CN116432820A - Flood inundation evolution prediction and early warning method and system - Google Patents

Flood inundation evolution prediction and early warning method and system Download PDF

Info

Publication number
CN116432820A
CN116432820A CN202310213361.3A CN202310213361A CN116432820A CN 116432820 A CN116432820 A CN 116432820A CN 202310213361 A CN202310213361 A CN 202310213361A CN 116432820 A CN116432820 A CN 116432820A
Authority
CN
China
Prior art keywords
flood
data
early warning
inundation
evolution
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
Application number
CN202310213361.3A
Other languages
Chinese (zh)
Inventor
李珊
张炜
周毅波
尹立群
黄伟翔
俸波
陈千懿
奉斌
黎新
王乐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electric Power Research Institute of Guangxi Power Grid Co Ltd
Original Assignee
Electric Power Research Institute of Guangxi Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Electric Power Research Institute of Guangxi Power Grid Co Ltd filed Critical Electric Power Research Institute of Guangxi Power Grid Co Ltd
Priority to CN202310213361.3A priority Critical patent/CN116432820A/en
Publication of CN116432820A publication Critical patent/CN116432820A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/14—Rainfall or precipitation gauges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G06N3/045—Combinations of 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • 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
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Molecular Biology (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Hardware Design (AREA)
  • Ecology (AREA)
  • Marketing (AREA)
  • Atmospheric Sciences (AREA)
  • Environmental Sciences (AREA)
  • Geometry (AREA)
  • Primary Health Care (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Fluid Mechanics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)

Abstract

The invention belongs to the technical field of flood early warning, and particularly relates to a flood submerged evolution prediction early warning method and system. According to the method, a shallow water equation numerical simulation result is used as data drive, and a ConvLSTM prediction model is constructed. Under the condition of lacking a large amount of actual data, the accuracy of the flooding range and the flooding depth of the flood evolution prediction is ensured, the speed of the flood flooding evolution prediction is greatly improved, and important support is provided for people's life and property transfer arrangement and emergency plan response.

