CN111079595A - Novel concept and intelligent risk identification method for dynamic flood risk graph - Google Patents
Novel concept and intelligent risk identification method for dynamic flood risk graph Download PDFInfo
- Publication number
- CN111079595A CN111079595A CN201911229602.3A CN201911229602A CN111079595A CN 111079595 A CN111079595 A CN 111079595A CN 201911229602 A CN201911229602 A CN 201911229602A CN 111079595 A CN111079595 A CN 111079595A
- Authority
- CN
- China
- Prior art keywords
- flood
- risk
- dynamic
- graph
- flow
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/08—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
- G06Q10/06—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—Systems or methods specially adapted for 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
Abstract
The invention discloses a new idea of a dynamic flood risk graph and an intelligent risk identification method, which comprise the following steps: inputting the preprocessed and normalized remote sensing image data into the established BP neural network for processing, and identifying and outputting classification result images; modeling by using the classification result image and a flood flooding cellular automaton based on a volume method, and drawing to form a dynamic flood risk graph; the dynamic flood risk graph comprises a flood risk time-varying graph, a flood risk dynamic analysis graph, a flood risk dynamic scheduling graph and a flood management dynamic risk graph. By introducing the remote sensing disaster identification method of the BP neural network, disaster data information can be rapidly acquired, flood risk analysis and calculation speed is improved, network convergence time is shortened, rapid classification and identification are carried out, flood disaster monitoring basic data can be rapidly and accurately acquired, and a means with less manual intervention, high automation degree and high classification precision is provided for remote sensing intelligent information extraction and classification.
Description
Technical Field
The invention relates to the technical field of flood risk identification, in particular to a new idea of a dynamic flood risk graph and an intelligent risk identification method.
Background
The flood risk map has irreplaceable important functions in aspects of flood control and flood fighting, flood risk management, urban and rural construction planning, land utilization planning, establishment of a flood insurance system, improvement of civil flood prevention consciousness and the like. At present, flood risk maps in China are mostly compiled under specific frequency flood or rainstorm conditions, and the problems of insufficient practical information, high updating difficulty, difficulty in achievement sharing and the like exist.
With the rapid development of social economy in China, the landform, the underlying surface, the engineering facilities and the like in a flood control area are changed greatly, the flood routing path, the propagation time, the flooding risk and the distribution condition of the flooding risk are partially or completely changed, the regional flood control situation is seriously influenced, and the flood risk is transferred to different degrees. Particularly, in flood control emergency management, due to the variability and complexity of water conditions, uncertainty and time variability exist in a flood scheme, so that real-time analysis of flood risks is more necessary, and higher requirements are provided for flood risk map compilation work.
Disclosure of Invention
The invention aims to provide a new concept of a dynamic flood risk graph and an intelligent risk identification method aiming at the technical defects in the prior art, so as to further embody the dynamic characteristics and time-varying characteristics of flood risks and provide technical support and decision basis for flood control emergency rescue.
The technical scheme adopted for realizing the purpose of the invention is as follows:
a new idea of a dynamic flood risk graph and an intelligent risk identification method comprise the following steps:
inputting the preprocessed and normalized remote sensing image data into the established BP neural network for processing, and outputting a classification result image;
modeling by using the classification result image and a flood flooding cellular automaton based on a volume method, and drawing to form a dynamic flood risk graph;
the dynamic flood risk graph comprises a flood risk time-varying graph, a flood risk dynamic analysis graph, a flood risk dynamic scheduling graph and a flood management dynamic risk graph.
By introducing the remote sensing disaster identification method of the BP neural network, disaster data information can be rapidly acquired, the flood risk analysis and calculation speed is improved, the network convergence time is shortened, rapid classification and identification are carried out, the flood disaster monitoring basic data can be rapidly and accurately acquired, a means with less manual intervention, high automation degree and high classification precision is provided for remote sensing intelligent information extraction and classification, and meanwhile, a scientific basis can be provided for flood prevention command decision-making of government departments.
