Flood collaborative forecast management system and method based on big data analysis

Abstract

The invention relates to a flood collaborative forecast management system and method based on big data analysis, and belongs to the technical field of big data analysis. The method comprises the steps that a grid gradient set of a target monitoring drainage basin is obtained according to overlook topographic data, a sub-drainage basin grid set and a sub-drainage basin set are obtained according to the grid gradient set, and sub-drainage basin division can help to improve the accuracy of flood dam burst position positioning of the target monitoring drainage basin; the method comprises the following steps: constructing a sub-basin topographic parameter set according to a sub-basin set, carrying out feature extraction on the sub-basin topographic parameter set to obtain a sub-basin topographic feature set, and analyzing the sub-basin topographic feature set to obtain referable flood data, thereby solving the problem of scarcity of target monitoring basin data, improving the reference of the data, and improving the accuracy of flood monitoring. The flood risk assessment model is used to process the referable flood data and the real-time monitoring data set to obtain the flood risk coefficient, and the flood forecasting list is obtained according to the flood risk coefficient, so that the management efficiency of flood forecasting is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data analysis, and specifically relates to a flood collaborative forecasting management system and method based on big data analysis. Background Art

[0002] At present, the flood forecasting technology used in areas with frequent floods is to establish flood prediction models based on a large amount of historical data, and then predict the time probability of floods in the basin. However, for areas where floods are not frequent, there is not a large amount of historical data for research and reference. This will result in no flood forecasting models available, and flood warnings will be untimely, resulting in short time for people to evacuate, which will lead to disasters and economic losses for the people. Summary of the invention

[0003] In order to solve the above-mentioned problems existing in the prior art, the present invention provides a flood collaborative forecasting management system and method based on big data analysis. According to the overhead terrain data, the target monitoring basin is divided and numbered in a coordinated manner to obtain a sub-basin set, and the flow information, water level information and precipitation of the sub-basin set are collected to obtain a real-time monitoring data set. A sub-basin terrain parameter set is constructed according to the sub-basin set, and features are extracted from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set. Reference flood data is obtained by analyzing the sub-basin terrain feature set. According to the reference flood data and the real-time monitoring data set, a flood risk coefficient is obtained by processing through a flood risk assessment model. According to the flood risk coefficient, a flood forecast list is obtained, and the flood forecast list is uploaded to the terminal.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] A flood collaborative forecasting management method based on big data analysis includes the following steps:

[0006] S1: obtaining a grid slope set of the target monitoring basin according to the topographic data, obtaining a sub-basin grid set by processing the grid slope set, and performing overall numbering on the sub-basin grid sets to obtain a sub-basin set;

[0007] S2: Collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set;

[0008] S3: construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set;

[0009] S4: Processing the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtaining a flood forecast list according to the flood risk coefficient, and uploading the flood forecast list to a terminal.

[0010] Preferably, the specific implementation steps of obtaining the grid slope set of the target monitoring basin based on the topographic data are as follows:

[0011] Step A1: Collect the topographic map of the target monitoring basin through remote sensing technology, rasterize the topographic map, and obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid of the i-th row and j-th column is recorded as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number;

[0012] Step A2: In the topographic map, obtain the ij All adjacent grids are obtained to obtain the adjacent grid set, which is recorded as W(a ij )={a xy |x∈[i-1,i+1],y∈[j-1,j+1]}, and x and y are both positive integers, a xy Represents the grid a ij Any adjacent grid, calculate grid a ij With grid a xy Grid slope Wherein, d represents the grid spacing, and the grid spacing is the grid a ij Center point and grid a xy The straight-line distance between the center points, h(a xy ) represents grid a xy The altitude value, h(a ij ) represents grid a ij The altitude value of

[0013] Step A3: Calculate the adjacent grid set W(a ij ) and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope D(a ij );

[0014] Step A4: Repeat steps A2 and A3 until the grid slopes of all grids are selected, and obtain a grid slope set, which is recorded as P = {D (a ij )|i∈[1, I], j∈[1, J]}.

