydrophysics, etc., specifically, the rainfall may be used as input, the flood level and the flood flow of each node may be calculated through the model, the influence of the topography on the flood may also be considered, for example, where the topography is low-lying is susceptible to the influence of the flood, the flood risk of each node may be calculated by applying the model, then the flood risk of each node may be calculated using the constructed typical flood model, the geographical information data of the basin may be input into the model, the flood level and the flood flow of each node may be obtained, and then the flood risk of each node may be calculated from the flood level and the flood flow.
The flood risk for each node can be calculated by:
flood risk = flood level/critical level + flood flow/critical flow
The critical water level and the critical flow are threshold values set according to practical conditions, and are used for judging whether the nodes are affected by flood disasters, drawing an optimal flood disaster avoidance route, after calculating flood risks of each node, drawing the optimal flood disaster avoidance route, specifically, calculating the optimal disaster avoidance route according to connection relations among the nodes and geographic features around the nodes, calculating the optimal disaster avoidance route by using knowledge such as graph theory and shortest path algorithm, specifically, converting geographic information data of a river basin into a structure of a graph, and then calculating the optimal route from each node to a safe place by using a shortest path algorithm such as Dijkstra algorithm.
And finally, drawing an optimal flood disaster avoidance route map, marking the flood risk of each node, and enabling a decision maker to better know the flood risk and the optimal disaster avoidance route in the flow area through the map, so that flood prevention and disaster reduction measures are better formulated.
Taking a four-stage cascade hydroelectric junction group as an example, when the upstream precipitation reaches 100 years, and the gradient and intensity are unchanged, the flood peak flow at the downstream outlet is 50 years, when the upstream precipitation reaches 100 years, the gradient and intensity are changed remarkably, the flood peak flow at the downstream outlet is far more than hundred years,
the technical scheme of the invention is not limited to the specific embodiment, and all technical modifications made according to the technical scheme of the invention fall within the protection scope of the invention.
Claims (4)
1. A flood disaster avoidance route determining method is characterized in that: the method comprises the following steps:
s1, collecting drainage basin and humane data, including drainage basin water system distribution, digital elevation model, hydraulic engineering facilities, population cultivated land data, road network data and traffic infrastructure data in the drainage basin;
s2, visually displaying the river basin water system, the populated areas, the water conservancy facilities, the house distribution and the road network distribution according to the river basin geographic basic information and the humanization data;
s3, determining connection relations between key nodes of a risk network, drawing a river basin flood risk network diagram, defining an infeasible route if a node flood risk value is greater than 0.5 in the route, and selecting a route with the minimum risk accumulation value from other routes as an optimal escape route;
wherein R represents a risk value for a preferred disaster avoidance route,representing the risk value of the ith disaster avoidance line, < ->A risk value representing an i-th node in the route;
s4, constructing a drainage basin flood map neural network model according to the node flood inundation risk of the drainage basin flood risk network map, wherein a risk transfer calculation formula of the node flood inundation risk comprises:
（4）
wherein the method comprises the steps ofRepresenting the risk transmissibility of the target node u and node v at time t, +.>Is a nonlinear activation function [ - ]]Representing a concatenation of vectors, +.>The method for determining the node represents the learnable parameters of the space perception aggregator at the time t comprises the following steps: combining flood inundation risk data distribution characteristic conditions, and preliminarily selecting nodes by taking node influence factors as constraint conditions; the method comprises the following steps:
the first step: screening all candidate nodes meeting the conditions in the research area according to the node selection principle,
and a second step of: under the condition of no road resistance, selecting nodes according to time constraint conditions, namely: the method is characterized in that a nearby rule is followed, so that a transfer person can efficiently and quickly reach a node, d is set as a migration range radius and defined as a distance threshold, and the time constraint condition under the condition of no road resistance is as follows:
wherein:xi to avoid dangerous units in the dangerous area, yi As a candidate node it is possible to select,
and a third step of: under the condition of road resistance, selecting nodes according to time constraint conditions, namely: to transfer personnel
The node can be reached quickly and efficiently in a limited time, t is set as a time threshold, and the time constraint condition under the condition of the road resistance is as follows:
wherein the method comprises the steps ofTi In order for the risk avoidance unit to reach the node,
fourth step: selecting nodes according to the capacity constraint condition of the nodes, wherein the occupied area of each node is generally more than 3m < 2 > in order to ensure the normal life of node placement personnel; let v be the capacity threshold, then the node capacity constraint is:
in the method, in the process of the invention,Vi for the number of people accommodated by the node,Vi area of Placement area occupied by people
Fifth step: selecting a node according to the constraint condition of the node security level, wherein a location area with high security coefficient is selected, but is not too high, and s is set as the lowest security coefficient under the condition of meeting the security premise, and the constraint condition of the node security level is as follows:
wherein:Si is the security level of the node; the security level representation method comprises the following steps: 1. representing general safety, 2 representing relatively safe, and 3 representing very safe;
s5, historical flood disaster observation and flood data in an input stream domain are used for training the model;
s6, setting a typical flood model, calculating flood risks of each node by using the model, and drawing an optimal flood disaster avoiding route.