Drawings
FIG. 1 is a diagram of dynamic flood risk graph impact factor logical relationships;
FIG. 2 is a flow chart of remote sensing data preprocessing;
FIG. 3 is a dynamic flood risk graph profile analysis table;
fig. 4 is a classification table of dynamic flood risk map.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1-2, the new concept and risk intelligent identification method for a dynamic flood risk graph of the present invention includes:
inputting the preprocessed and normalized remote sensing image data into the established BP neural network for processing, and outputting a classification result image;
modeling by using the classification result image and a flood flooding cellular automaton based on a volume method, and drawing to form a dynamic flood risk graph;
the dynamic flood risk graph comprises a flood risk time-varying graph, a flood risk dynamic analysis graph, a flood risk dynamic scheduling graph and a flood management dynamic risk graph.
In order to reflect flood risks dynamically and accurately, the invention provides a dynamic flood risk map system, which mainly comprises the following functions: the flood monitoring information of multi-source data can be dynamically received and quickly processed based on a GIS platform; the method has the advantages that the method is capable of dynamically updating and managing basic geographic information, social and economic information and flood prevention special topic information of the cloud platform; seamless connection with a flood risk information rapid calculation and evaluation model is realized, and dynamic updating and management of risk information can be performed; the rapid drawing and dynamic updating of graphs can be carried out according to flood risk information of different classifications; and flexible management, network publishing and the like of the dynamic flood risk graph are realized.
According to the flood risk management and flood prevention command decision-making practical requirements, the dynamic flood risk graph dynamically acquires rain, water, work, dangerous, social and economic information by utilizing the advanced technology, rapidly calculates and evaluates flood risk information (flood submerging range, water depth, duration, flood influence, disaster loss, flood avoidance transfer and other information) by adopting an intelligent flood rapid analysis method, and rapidly draws the flood risk information graph according to technical specifications and requirements.
According to the characteristics of the dynamic flood risk graph, the dynamic flood risk graph classification comprises a flood risk time-varying graph, a flood risk dynamic analysis graph, a flood risk dynamic scheduling graph and a flood management dynamic risk graph. The method comprises the steps of obtaining a flood inundation degree risk, a flood influence risk, a flood loss risk, a flood avoidance transfer risk and the like, wherein the flood inundation degree risk, the flood influence risk, the flood loss risk, the flood avoidance transfer risk and the like are respectively included in corresponding thematic risk maps.
The flood risk time-varying graph is a dynamic risk graph which is drawn according to rainfall and real-time or dynamic changes of flood conditions, researches flood inundation and real-time dynamic changes of influencing factors by using a multi-source flood rapid analysis technology, and is used for drawing a flood risk change process.
The flood risk dynamic analysis graph is used for analyzing and researching the possible change of flood or analyzing the possibility of flood risk generation due to the change situation of engineering dangerous situations according to the uncertainty of the rainwater situation, researching the possible distribution situation of the flood risk based on a flood risk rapid analysis technology, and drawing a possible flood risk analysis result graph.
The flood risk dynamic scheduling graph is used for reducing flood risks or transferring flood risks to a certain extent through scientific flood scheduling according to the requirements of flood control emergency scheduling or flood control emergency rescue work, different flood scheduling schemes correspond to corresponding flood risks, flood risk changes generated by different flood scheduling modes are reflected, risk factor analysis is carried out on the basis of flood analysis and calculation, and flood risk change comparison graphs corresponding to different flood scheduling schemes are drawn.
The flood management dynamic risk graph is a dynamic update graph for flood risks, which is drawn according to actual requirements of flood risk management such as flood control planning, flood insurance, land utilization and the like, fully considers the time-space change of basic geographic information, flood control management information and social and economic information, and is based on the support environments such as intelligent drainage basins, big data, cloud platforms and the like, so that the flood risk information is quickly and timely updated, the time-space transformation characteristics of the flood risks are truly reflected.
In the invention, the flood submerging cellular automaton rapid analysis and calculation based on the volume method comprises the contents of breach flow calculation, time step length determination, initial submerging area and calculation area determination, initial submerging flow calculation, calculation of calculating area cellular containable flow and submerging water level, submerging area and calculation area updating and the like in the modeling process of the flood submerging cellular automaton based on the volume method. The basic principle is as follows.
(1) Breach flow calculation
Assuming that the initial breach is rectangular in shape, the flow at the breach can be calculated using the following equation:
in the formula: q is flood flow at the breach; m is a flow coefficient; sigma is a submergence coefficient; epsilon is the lateral shrinkage coefficient; b is the width of the breach; h is the water level elevation; hcIs the elevation of the bottom of the breach.