[0015] Preferably, the sub-basin grid set is obtained by processing the grid slope set, and the sub-basin grid set is numbered in a coordinated manner to obtain the sub-basin set. The specific implementation method is as follows:

[0016] Set k slope levels, k ≥ 2, and obtain the maximum grid slope MAX(D(a ij )) and the minimum grid slope MIN(D(a ij )), calculate the interval width Determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j;

[0017] The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper bound of the kth slope grade range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, and this step is repeated until the upper bounds of all slope grade ranges are compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained;

[0018] k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

[0019] Preferably, the specific method for constructing the sub-basin terrain feature set is as follows:

[0020] Get the number of grids in each sub-basin grid set and number the grids according to the number of grids. The sub-basin set is And r and q are both positive integers, where r represents the number of grids and q represents the sub-basin grid set number. The qth grid represents a sub-basin grid set with r grid numbers, and in, represents the grid elevation of the rth grid in the qth sub-basin grid set, and Where, represents the grid slope of the rth grid in the qth sub-basin grid set;

[0021] Calculate the average elevation of sub-basins based on the sub-basin set in, The sub-basin topographic factor is calculated based on the sub-basin set. in, represents the sub-basin terrain factor of the qth sub-basin raster set;

[0022] A sub-basin terrain parameter set is constructed according to the sub-basin average slope and the sub-basin terrain factor, and the sub-basin terrain feature set is obtained by extracting features from the sub-basin terrain parameter set.

[0023] Preferably, the specific method for obtaining reference flood data through analysis includes the following steps:

[0024] Step 1: Obtain a set of topographic features of flood-prone basins in the same region Among them, z represents the number of the flood-prone basin, b n Represents terrain features, represents the average elevation of the flood-prone basin z, F z represents the topographic factor of the flood-prone basin z, and the sub-basin topographic feature set is Where k represents the sub-basin number, a n Represents the sub-basin terrain characteristics. According to the terrain feature set and the sub-basin terrain feature set, the formula The terrain feature similarity is calculated, where TZ k represents the similarity of the topographic features between sub-basin k and reference basin z, and ||·|| represents the modular operation;

[0025] Step 2: Obtain the similarity of terrain features between sub-basin k and each flood-prone basin through step 1, screen out the basin with the maximum similarity of terrain features, and use the corresponding flood-prone basin as the reference basin of sub-basin k. Number the reference basin as e, where e=k, and obtain the historical flood data of the reference basin as the reference flood data of the target monitoring basin.

[0026] Preferably, in S4, the specific method for obtaining the flood forecast list according to the flood risk coefficient comprises the following steps:

[0027] S401: The reference flood data includes reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, and feature extraction is performed on the reference flood data to obtain a reference flood data feature set. Among them, t1 represents the historical monitoring time, e represents the reference basin number, si represents the flow characteristics of the reference basin, wi represents the water level characteristics of the reference basin, and fi represents the precipitation characteristics of the reference basin;

[0028] S402: Extract features from the real-time monitoring data set to obtain a real-time monitoring data feature set Where k represents the sub-basin number, t represents the real-time monitoring time, and t=t1, sr represents the flow characteristics of the sub-basin, wr represents the water level characteristics of the sub-basin, and fr represents the precipitation characteristics of the sub-basin;

[0029] S403: The flood risk assessment model is expressed as: Among them, F k represents the flood risk coefficient of sub-basin k;

[0030] S404: According to a preset risk threshold, sub-basins whose flood risk coefficients are less than or equal to the risk threshold are screened, and the flood risk coefficients of the screened sub-basins are sorted in ascending order, a flood forecast list is generated, and the flood forecast list is uploaded to the terminal.

[0031] Furthermore, the present application also provides a flood collaborative forecasting management system based on big data analysis, including:

[0032] The watershed division module obtains the grid slope set of the target monitoring watershed according to the topographic data, obtains the sub-watershed grid set by processing the grid slope set, and obtains the sub-watershed grid set by overall numbering;

[0033] The data collection module is used to collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set;

[0034] A data analysis module is used to construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set;

[0035] The flood forecasting module is used to process the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtain a flood forecast list according to the flood risk coefficient, and upload the flood forecast list to a terminal.