2. The flood disaster avoidance line determination method of claim 1, wherein: in step S1, preprocessing is performed on the drainage basin and the humanization data, where the preprocessing includes removing duplicate data, removing abnormal data, integrating data, converting data, and normalizing data.
3. The flood disaster avoidance line determination method of claim 1, wherein: the watershed flood map neural network model is constructed by adopting a multi-layer feedforward network model based on a BP algorithm, layer weight adjustment is determined by learning rate, error signals output by a layer and input signals y of the layer, wherein the error signals of the output layer are related to the difference between expected output and actual output of the network, the output errors are directly reflected, the error signals of hidden layers are related to the error signals of the previous layers, the input signals are reversely transmitted layer by layer from the output layer, each node receives the input signals and carries out nonlinear transformation on the input signals, the weight of the neural network is updated according to the errors of the network in the training process, the neural network calculates the errors between the output layer and the expected output, and the errors are reversely transmitted back to the network to update the weight of each layer.
4. The flood disaster avoidance line determination method of claim 1, wherein: after the flood risk network graph is built by using the graph neural network algorithm, model training can be performed by using the graph neural network algorithm, and association relations among nodes in the network and characteristic information of each node are learned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311498557.8A CN117251973B (en) | 2023-11-13 | 2023-11-13 | Flood disaster avoidance route determination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311498557.8A CN117251973B (en) | 2023-11-13 | 2023-11-13 | Flood disaster avoidance route determination method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117251973A CN117251973A (en) | 2023-12-19 |
| CN117251973B true CN117251973B (en) | 2024-02-20 |
Family
ID=89126642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311498557.8A Active CN117251973B (en) | 2023-11-13 | 2023-11-13 | Flood disaster avoidance route determination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117251973B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079595A (en) * | 2019-12-04 | 2020-04-28 | 天津大学 | Novel concept and intelligent risk identification method for dynamic flood risk graph |
| CN114444791A (en) * | 2022-01-19 | 2022-05-06 | 国网新疆电力有限公司电力科学研究院 | Flood disaster remote sensing monitoring and evaluation method based on machine learning |
| CN115115262A (en) * | 2022-07-20 | 2022-09-27 | 湖南省水利水电科学研究院 | Flood risk disaster assessment method |
| CN116187608A (en) * | 2023-02-01 | 2023-05-30 | 青岛理工大学 | Underground traffic facility evacuation path decision method, system and equipment in flood environment |
| US11721191B1 (en) * | 2022-05-16 | 2023-08-08 | Chengdu Qinchuan Iot Technology Co., Ltd. | Method and system for flood early warning in smart city based on internet of things |
| CN116702959A (en) * | 2023-05-22 | 2023-09-05 | 河海大学 | Flood forecasting method based on distributed self-adaptive graph attention network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674099B (en) * | 2021-08-27 | 2022-07-05 | 中国农业科学院农业环境与可持续发展研究所 | Comprehensive risk assessment method for drought and waterlogging disasters of apples |
-
2023
- 2023-11-13 CN CN202311498557.8A patent/CN117251973B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079595A (en) * | 2019-12-04 | 2020-04-28 | 天津大学 | Novel concept and intelligent risk identification method for dynamic flood risk graph |
| CN114444791A (en) * | 2022-01-19 | 2022-05-06 | 国网新疆电力有限公司电力科学研究院 | Flood disaster remote sensing monitoring and evaluation method based on machine learning |
| US11721191B1 (en) * | 2022-05-16 | 2023-08-08 | Chengdu Qinchuan Iot Technology Co., Ltd. | Method and system for flood early warning in smart city based on internet of things |