In the process of developing the burst opening, the shape of the burst opening is gradually changed from a rectangle to a trapezoid, and the flow at the burst opening can be calculated by adopting the following formula:
Q＝1.55σB(H-Hc)1.5+1.2tan(α)(H-Hc)2.5
in the formula: q is flood flow at the breach; sigma is a submergence coefficient; b is the width of the breach; h is the water level elevation; hcIs the elevation of the bottom of the breach, and α is the included angle between the slope of the breach and the vertical direction.
(2) Time step determination
In the flood inundation cellular automata model, the calculation time step length has certain influence on the simulation result, if the step length is too small, the flood flow at the burst opening in each calculation time step length is too small, and the cells adjacent to the burst opening cannot be filled; if the step length is too long, the flood flow at the break is too large in each calculation time step length, and then the flood fills the cells adjacent to the break and flows into the adjacent space. In order to ensure that the flood shunted from the break opening in each calculation time step just fills the cells adjacent to the break opening, the time step can be determined by adopting the following modes: calculating the flood flow velocity by the flowmeter at the breach, wherein the calculation time step required by each step of simulation can be obtained by the side length of the grid and the flow velocity, and the calculation formula is as follows:
in the formula: v is the water flow speed at the break; q is flood flow at the breach; b is the width of the breach; h is the water level elevation; hcIs the elevation of the bottom of the breach; dt is the calculation time step; and L is the side length of the grid.
(3) Initial flooding area, initial calculation area and flooding flow calculation
The initial flooding area is a cell at the position of a break port of the dike, the initial calculation area is a cell at the position of the break port and a cell adjacent to the cell, the cells in the calculation area are arranged in a sequence from low elevation to high elevation, the flooding flow refers to the total amount of flood flowing out of the break port at the end of the simulation time t, and the calculation formula is as follows:
Qi+1＝Qi+qi+1Δt
in the formula: qi+1The total amount of the invading flood at the moment i + 1; qiThe total amount of the invading flood at the moment i; q. q.si+1Is a delta at the breachtFlood flow rate in time units.
(4) The cellular capacity of the calculation area can be used for calculating the flow and the submerging water level
The cell-receivable flow of the calculation area is defined as the total flood which can be stored by all cells with the elevation lower than the elevation value of a certain cell in the calculation area. When the cells in the calculation area are arranged in the sequence from the low elevation to the high elevation, the cell-receivable flow of the calculation area is distributed in a ladder shape, and the receivable flow is calculated according to the following formula:
V_floodi+1＝V_floodi+A·i·(Zi+2-Zi+1)
in the formula: v _ loodi+1The flow rate which can be accommodated by all the cells with the elevation lower than the (i + 1) th cell elevation value in the calculated area is calculated; a is the cell area; z is the topographic elevation value of the cells.
After the distribution condition of the cellular containable flow of the calculation area is obtained, calculating the elevation value of the submerging water level according to the following piecewise function:
wherein: zQThe height value of the submerged water level is obtained; z is a cellular elevation value; q is flood flow at the breach; a is the cell area; n is the total number of cells in the calculation area.
(5) Inundation area, calculation area update
And after the height value of the submerging water level is obtained, dividing all the submerging cells in the original calculation area into the submerging area to form a new flood submerging area, dividing all the cells and neighbor cells in the new flood submerging area into the calculation area, and arranging all the cells in the height sequence from low to high to form a calculation area for next simulation.
In the invention, the steps of adopting the BP neural network to intelligently identify and output the classification result image by remote sensing disaster are as follows:
(1) data pre-processing
The remote sensing image preprocessing process mainly comprises the links of geometric correction (geographical positioning, geometric fine correction, image registration, orthorectification and the like), image fusion, image mosaic, image cutting, cloud removal, shadow processing, atmospheric correction and the like, and the preprocessing flow is shown in the attached figure 2. Geometric correction is carried out on the panchromatic image by selecting a control point from the standard data, the multispectral image is registered by taking the panchromatic image as a reference image, fusion processing is carried out on the multispectral image and the panchromatic image, and a fusion result is cut by utilizing a vector boundary to obtain the multispectral image with geographic coordinates and higher resolution.