[0036] Preferably, the specific implementation steps of obtaining the grid slope set of the target monitoring basin based on the topographic data are as follows:

[0037] Step A1: Collect the topographic map of the target monitoring basin through remote sensing technology, rasterize the topographic map, and obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid of the i-th row and j-th column is recorded as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number;

[0038] Step A2: In the topographic map, obtain the ij All adjacent grids, to obtain an adjacent grid set;

[0039] Step A3: Calculate the relationship between each grid in the adjacent grid set and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope of

[0040] Step A4: Repeat steps A2 and A3 until the grid slopes of all grids are selected to obtain a grid slope set.

[0041] Preferably, the sub-basin grid set is obtained by processing the grid slope set, and the sub-basin grid set is numbered in a coordinated manner to obtain the sub-basin set. The specific implementation method is as follows:

[0042] Set k slope levels, k ≥ 2, calculate the interval width according to the maximum grid slope and the minimum grid slope of the grid slope set obtained, determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j;

[0043] The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper bound of the kth slope grade range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, and this step is repeated until the upper bounds of all slope grade ranges are compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained;

[0044] k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

[0045] Preferably, the specific implementation method of obtaining the flood forecast list according to the flood risk coefficient is as follows:

[0046] The reference flood data includes a reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, feature extraction is performed on the reference flood data to obtain a reference flood data feature set, feature extraction is performed on the real-time monitoring data set to obtain a real-time monitoring data feature set, the reference flood data feature set and the real-time monitoring data feature set are processed by a flood risk assessment model to obtain a flood risk coefficient; based on a risk threshold, the flood risk coefficients of the sub-basins are screened to screen out sub-basins whose flood risk coefficients are less than the risk threshold, and the flood risk coefficients of the sub-basins are sorted in ascending order to generate a flood forecast list, and the flood forecast list is uploaded to a terminal.

[0047] The beneficial effects of the present invention are:

[0048] 1. By setting up a watershed division module, a grid slope set of the target monitoring watershed is obtained according to the topographic data, and a sub-watershed grid set is obtained by processing the grid slope set. The sub-watershed grid set is numbered in a coordinated manner to obtain a sub-watershed set. The sub-watersheds are divided according to the topographic data, which is beneficial to the flood disaster warning of the target monitoring watershed and can help improve the accuracy of the location of the flood breach in the target monitoring watershed;

[0049] 2. By setting up a data analysis module, it is used to construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, obtain reference flood data by analyzing the sub-basin terrain feature set, find flood-prone basins with similar terrain features according to the terrain features of the sub-basin, and use the historical flood data of flood-prone basins in the same region as reference flood data for the sub-basin, which solves the problem of data scarcity in basins that do not often flood. The reference flood data obtained are historical flood data of flood-prone basins in the same region, which ensures that the climate characteristics and geological characteristics between basins are similar, and ensures the referenceability of the data;

[0050] 3. A flood forecasting module is set up to process the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, a flood forecast list is obtained based on the flood risk coefficient, and the flood forecast list is uploaded to the terminal. A flood forecast list for the target monitoring basin is obtained based on the sub-basin flood risk coefficient. By uploading the flood forecast list to the terminal, the management efficiency of flood forecasting is improved, so that the regulatory department can arrange emergency rescue and personnel evacuation work in the target monitoring basin according to the degree of urgency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0052] Figure 1 It is a flow chart of a flood collaborative forecasting management method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0053] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0054] See also Figure 1 , a flood collaborative forecasting management method based on big data analysis, comprising the following steps:

[0055] S1: obtaining a grid slope set of the target monitoring basin according to the topographic data, obtaining a sub-basin grid set by processing the grid slope set, and performing overall numbering on the sub-basin grid sets to obtain a sub-basin set;

[0056] S2: Collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set;

[0057] S3: construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set;

[0058] S4: Processing the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtaining a flood forecast list according to the flood risk coefficient, and uploading the flood forecast list to a terminal.

[0059] It should be further explained that the target monitoring basin in the present invention is a smaller basin with a lack of historical flood data. The flood forecast list is pushed to the terminal, and the regulatory department carries out emergency rescue deployment work according to the sub-basins in the flood forecast list to ensure that losses and damages are reduced within a controllable time. The flood forecast list can protect the safety of the people and reduce disaster losses as much as possible.