Description

Flood inundation evolution prediction and early warning method and system
Technical Field
The invention belongs to the technical field of flood early warning, and particularly relates to a flood submerged evolution prediction early warning method and system.
Background
The domestic research on flood inundation evolution prediction is mainly based on coupling of a hydrological model and various hydraulic models, and solving of improved and optimized numerical models by using a finite volume method, a finite element method, a finite difference method and the like, for example, in Wangyang and the like, hydrological models and application thereof in flood risk analysis [ J ], yu Fujiang and the like, resistance characteristic research [ J ] of different house distributions in flood inundation based on a hydrological hydrodynamic coupling model, uozhen and the like, xie Yifan, improved multi-scale finite element method, solving of two-dimensional subsurface water flow problems [ D ], zheng Supei and the like, and moving grid rotation flux method [ J ], li Xiaotian and the like, and cement paste rheological distribution algorithm [ J ] based on particle flow interaction theory. Although the numerical method can accurately simulate the flow of flood evolution, the time consumed by model establishment and numerical solution is too long, and the time requirement of quick emergency response cannot be met. Meanwhile, compared with the subjects of medical science, finance and the like, which are easy to obtain a large amount of data, the flood evolution prediction can use less practical data, because obtaining time series data of a large amount of flood inundation in a specific area is not practical in both economy and engineering.
The evolution of floods has a physically definite constitutive equation containing important priori information of water flow, and the deep learning algorithm can make predictions on the flood evolution through the priori information in the absence of a large amount of actual data. And the numerical simulation result controlled by the hydraulic physical model is used for constructing a deep learning model, so that the flood flooding prediction early warning speed is greatly improved on the basis of ensuring the flooding range and the accuracy of the flooding depth of the flood flooding prediction. However, a prediction and early warning method and a system for flood inundation do not exist at present.
Disclosure of Invention
In order to solve the problems, the invention provides a flood inundation evolution prediction and early warning method and a system, and the specific technical scheme is as follows:
a flood inundation evolution prediction and early warning method comprises the following steps:
step S1, flood dynamic time sequence data S in a period of time within a grid is obtained;
s2, acquiring rainfall forecast data in the grid every n hours in the future;
step S3, obtaining analog numerical data of flood flow by using a shallow water equation based on the flood dynamic time sequence data S obtained in the step S1;
s4, training a ConvLSTM model based on the numerical simulation data of the flood flow obtained in the step S3;
step S5, inputting the future n-hour time-by-time rainfall forecast data acquired in the step S2 into the ConvLSTM model trained in the step S4, and respectively forecasting the flooding evolution data of the future n-hour time-by-time in the grid, wherein the flooding evolution data specifically comprises a flooding range and flooding water level data;
and S6, sending out an early warning signal when the predicted submerged water level exceeds a preset safety value.
Preferably, the size of the grid in the step S1 is 101×101km.
Preferably, the flood dynamic time series data S in the step S1 includes the water level, x-direction flow rate and y-direction flow rate of the flood.
Preferably, the shallow water equation in the step S3 includes:
the continuous equation:
Figure BDA0004114098470000021
equation of motion:
Figure BDA0004114098470000022
Figure BDA0004114098470000023
bottom surface resistance term:
Figure BDA0004114098470000031
Figure BDA0004114098470000032
flux:
M＝uh； (6)
N＝vh； (7)
wherein: h represents the flood depth; h represents a flood level; u represents the flow rate of flood in x direction; v represents the velocity of flow in the y direction of the flood; m represents flood x-direction flux; n represents flood y-direction flux; τ xb And τ yb Respectively representing the ground resistance of the flood in the x and y directions; g represents the gravitational acceleration m/s; ρ represents the water density; n represents the roughness coefficient in the Manning coefficient.
Preferably, in the step S4, the flood dynamics S at time t is determined t And inputting rainfall forecast data Q within t+1h into a trained ConvLSTM model, wherein the forecast value is flood dynamic S at t+1h t+1 The flood dynamics comprises three dimensions, namely a flow velocity u in the direction of the water level H, x and a flow velocity v in the direction of y.
Preferably, n=6 hours in step S2.
Preferably, the analog numerical data of the flood flow in the step S3 is specifically a drainage basin unit line.
Preferably, the flooding scope in step S4 is specifically: output value flood dynamics S of ConvLSTM model t+1 The sum of the x-direction flow velocity u, the y-direction flow velocity v and the integration area of the future n hours from hour to hour.