(2) BP neural network data normalization processing
Reading raster images by using an imread function, calling an rgb2gray function to convert the raster images into grayscale images, but the images cannot be directly input into a BP neural network, and calling an im2double function to convert the grayscale values into a double-precision format. Since singular sample data may exist in the remote sensing image training sample, the existence of the singular sample may cause the network training time to increase and cause the network to be incapable of converging, the gray values of the training sample and the image data to be classified are normalized to be (0,1) by adopting the mapminmax function. The image processed by dimension reduction can not be directly input into the neural network, and must be firstly changed into a one-dimensional vector form, and the gray value needs to be converted into a double-precision format and normalized.
(3) BP neural network model establishment
The number of the wave bands participating in classification is 7, and 7 nodes of an input layer are provided; the coverage types are 8 types, and 8 nodes are output; the hidden layer 19 nodes are according to equation (8). The neuron of the hidden layer adopts a tansig hyperbolic tangent S-type transfer function, and the output is (-1, 1); the neurons of the output layer adopt logsig logarithm S-type transfer functions, and the output is (0, 1). And (3) establishing a BP network by applying a function newff, and training the network by adopting a Levenberg-Marquardt algorithm.
(4) BP neural network training
The method comprises the steps of carrying out network training by applying a function train, presetting training parameters, setting training times to 2000 times, setting training precision to 0.1, optimizing calculation of weights and offset values by the train lm function according to a Levenberg-Marquardt algorithm, namely, setting the minimum performance gradient to be 1e-6, the learning rate base value to be 0.001, the learning rate reduction rate to be 0.1, the learning rate increase rate to be 10, the maximum learning rate to be 1e10, and using default values for other parameters. And after the training is finished, classifying by using the trained BP network. And finally, performing inverse normalization processing on the classification result and outputting a classification result image.
(5) Accuracy testing
The accuracy check is usually calculated using the overall accuracy and the Kappa coefficient. The overall accuracy is the number of correctly classified pixels divided by the total number of image pixels.
The total precision is (number of correctly classified pixels/total pixels) × 100%
Kappa coefficient:
in the formula: poIs the sum of the number of correctly classified samples of each class divided by the total number of samples, i.e., the overall classification accuracy. Suppose the number of true samples of each class is a1，a2，...，anAnd the predicted number of samples of each class is b1，b2，...，bnAnd if the total number of samples is m, the following samples are obtained:
the dynamic flood risk map of the invention serves flood control command, flood control planning, flood risk scheduling, flood risk management, flood control emergency plan compilation, land utilization planning, flood insurance and the like. The invention provides a new concept, definition, function and classification of the dynamic flood risk graph, and perfects the theoretical and technical research of the dynamic flood risk graph.
In addition, the dynamic flood risk map adopts a construction concept of intelligent water conservancy, applies high and new technologies such as internet, big data, cloud computing and a geographic information system to flood risk analysis, further promotes the application of a GIS space analysis technology, a remote sensing dynamic monitoring technology, a digital observation technology, an artificial intelligence technology, a multi-source model disaster situation rapid evaluation technology and the like in the flood prevention and disaster reduction field, promotes the integration of informatization, intellectualization and flood prevention and disaster reduction depth, continuously improves the comprehensive disaster prevention and reduction capability, and promotes the rapid development of a front-edge information technology and an intelligent technology from an application level.
The invention provides an intelligent flood risk identification method under different conditions aiming at the change of flood control situation and risk distribution characteristics under a changing environment, analyzes the applicability of a dynamic flood risk graph, provides technical and theoretical support for dynamic flood risk graph compilation and system development, further improves the technical level of the dynamic flood risk graph compilation in China, promotes the standardization and standardization work of the dynamic flood risk graph compilation, and promotes the popularization and application of the dynamic flood risk graph in the fields of flood control command, emergency rescue, refuge and moving safety and the like.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (4)
1. A new idea of a dynamic flood risk graph and an intelligent risk identification method are characterized by comprising the following steps:
inputting the preprocessed and normalized remote sensing image data into the established BP neural network for processing, and outputting a classification result image;
modeling by using the classification result image and a flood flooding cellular automaton based on a volume method, and drawing to form a dynamic flood risk graph;
the dynamic flood risk graph comprises a flood risk time-varying graph, a flood risk dynamic analysis graph, a flood risk dynamic scheduling graph and a flood management dynamic risk graph.