[0060] Specifically, the specific implementation steps for obtaining the grid slope set of the target monitoring basin based on the topographic data are as follows:

[0061] Step A1: Collect the topographic map of the target monitoring basin through remote sensing technology, rasterize the topographic map, and obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid of the i-th row and j-th column is recorded as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number;

[0062] Step A2: In the topographic map, obtain the ij All adjacent grids are obtained to obtain the adjacent grid set, which is recorded as W(a ij )={a xy |x∈[i-1,i+1],y∈[j-1,j+1]}, and x and y are both positive integers, a xy Represents the grid a ij Any adjacent grid, calculate grid a ij With grid a xy Grid slope Wherein, d represents the grid spacing, and the grid spacing is the grid a ij Center point and grid a xy The straight-line distance between the center points, h(a xy ) represents grid a xy The altitude value, h(a ij ) represents grid a ij The altitude value of

[0063] Step A3: Calculate the adjacent grid set W(a ij ) and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope D(a ij );

[0064] Step A4: Repeat steps A2 and A3 until the grid slopes of all grids are selected, and obtain a grid slope set, which is recorded as P = {D (a ij )|i∈[1, I], j∈[1, J]}.

[0065] Specifically, by processing the grid slope set to obtain the sub-basin grid set, and performing overall numbering on the sub-basin grid set, a specific implementation method for obtaining the sub-basin set is as follows:

[0066] Set k slope levels, k ≥ 2, and obtain the maximum grid slope MAX(D(a ij )) and the minimum grid slope MIN(D(a ij )), calculate the interval width Determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j;

[0067] The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper bound of the kth slope grade range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, and this step is repeated until the upper bounds of all slope grade ranges are compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained;

[0068] k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

[0069] It should be further explained that the advantage of dividing the target monitoring basin into sub-basins based on overhead terrain data is that it fully considers the terrain changes of the target monitoring basin. Dividing the sub-basins by grade slope values ​​can, on the one hand, accurately reflect the terrain changes of the target monitoring basin. On the other hand, dividing the sub-basins based on terrain data is conducive to the management of the target monitoring basin and the refined flood disaster warning, which can help improve the accuracy of locating the flood dam breach location in the target monitoring basin.

[0070] Specifically, the specific method for constructing the sub-basin terrain feature set is as follows:

[0071] Get the number of grids in each sub-basin grid set and number the grids according to the number of grids. The sub-basin set is And r and q are both positive integers, where r represents the number of grids and q represents the sub-basin grid set number. The qth grid represents a sub-basin grid set with r grid numbers, and in, represents the grid elevation of the rth grid in the qth sub-basin grid set, and Where, represents the grid slope of the rth grid in the qth sub-basin grid set;

[0072] Calculate the average elevation of sub-basins based on the sub-basin set in, The sub-basin topographic factor is calculated based on the sub-basin set. in, represents the sub-basin terrain factor of the qth sub-basin raster set;

[0073] A sub-basin terrain parameter set is constructed according to the sub-basin average slope and the sub-basin terrain factor, and the sub-basin terrain feature set is obtained by extracting features from the sub-basin terrain parameter set.

[0074] Specifically, the specific method for obtaining reference flood data through analysis includes the following steps:

[0075] Step 1: Obtain a set of topographic features of flood-prone basins in the same region Among them, z represents the number of the flood-prone basin, b n Represents terrain features, represents the average elevation of the flood-prone basin z, F z represents the topographic factor of the flood-prone basin z, and the sub-basin topographic feature set is Where k represents the sub-basin number, a n Represents the sub-basin terrain characteristics. According to the terrain feature set and the sub-basin terrain feature set, the formula The terrain feature similarity is calculated, where TZ k represents the similarity of the topographic features between sub-basin k and reference basin z, and ||·|| represents the modular operation;

[0076] Step 2: Obtain the similarity of terrain features between sub-basin k and each flood-prone basin through step 1, screen out the basin with the maximum similarity of terrain features, and use the corresponding flood-prone basin as the reference basin of sub-basin k. Number the reference basin as e, where e=k, and obtain the historical flood data of the reference basin as the reference flood data of the target monitoring basin.