The flood inundation evolution prediction early warning system is applied to the method and comprises a flood dynamic data acquisition module, a rainfall forecast data acquisition module, a flood simulation data acquisition module, a model training module, a flood inundation evolution prediction module and an early warning module;
the flood dynamic data acquisition module, the flood simulation data acquisition module, the model training module, the flood submerged evolution prediction module and the early warning module are connected in sequence; the rainfall forecast data acquisition module is respectively connected with the model training module and the flood inundation evolution prediction module;
the flood dynamic data acquisition module is used for acquiring flood dynamic time sequence data in a period of time within a grid;
the rainfall forecast data acquisition module is used for acquiring rainfall forecast data time by time in the future n hours in the grid; the flood simulation data acquisition module is used for acquiring simulation numerical data of flood flow based on the acquired flood dynamic time sequence data S and by utilizing a shallow water equation;
the model training module is used for training a ConvLSTM model based on the obtained numerical simulation data of the flood flow;
the flood inundation evolution prediction module is used for inputting the obtained future n-hour time-by-time rainfall forecast data into a trained ConvLSTM model to respectively predict the future n-hour time-by-time flood inundation evolution data in the grid, wherein the flood inundation evolution data comprises a inundation range and inundation water level data;
and the early warning module is used for sending an early warning signal when the predicted submerged water level exceeds a preset safety value.
The beneficial effects of the invention are as follows: according to the method, a shallow water equation numerical simulation result is used as data drive, and a ConvLSTM prediction model is constructed. Under the condition of lacking a large amount of actual data, the accuracy of the flooding range and the flooding depth of the flood evolution prediction is ensured, the speed of the flood flooding evolution prediction is greatly improved, and important support is provided for people's life and property transfer arrangement and emergency plan response.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 is a flow chart of the system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Example 1:
the specific embodiment of the invention provides a flood inundation evolution prediction and early warning method, which comprises the following steps: step S1, flood dynamic time sequence data S in a period of time within a grid is obtained; the size of the grid is 101 x 101km. The flood dynamic time series data S includes the water level of the flood, the flow rate in x and y directions.
And S2, acquiring rainfall forecast data time by time in the future 6 hours within the grid 101 multiplied by 101km.
Cleaning the collected data, which specifically comprises:
deleting the acquired null value; performing deduplication on the acquired and repeated data; replacing the missing value by an average value; deleting the abnormal value directly; carrying out standardized processing on the data; the processed data were processed as 6:2:2 are divided into training data samples, test data samples and verification data samples.
And step S3, obtaining the analog numerical data of the flood flow by using a shallow water equation based on the flood dynamic time sequence data S obtained in the step S1. The physical model of flood evolution belongs to hydraulics, in order to ensure the accuracy of solving, the step length of each iteration is usually very small, the flood dynamics after 1h is calculated, and the numerical method can be used for solving partial differential equations in thousands of iterations, namely running a partial differential equation solver PDEsolver, and the time consumption is huge. And the numerical simulation result controlled by the shallow water equation is used for constructing a ConvLSTM prediction model, and the model can rapidly predict the flood dynamics at the next moment according to the learned boundary conditions and the immobilized parameters after inputting the flood dynamics at the moment and the expected rainfall, so that the flood flooding evolution prediction speed is greatly improved.
Shallow water equations add several assumptions on the basis of the Naviet-Stokes equation: (1) the flow of shallow water is two-dimensional, and the flow velocity is uniformly distributed in the depth direction; (2) the friction force is a volumetric force; (3) the pressure corresponds to the hydrostatic pressure distribution. The vector form of the continuous equation and the motion equation describing the shallow water equation by using the Euler coordinate system is as follows: the shallow water equation includes:
the continuous equation:
Figure BDA0004114098470000061
equation of motion:
Figure BDA0004114098470000062
Figure BDA0004114098470000063
bottom surface resistance term:
Figure BDA0004114098470000064
Figure BDA0004114098470000065
flux:
M＝uh； (6)
N＝vh； (7)
wherein: h represents the flood depth; h represents a flood level; u represents the flow rate of flood in x direction; v represents the velocity of flow in the y direction of the flood; m represents flood x-direction flux; n represents flood y-direction flux; τ xb And τ yb Respectively representing the ground resistance of the flood in the x and y directions; g represents the gravitational acceleration m/s; ρ represents the water density; n represents the roughness coefficient in the Manning coefficient.