2. The new concept and risk intelligent identification method for dynamic flood risk graph according to claim 1, wherein the modeling of flood submerging cellular automata based on volume method is realized by calculating breach flow, determining time step, determining initial submerging area and calculating area, calculating initial submerging flow, calculating the cellular containable flow and submerging water level of calculating area, and updating submerging area and calculating area in real time:
the rectangular breach flow is calculated by adopting the following formula:
in the formula, Q is flood flow at the breach; m is a flow coefficient; sigma is a submergence coefficient; epsilon is the lateral shrinkage coefficient; b is the width of the breach; h is the water level elevation; hcIs the elevation of the bottom of the breach;
in the process of developing the burst, the shape of the burst is gradually changed from rectangle to trapezoid, and at the moment, the flow of the burst is calculated by adopting the following formula:
Q＝1.55σB(H-Hc)1.5+1.2tan(α)(H-Hc)2.5
wherein α is the included angle between the breach slope and the vertical direction,
the time step is determined by calculating the flood flow rate through the flow meter at the breach, and then obtaining the time step required by each step of simulation through the side length of the grid and the flood flow rate, wherein the calculation mode is as follows:
in the formula, v is the flow velocity of water flow at the breach, and dt is the calculation time step length; l is the side length of the grid;
the initial flooding area is a cell at the position of a break of the dike, the initial calculation area is a cell at the position of the break and a cell adjacent to the cell, the cells in the calculation area are arranged in an order from low to high in elevation, the initial flooding flow refers to the total flood amount flowing out of the break at the end of the simulation time t, and the calculation formula is as follows:
Qi+1＝Qi+qi+1Δt
in the formula, Qi+1The total amount of the invading flood at the moment i + 1; qiThe total amount of the invading flood at the moment i; q. q.si+1Is a delta at the breachtFlood flow rate in time unit time;
calculating the total flood volume which can be stored by all the cells with the elevation lower than the elevation value of a certain cell in the calculated area; when the cellular units in the calculation area are arranged in the sequence from the low elevation to the high elevation, the cellular units in the calculation area can accommodate the flow in a step-shaped distribution, and the cellular units in the calculation area can accommodate the flow calculated according to the following formula:
V_floodi+1＝V_floodi+A·i·(Zi+2-Zi+1)
in the formula, V _ loodi+1Calculating the containable flow of all cells with the elevation lower than the (i + 1) th cell elevation value in the area, wherein A is the cell area, and Z is the topographic elevation value of the cells;
after the distribution condition of the receivable flow of the cellular cells in the calculation area is obtained, calculating the elevation value of the submerging water level according to the following piecewise function:
wherein Z isQThe height value of the submerged water level is obtained, Q is flood flow at the breach, and n is the total number of cells in the calculation area;
and after the height value of the submerging water level is obtained, dividing all the submerging cells in the original calculation area into the submerging area to form a new flood submerging area, dividing all the cells and neighbor cells in the new flood submerging area into the calculation area, and arranging all the cells in the height sequence from low to high to form a calculation area for next simulation.
3. The new idea and risk intelligent recognition method of the dynamic flood risk graph according to claim 1, wherein the classification step using the trained BP neural network is as follows:
and using the connection weight matrix obtained by training, taking the gray value of each pixel of the remote sensing image as an input vector, calculating an output vector, wherein the component of the output vector is the probability value of the pixel in each category, merging each pixel into the wetland coverage type with the maximum probability value, and finally performing inverse normalization processing on the classification result and outputting a classification result image.