[0077] It should be further explained that the set of terrain features of flood-prone basins in the same region refers to the set of terrain features within the large basin where the target monitoring basin is located. The purpose of obtaining the set of terrain features of flood-prone basins in the same region is to ensure that the climate, soil type and geological structure of the basin area can remain consistent to a certain extent, which is conducive to using the historical flood data of flood-prone areas in the same region as reference flood data. In this embodiment, for the target monitoring basins where floods are not common, there are shortcomings such as scarce data and insufficient experience. Due to insufficient historical data, there is a lack of historical data to establish a prediction model for flood prediction. Taking into account the prediction accuracy, in this embodiment, the terrain data of the target monitoring basin is analyzed for terrain features, and historical flood data of reference basins with similar terrain features are found as reference flood data, which solves the problem of sparse data in the target monitoring basin. The reference flood data is the historical flood data of the reference basin within a preset time period before the flood breach.

[0078] Specifically, in S4, the specific method of obtaining the flood forecast list according to the flood risk coefficient includes the following steps:

[0079] S401: The reference flood data includes reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, and feature extraction is performed on the reference flood data to obtain a reference flood data feature set. Among them, t1 represents the historical monitoring time, e represents the reference basin number, si represents the flow characteristics of the reference basin, wi represents the water level characteristics of the reference basin, and fi represents the precipitation characteristics of the reference basin;

[0080] S402: Extract features from the real-time monitoring data set to obtain a real-time monitoring data feature set Where k represents the sub-basin number, t represents the real-time monitoring time, and t=t1, sr represents the flow characteristics of the sub-basin, wr represents the water level characteristics of the sub-basin, and fr represents the precipitation characteristics of the sub-basin;

[0081] S403: The flood risk assessment model is expressed as: Among them, F k represents the flood risk coefficient of sub-basin k;

[0082] S404: According to a preset risk threshold, sub-basins whose flood risk coefficients are less than or equal to the risk threshold are screened, and the flood risk coefficients of the screened sub-basins are sorted in ascending order, a flood forecast list is generated, and the flood forecast list is uploaded to the terminal.

[0083] It should be further explained that the sub-basin grid set is divided according to the riverbed elevation grid matrix, and the sub-basin set is obtained by numbering them. In this embodiment, the actual meaning of the numerator in the flood risk assessment model is to judge the discrete degree of the real-time monitoring data characteristics of the sub-basin k. When the value of the numerator is smaller, the degree of change of the data is greater, and vice versa, the degree of change of the data is smaller. In addition, the actual meaning of the denominator in the flood risk assessment model is to judge the distance between the reference flood feature set and the real-time monitoring data feature set. When the value of the denominator is smaller, the similarity of the two feature sets is higher. Therefore, the smaller the flood risk coefficient, the higher the flood risk. The flood risk coefficients of the sub-basins are sorted in order from small to large, that is, a flood forecast list of sub-basin flood risk levels from high to low is obtained, so that the regulatory authorities can arrange emergency rescue work within the sub-basin according to the degree of urgency.

[0084] Furthermore, the present application also provides a flood collaborative forecasting management system based on big data analysis, including:

[0085] The watershed division module obtains the grid slope set of the target monitoring watershed according to the topographic data, obtains the sub-watershed grid set by processing the grid slope set, and obtains the sub-watershed grid set by overall numbering;

[0086] The data collection module is used to collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set;

[0087] A data analysis module is used to construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set;

[0088] The flood forecasting module is used to process the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtain a flood forecast list according to the flood risk coefficient, and upload the flood forecast list to a terminal.

[0089] Specifically, the specific implementation steps for obtaining the grid slope set of the target monitoring basin based on the topographic data are as follows:

[0090] Step A1: Collect the topographic map of the target monitoring basin through remote sensing technology, rasterize the topographic map, and obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid of the i-th row and j-th column is recorded as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number;

[0091] Step A2: In the topographic map, obtain theij All adjacent grids, to obtain an adjacent grid set;

[0092] Step A3: Calculate the relationship between each grid in the adjacent grid set and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope of

[0093] Step A4: Repeat steps A2 and A3 until the grid slopes of all grids are selected to obtain a grid slope set.