Based on historical water flow dynamic time sequence data S (water level, water depth, flow velocity in x and y directions), ground resistance in x and y directions, gravity acceleration g, water density rho and Manning coefficient n, the numerical simulation data of flood flow can be obtained by utilizing the shallow water equation. The numerical simulation data is specifically a river basin unit line, namely a ground runoff process line formed at the outlet section of the river basin by unit net rainfall uniformly distributed on the river basin in unit time.
And S4, training a ConvLSTM model based on the numerical simulation data of the flood flow obtained in the step S3. Flood flooding has spatiotemporal characteristics, and conventional Lstm models can lead to loss of data space characteristics, so that it is difficult to predict the flood flooding process. The ConvLstm model learns how floods move along spatial and temporal axes and is used to predict future flood motion patterns. ConvLSTM principle of operation:
i t ＝σ(w xi *x t +w hi *H t-1 +w ci ℃ t-1 +b i )； (8)
f t ＝σ(w xf *x t +w hf *H t-1 +w cf ℃ t-1 +b f )； (9)
C t ＝f t ℃ t-1 +i t °tanh(w xc *x t +w hc *H t-1 +b c )； (10)
o t ＝σ(w xo *x t +w ho *H t-1 +w co ℃ t +b o )； (11)
H t ＝o t °tanh(C t )； (12)
wherein, represents convolution operation, and the ° represents corresponding multiplication; w (w) xi 、w hi 、w ci 、w xf 、w hf 、w cf 、w xc 、w hc 、w xo 、w ho 、w co The weight to be trained; b i 、b f 、b C 、b o Is a bias requiring training; sigma is a sigmoid activation function; x is x t For the input value at time t (namely the numerical simulation result of the shallow water equation), H t-1 Is the hidden state at the moment t-1, C t-1 Memory cells at time t-1; h t The output value at time t.
And S5, inputting the future 6-hour time-by-time rainfall forecast data acquired in the step S2 into the ConvLSTM model trained in the step S4, and respectively forecasting flooding evolution data of 101X 101km future 6-hour time by time in a grid, wherein the flooding evolution data specifically comprises a flooding range and flooding water level data. The method comprises the following steps:
flood dynamics S at time t t And inputting rainfall forecast data Q within t+1h into a trained ConvLSTM model, wherein the forecast value is flood dynamic S at t+1h t+1 The flood dynamics comprises three dimensions, namely a flow velocity u in the direction of the water level H, x and a flow velocity v in the direction of y.
The flooding range is specifically as follows: output value flood dynamics S of ConvLSTM model t+1 The sum of the x-direction flow velocity u, the y-direction flow velocity v and the integration area of the future n hours from hour to hour.
And S6, sending out an early warning signal when the predicted submerged water level exceeds a preset safety value.
Example 2:
the specific embodiment of the invention provides a flood inundation evolution prediction and early warning system which is applied to a method and comprises a flood dynamic data acquisition module, a rainfall forecast data acquisition module, a flood simulation data acquisition module, a model training module, a flood inundation evolution prediction module and an early warning module;
the flood dynamic data acquisition module, the flood simulation data acquisition module, the model training module, the flood submerged evolution prediction module and the early warning module are connected in sequence; the rainfall forecast data acquisition module is respectively connected with the model training module and the flood inundation evolution prediction module;
the flood dynamic data acquisition module is used for acquiring flood dynamic time sequence data in a period of time within a grid; the principle is as described in the step S1 of the embodiment.
The rainfall forecast data acquisition module is used for acquiring rainfall forecast data time by time in the future n hours in the grid; the principle is as described in step S2 of the embodiment.
The flood simulation data acquisition module is used for acquiring simulation numerical data of flood flow based on the acquired flood dynamic time sequence data S and by utilizing a shallow water equation; the principle is as described in step S3 of the embodiment.
The model training module is used for training a ConvLSTM model based on the obtained numerical simulation data of the flood flow; the principle is as described in step S4 of the embodiment.
The flood inundation evolution prediction module is used for inputting the obtained future n-hour time-by-time rainfall forecast data into a trained ConvLSTM model to respectively predict the future n-hour time-by-time flood inundation evolution data in the grid, wherein the flood inundation evolution data comprises a inundation range and inundation water level data; the principle is as described in step S5 of the embodiment.
And the early warning module is used for sending an early warning signal when the predicted submerged water level exceeds a preset safety value.
Those of ordinary skill in the art will appreciate that the elements of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements of the examples have been described generally in terms of functionality in the foregoing description to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in this application, it should be understood that the division of units is merely a logic function division, and there may be other manners of division in practical implementation, for example, multiple units may be combined into one unit, one unit may be split into multiple units, or some features may be omitted.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.