4. The new concept and risk intelligent identification method for dynamic flood risk graph according to claim 1, wherein the accuracy test of BP neural network is calculated by using overall accuracy and Kappa coefficient,
the total precision is (number of correctly classified pixels/total pixels) × 100%
Kappa coefficient:
in the formula, PoThe sum of the number of samples correctly classified in each class is divided by the total number of samples, and the number of real samples in each class is a1，a2，...，anThe predicted number of samples of each class is b1，b2，...，bnAnd if the total number of samples is m, the following samples are obtained:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229602.3A CN111079595A (en) | 2019-12-04 | 2019-12-04 | Novel concept and intelligent risk identification method for dynamic flood risk graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229602.3A CN111079595A (en) | 2019-12-04 | 2019-12-04 | Novel concept and intelligent risk identification method for dynamic flood risk graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111079595A true CN111079595A (en) | 2020-04-28 |
Family
ID=70312834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911229602.3A Pending CN111079595A (en) | 2019-12-04 | 2019-12-04 | Novel concept and intelligent risk identification method for dynamic flood risk graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111079595A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251973A (en) * | 2023-11-13 | 2023-12-19 | 中国水利水电科学研究院 | Flood disaster avoidance route determination method |
| CN117726308A (en) * | 2024-02-18 | 2024-03-19 | 中铁水利信息科技有限公司 | Intelligent water conservancy management system and method based on Internet of things and 5G |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130116920A1 (en) * | 2011-11-07 | 2013-05-09 | International Business Machines Corporation | System, method and program product for flood aware travel routing |
| CN110458391A (en) * | 2019-07-04 | 2019-11-15 | 天津大学 | A kind of fining diagnostic method for Megapolis flood risk zoning |
-
2019
- 2019-12-04 CN CN201911229602.3A patent/CN111079595A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130116920A1 (en) * | 2011-11-07 | 2013-05-09 | International Business Machines Corporation | System, method and program product for flood aware travel routing |
| CN110458391A (en) * | 2019-07-04 | 2019-11-15 | 天津大学 | A kind of fining diagnostic method for Megapolis flood risk zoning |
Non-Patent Citations (2)
| Title |
|---|
| 王雪梅等: "BP神经网络在土地覆盖分类中的应用研究-以新疆于田绿洲为例", 《新疆农业科学》 * |
| 蔡新等: "基于体积法思想的洪水淹没元胞自动机模型", 《水力发电学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251973A (en) * | 2023-11-13 | 2023-12-19 | 中国水利水电科学研究院 | Flood disaster avoidance route determination method |
| CN117251973B (en) * | 2023-11-13 | 2024-02-20 | 中国水利水电科学研究院 | Flood disaster avoidance route determination method |
| CN117726308A (en) * | 2024-02-18 | 2024-03-19 | 中铁水利信息科技有限公司 | Intelligent water conservancy management system and method based on Internet of things and 5G |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112561146B (en) | Large-scale real-time traffic flow prediction method based on fuzzy logic and depth LSTM | |
| WO2021258758A1 (en) | Coastline change identification method based on multiple factors | |
| Sun et al. | Modeling urban land use change and urban sprawl: Calgary, Alberta, Canada | |
| CN112084869B (en) | Compact quadrilateral representation-based building target detection method | |
| CN111027511B (en) | Remote sensing image ship detection method based on region of interest block extraction | |
| CN111091095B (en) | Method for detecting ship target in remote sensing image | |
| CN114926749B (en) | Near-surface atmospheric pollutant inversion method and system based on remote sensing image | |
| CN110060508B (en) | Automatic ship detection method for inland river bridge area | |
| CN112287832A (en) | High-resolution remote sensing image-based urban illegal building detection method | |
| CN111241994B (en) | Deep learning remote sensing image rural highway sanded road section extraction method | |
| CN112001411B (en) | Dam crack detection algorithm based on FPN structure | |
| CN113591617B (en) | Deep learning-based water surface small target detection and classification method | |
| CN111079595A (en) | Novel concept and intelligent risk identification method for dynamic flood risk graph | |
| CN112257793A (en) | Remote traffic sign detection method based on improved YOLO v3 algorithm | |
| CN114942596B (en) | Intelligent control system for urban flood control and drainage | |
| CN115512247A (en) | Regional building damage grade assessment method based on image multi-parameter extraction | |
| CN115049841A (en) | Depth unsupervised multistep anti-domain self-adaptive high-resolution SAR image surface feature extraction method | |
| CN110097047A (en) | A kind of vehicle checking method using single line laser radar based on deep learning | |
| CN116246169A (en) | SAH-Unet-based high-resolution remote sensing image impervious surface extraction method | |
| CN113343858A (en) | Road network geographic position identification method and device, electronic equipment and storage medium | |
| CN115393700A (en) | Water level height identification method and device, electronic equipment and storage medium | |
| Bhuyan et al. | Mapping and characterising buildings for flood exposure analysis using open-source data and artificial intelligence | |
| CN115272876A (en) | Remote sensing image ship target detection method based on deep learning | |
| CN117556197B (en) | Typhoon vortex initialization method based on artificial intelligence | |
| CN115019163A (en) | City factor identification method based on multi-source big data |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200428 |
|
| WD01 | Invention patent application deemed withdrawn after publication |