[0094] Specifically, by processing the grid slope set to obtain the sub-basin grid set, and performing overall numbering on the sub-basin grid set, a specific implementation method for obtaining the sub-basin set is as follows:

[0095] Set k slope levels, k ≥ 2, calculate the interval width according to the maximum grid slope and the minimum grid slope of the grid slope set obtained, determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j;

[0096] The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper bound of the kth slope grade range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, and this step is repeated until the upper bounds of all slope grade ranges are compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained;

[0097] k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

[0098] Specifically, the specific implementation method of obtaining the flood forecast list according to the flood risk coefficient is as follows:

[0099] The reference flood data includes a reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, feature extraction is performed on the reference flood data to obtain a reference flood data feature set, feature extraction is performed on the real-time monitoring data set to obtain a real-time monitoring data feature set, the reference flood data feature set and the real-time monitoring data feature set are processed by a flood risk assessment model to obtain a flood risk coefficient; based on a risk threshold, the flood risk coefficients of the sub-basins are screened to screen out sub-basins whose flood risk coefficients are less than the risk threshold, and the flood risk coefficients of the sub-basins are sorted in ascending order to generate a flood forecast list, and the flood forecast list is uploaded to a terminal.

[0100] The working principle and use process of the present invention:

[0101] Based on the topographic data, the target monitoring basin is divided and numbered to obtain a sub-basin set. The flow information, water level information and precipitation of the sub-basin set are collected to obtain a real-time monitoring data set. A sub-basin terrain parameter set is constructed based on the sub-basin set. Feature extraction is performed on the sub-basin terrain parameter set to obtain a sub-basin terrain feature set. Reference flood data is obtained by analyzing the sub-basin terrain feature set. Based on the reference flood data and the real-time monitoring data set, a flood risk coefficient is obtained through flood risk assessment model processing. Based on the flood risk coefficient, a flood forecast list is obtained, and the flood forecast list is uploaded to the terminal.

[0102] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0103] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0104] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wire, optical cable, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0105] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A flood collaborative forecasting management method based on big data analysis, characterized in that: The following steps are involved: S1: obtaining a grid slope set of the target monitoring basin according to the topographic data, obtaining a sub-basin grid set by processing the grid slope set, and performing overall numbering on the sub-basin grid sets to obtain a sub-basin set; S2: Collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set; S3: construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set; S4: Processing the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtaining a flood forecast list according to the flood risk coefficient, and uploading the flood forecast list to a terminal.

2. A flood collaborative forecasting management method based on big data analysis according to claim 1, characterized in that: In S1, the specific implementation steps of obtaining the grid slope set of the target monitoring basin based on the topographic data are as follows: The topographic map of the target monitoring basin is collected by remote sensing technology, and the topographic map is rasterized to obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid in the i-th row and j-th column is denoted as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number; In the topographic map, obtain the ij All adjacent grids are obtained to obtain the adjacent grid set, which is recorded as W(a ij )={a xy |x∈[i-1,i+1],y∈[j-1,j+1]}, and x and y are both positive integers, a xy Represents the grid a ij Any adjacent grid, calculate grid a ij With grid a xy Grid slope Wherein, d represents the grid spacing, and the grid spacing is the grid a ij Center point and grid a xy The straight-line distance between the center points, h(a xy ) represents grid a xy The altitude value, h(a ij ) represents grid a ij The altitude value of Calculate the adjacent grid set W(a ij ) and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope D(a ij );until the grid slope selection of i×j grids is completed, the grid slope set is obtained, which is recorded as P = {D(a ij )|i∈[1, I], j∈[1, J]}.

3. A flood collaborative forecasting management method based on big data analysis according to claim 2, characterized in that: In S1, the grid slope set is processed to obtain a sub-basin grid set, and the sub-basin grid set is numbered in a coordinated manner to obtain the sub-basin set. The specific implementation method is as follows: Set k slope levels, k ≥ 2, and obtain the maximum grid slope MAX(D(a ij )) and the minimum grid slope MIN(D(a ij )), calculate the interval width Determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j; The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper limit of the kth slope level range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, until the upper limit of all slope level ranges is compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained; k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

4. The method for collaborative flood forecasting management based on big data analysis according to claim 3 is characterized in that: In S3, the specific method for constructing the sub-basin terrain feature set is as follows: Get the number of grids in each sub-basin grid set and number the grids according to the number of grids. The sub-basin set is And r and q are both positive integers, where r represents the number of grids and q represents the sub-basin grid set number. The qth grid represents a sub-basin grid set with r grid numbers, and in, represents the grid elevation of the rth grid in the qth sub-basin grid set, and Where, represents the grid slope of the rth grid in the qth sub-basin grid set; Calculate the average elevation of sub-basins based on the sub-basin set in, The sub-basin topographic factor is calculated based on the sub-basin set. in, represents the sub-basin terrain factor of the qth sub-basin raster set; A sub-basin terrain parameter set is constructed according to the sub-basin average slope and the sub-basin terrain factor, and the sub-basin terrain feature set is obtained by extracting features from the sub-basin terrain parameter set.