Claims (9)

1. A flood inundation evolution prediction and early warning method is characterized by comprising the following steps:
step S1, flood dynamic time sequence data S in a period of time within a grid is obtained;
s2, acquiring rainfall forecast data in the grid every n hours in the future;
step S3, obtaining analog numerical data of flood flow by using a shallow water equation based on the flood dynamic time sequence data S obtained in the step S1;
s4, training a ConvLSTM model based on the numerical simulation data of the flood flow obtained in the step S3;
step S5, inputting the future n-hour time-by-time rainfall forecast data acquired in the step S2 into the ConvLSTM model trained in the step S4, and respectively forecasting the flooding evolution data of the future n-hour time-by-time in the grid, wherein the flooding evolution data specifically comprises a flooding range and flooding water level data;
and S6, sending out an early warning signal when the predicted submerged water level exceeds a preset safety value.
2. The flood inundation evolution prediction and early warning method according to claim 1, wherein the size of the grid in the step S1 is 101×101km.
3. The flood inundation evolution prediction and early warning method according to claim 1, wherein the flood dynamic time series data S in the step S1 comprises the water level, the flow rate in the x and y directions of the flood.
4. The flood inundation evolution prediction and early warning method according to claim 1, wherein the shallow water equation in the step S3 comprises:
the continuous equation:
Figure FDA0004114098460000011
equation of motion:
Figure FDA0004114098460000012
Figure FDA0004114098460000013
bottom surface resistance term:
Figure FDA0004114098460000021
Figure FDA0004114098460000022
flux:
M＝uh； (6)
N＝vh； (7)
wherein: h represents the flood depth; h represents a flood level; u represents the flow rate of flood in x direction; v represents the velocity of flow in the y direction of the flood; m represents flood x-direction flux; n represents flood y-direction flux; τ xb And τ yb Respectively representing the ground resistance of the flood in the x and y directions; g represents the gravitational acceleration m/s; ρ represents the water density; n represents the roughness coefficient in the Manning coefficient.
5. The flood inundation evolution prediction and early warning method according to claim 1, wherein in the step S5, the flood dynamics S at time t is as follows t And inputting rainfall forecast data Q within t+1h into a trained ConvLSTM model, wherein the forecast value is flood dynamic S at t+1h t+1 The flood dynamics comprises three dimensions, namely a flow velocity u in the direction of the water level H, x and a flow velocity v in the direction of y.
6. The flood inundation evolution prediction and early warning method according to claim 1, wherein n=6 hours in the step S2.
7. The flood inundation evolution prediction and early warning method according to claim 1, wherein the analog numerical data of the flood flow in the step S3 is specifically a river basin unit line.
8. The flooding evolution prediction and early warning method according to claim 5, wherein the flooding range in step S5 is specifically: output value flood dynamics S of ConvLSTM model t+1 The sum of the x-direction flow velocity u, the y-direction flow velocity v and the integration area of the future n hours from hour to hour.
9. The flood inundation evolution prediction and early warning system is characterized by being applied to the method of any one of claims 1-8, and comprises a flood dynamic data acquisition module, a rainfall forecast data acquisition module, a flood simulation data acquisition module, a model training module, a flood inundation evolution prediction module and an early warning module;
the flood dynamic data acquisition module, the flood simulation data acquisition module, the model training module, the flood submerged evolution prediction module and the early warning module are connected in sequence; the rainfall forecast data acquisition module is respectively connected with the model training module and the flood inundation evolution prediction module;
the flood dynamic data acquisition module is used for acquiring flood dynamic time sequence data in a period of time within a grid;
the rainfall forecast data acquisition module is used for acquiring rainfall forecast data time by time in the future n hours in the grid; the flood simulation data acquisition module is used for acquiring simulation numerical data of flood flow based on the acquired flood dynamic time sequence data S and by utilizing a shallow water equation;
the model training module is used for training a ConvLSTM model based on the obtained numerical simulation data of the flood flow;
the flood inundation evolution prediction module is used for inputting the obtained future n-hour time-by-time rainfall forecast data into a trained ConvLSTM model to respectively predict the future n-hour time-by-time flood inundation evolution data in the grid, wherein the flood inundation evolution data comprises a inundation range and inundation water level data;
and the early warning module is used for sending an early warning signal when the predicted submerged water level exceeds a preset safety value.
CN202310213361.3A 2023-03-07 2023-03-07 Flood inundation evolution prediction and early warning method and system Pending CN116432820A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310213361.3A CN116432820A (en) 2023-03-07 2023-03-07 Flood inundation evolution prediction and early warning method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310213361.3A CN116432820A (en) 2023-03-07 2023-03-07 Flood inundation evolution prediction and early warning method and system