| CN115115262A (en) * | 2022-07-20 | 2022-09-27 | 湖南省水利水电科学研究院 | Flood risk disaster assessment method |
| CN116187608A (en) * | 2023-02-01 | 2023-05-30 | 青岛理工大学 | Underground traffic facility evacuation path decision method, system and equipment in flood environment |
| CN116702959A (en) * | 2023-05-22 | 2023-09-05 | 河海大学 | Flood forecasting method based on distributed self-adaptive graph attention network |
Non-Patent Citations (13)
| Title |
|---|
| 万州区滑坡灾害风险评价与管理研究;王芳;《中国优秀硕士学位论文数据库》(第1期);第1-100页 * |
| 单九生 ; 徐星生 ; 樊建勇 ; 管珉 ; .基于GIS的BP神经网络洪涝灾害评估模型研究.江西农业大学学报.2009,(第04期),全文. * |
| 基于BP神经网络的农户生计风险评价模型;苏芳;李景坤;许韶华;;冰川冻土(第06期);全文 * |
| 基于BP神经网络的北江流域洪灾风险评价;赖成光;王兆礼;宋海娟;;水电能源科学(第03期);全文 * |
| 基于BP神经网络的洪涝灾害风险评价――以杭埠河流域为例;程先富;匡毅;赵阳;;皖西学院学报(第02期);全文 * |
| 基于GIS的BP神经网络洪涝灾害评估模型研究;单九生;徐星生;樊建勇;管珉;;江西农业大学学报(第04期);全文 * |
| 孙章丽 ; 朱秀芳 ; 潘耀忠 ; 刘宪锋 ; .洪水灾害风险分析进展与展望.灾害学.2017,(第03期),全文. * |
| 崔鹏 ; 苏凤环 ; 邹强 ; 陈宁生 ; 张镱锂 ; .青藏高原山地灾害和气象灾害风险评估与减灾对策.科学通报.2015,(第32期),全文. * |
| 洪水灾害风险分析进展与展望;孙章丽;朱秀芳;潘耀忠;刘宪锋;;灾害学(第03期);全文 * |
| 程先富 ; 匡毅 ; 赵阳 ; .基于BP神经网络的洪涝灾害风险评价――以杭埠河流域为例.皖西学院学报.2015,(第02期),全文. * |
| 苏芳 ; 李景坤 ; 许韶华 ; .基于BP神经网络的农户生计风险评价模型.冰川冻土.2017,(第06期),全文. * |
| 赖成光 ; 王兆礼 ; 宋海娟 ; .基于BP神经网络的北江流域洪灾风险评价.水电能源科学.2011,(第03期),全文. * |
| 青藏高原山地灾害和气象灾害风险评估与减灾对策;崔鹏;苏凤环;邹强;陈宁生;张镱锂;;科学通报(第32期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117251973A (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Haque | Risk assessment, emergency preparedness and response to hazards: The case of the 1997 Red River Valley flood, Canada | |
| CN114240119A (en) | Digital twin-based flood control and waterlogging prevention system and early warning method for whole elements of territorial universe | |
| Sivakumar | Flood mitigation strategies adopted in Sri Lanka a review | |
| Seckin | Modeling flood discharge at ungauged sites across Turkey using neuro-fuzzy and neural networks | |
| Bahramifar et al. | An anfis-based approach for predicting the manning roughness coefficient in alluvial channels at the bank-full stage | |
| Garcia et al. | Sea-level rise and flooding in coastal riverine flood plains | |
| CN114511990A (en) | Debris flow probability measuring and calculating method and debris flow multi-factor cooperative monitoring and early warning method | |
| CN110187413A (en) | A kind of urban waterlogging forecasting procedure, electronic equipment and storage medium | |
| CN110232479A (en) | A kind of city flood control by reservoir regulation compensation optimizing dispatching method | |
| Ouyang | Input optimization of ANFIS typhoon inundation forecast models using a Multi-Objective Genetic Algorithm | |
| CN117251973B (en) | Flood disaster avoidance route determination method | |
| Voronin et al. | The Problem of Safe Evacuation of Large Floodplains Population During Flooding. | |
| CN105590034A (en) | Flood prevention and disaster reduction capability evaluation model | |
| Wei et al. | Multireservoir flood-control optimization with neural-based linear channel level routing under tidal effects | |
| Lin et al. | Automatic calibration of an unsteady river flow model by using dynamically dimensioned search algorithm | |
| Egawa et al. | A water flow forecasting for dam using neural networks and regression models | |
| CN115358526A (en) | Urban waterlogging early warning method and device, electronic equipment and storage medium | |
| Nam et al. | Flood forecasting and early warning for river basins in Central Vietnam | |
| Susetyo | Urban flood management in Surabaya City: anticipating changes in the Brantas River system | |
| Roushangar et al. | Suitability of different modelling strategies in predicting of solid load discharge of an alluvial river | |
| Tu et al. | Flood hazard and risk assessment of Hoang Long River basin, Vietnam | |
| Ackerman et al. | Hydrologic and hydraulic models for performing dam break studies | |
| Shankar et al. | Flood modeling for a part of Adyar river basin using HEC-HMS and HEC-RAS for the December 2015 floods | |
| Yu et al. | Optimal sizing of urban drainage systems using heuristic optimization | |
| CN117953648A (en) | Mountain torrent disaster early warning method and system based on distributed hydrologic model |
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 |