Publications (1)

Publication Number Publication Date
CN116432820A true CN116432820A (en) 2023-07-14

Family

ID=87082342

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310213361.3A Pending CN116432820A (en) 2023-03-07 2023-03-07 Flood inundation evolution prediction and early warning method and system

Country Status (1)

Country Link
CN (1) CN116432820A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117094448A (en) * 2023-10-17 2023-11-21 成都智慧企业发展研究院有限公司 Big data analysis method and system
CN117333587A (en) * 2023-12-01 2024-01-02 武汉大学 Urban inundation image data generation method and system based on video water level gauge
CN117494586A (en) * 2023-12-29 2024-02-02 浙江大学 Mountain torrent space-time prediction method based on deep learning

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117094448A (en) * 2023-10-17 2023-11-21 成都智慧企业发展研究院有限公司 Big data analysis method and system
CN117094448B (en) * 2023-10-17 2024-02-02 成都智慧企业发展研究院有限公司 Big data analysis method and system
CN117333587A (en) * 2023-12-01 2024-01-02 武汉大学 Urban inundation image data generation method and system based on video water level gauge
CN117333587B (en) * 2023-12-01 2024-02-27 武汉大学 Urban inundation image data generation method and system based on video water level gauge
CN117494586A (en) * 2023-12-29 2024-02-02 浙江大学 Mountain torrent space-time prediction method based on deep learning
CN117494586B (en) * 2023-12-29 2024-04-30 浙江大学 Mountain torrent space-time prediction method based on deep learning

Similar Documents

Publication Publication Date Title
CN116432820A (en) Flood inundation evolution prediction and early warning method and system
Chen et al. Reinforced recurrent neural networks for multi-step-ahead flood forecasts
Tayfur Soft computing in water resources engineering: Artificial neural networks, fuzzy logic and genetic algorithms
Shiri et al. Predicting groundwater level fluctuations with meteorological effect implications—A comparative study among soft computing techniques
Mohanty et al. Artificial neural network modeling for groundwater level forecasting in a river island of eastern India
Bhattacharjya et al. Optimal management of coastal aquifers using linked simulation optimization approach
Fernandes et al. The Patos lagoon hydrodynamics during an El Nino event (1998)
Mirzaei CFD modeling of micro and urban climates: Problems to be solved in the new decade
CN109711617B (en) Medium-and-long-term runoff prediction method based on BLSTM deep learning
Wang et al. A three-dimensional cohesive sediment transport model with data assimilation: Model development, sensitivity analysis and parameter estimation
Thomas et al. Simulation optimization model for aquifer parameter estimation using coupled meshfree point collocation method and cat swarm optimization
Zhu et al. Comprehensive analysis and artificial intelligent simulation of land subsidence of Beijing, China
Demirci et al. Prediction of cross-shore sandbar volumes using neural network approach
Yan et al. Modeling spatial distribution of flow depth in fluvial systems using a hybrid two-dimensional hydraulic-multigene genetic programming approach
CN106355003A (en) Markov Chain Monte Carlo automatic history matching method and system based on t-distribution
Wang et al. Water level prediction of rainwater pipe network using an SVM-based machine learning method
Wen et al. Lake level dynamics exploration using deep learning, artificial neural network, and multiple linear regression techniques
Tayyab et al. Application of artificial intelligence method coupled with discrete wavelet transform method
El-Ghandour et al. Groundwater management using a new coupled model of flow analytical solution and particle swarm optimization
Moeini et al. Wave parameter hindcasting in a lake using the SWAN model
Pramesti et al. Long-Short Term Memory (Lstm) for Predicting Velocity and Direction Sea Surface Current on Bali Strait
Zhou et al. Stability prediction of tailing dam slope based on neural network pattern recognition
Favis‐Mortlock Non‐Linear Dynamics, self‐organization and cellular automata models
Jiang et al. Deep-reinforcement-learning-based water diversion strategy
CN115114842A (en) Rainstorm waterlogging event prediction method based on small sample transfer learning algorithm

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