5. A flood collaborative forecasting management method based on big data analysis according to claim 4, characterized in that: In S3, the specific method of obtaining reference flood data through analysis includes the following steps: Get a collection of topographic features of flood-prone basins in the same region Among them, z represents the number of the flood-prone basin, b n Represents terrain features, represents the average elevation of the flood-prone basin z, F z represents the topographic factor of the flood-prone basin z, and the sub-basin topographic feature set is Where k represents the sub-basin number, a n Represents the sub-basin terrain characteristics. According to the terrain feature set and the sub-basin terrain feature set, the formula The terrain feature similarity is calculated, where TZ k represents the similarity of the topographic features between sub-basin k and reference basin z, and ||·|| represents the modular operation; Based on the similarity of terrain features between sub-basin k and each flood-prone basin, the maximum terrain feature similarity is screened out, and the corresponding flood-prone basin is used as the reference basin of sub-basin k. The reference basin is numbered as e, and e=k, and the historical flood data of the reference basin is obtained as the reference flood data of the target monitoring basin.

6. The method for collaborative flood forecasting management based on big data analysis according to claim 1 is characterized in that: In S4, the specific method of obtaining the flood forecast list according to the flood risk coefficient includes the following steps: The reference flood data includes reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, and feature extraction is performed on the reference flood data to obtain a reference flood data feature set. Among them, t1 represents the historical monitoring time, e represents the reference basin number, si represents the flow characteristics of the reference basin, wi represents the water level characteristics of the reference basin, and fi represents the precipitation characteristics of the reference basin; Extract features from the real-time monitoring data set to obtain a real-time monitoring data feature set. Where k represents the sub-basin number, t represents the real-time monitoring time, and t=t1, sr represents the flow characteristics of the sub-basin, wr represents the water level characteristics of the sub-basin, and fr represents the precipitation characteristics of the sub-basin; The flood risk assessment model is expressed as: Among them, F k represents the flood risk coefficient of sub-basin k; According to the preset risk threshold, sub-basins with flood risk coefficients less than or equal to the risk threshold are screened, and the flood risk coefficients of the screened sub-basins are sorted in ascending order to generate a flood forecast list, which is then uploaded to the terminal.

7. A flood collaborative forecasting management system based on big data analysis, which implements a flood collaborative forecasting management method based on big data analysis as claimed in any one of claims 1 to 6, characterized in that: include: The watershed division module obtains a grid slope set of the target monitoring watershed according to the topographic data, obtains a sub-watershed grid set by processing the grid slope set, and performs overall numbering on the sub-watershed grid set to obtain a sub-watershed set; The data collection module is used to collect the flow information, water level information and precipitation of the sub-basin set to obtain a real-time monitoring data set; A data analysis module is used to construct a sub-basin terrain parameter set according to the sub-basin set, extract features from the sub-basin terrain parameter set to obtain a sub-basin terrain feature set, and obtain reference flood data by analyzing the sub-basin terrain feature set; The flood forecasting module is used to process the reference flood data and the real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtain a flood forecast list according to the flood risk coefficient, and upload the flood forecast list to a terminal.

8. The flood collaborative forecasting management system based on big data analysis according to claim 7 is characterized in that: The grid slope set of the target monitoring basin obtained based on the topographic data includes: The topographic map of the target monitoring basin is collected by remote sensing technology, and the topographic map is rasterized to obtain i×j grids, where i and j represent the row and column numbers of the rasterization, respectively. The grid in the i-th row and j-th column is denoted as a ij , i∈[1,I], j∈[1,J], I represents the maximum row number, and J represents the maximum column number; In the topographic map, obtain the ij All adjacent grids, to obtain an adjacent grid set; Calculate the relationship between each grid in the adjacent grid set and grid a ij The grid slopes between the two are calculated and the largest grid slope is selected as grid a ij The grid slope of Until the grid slope selection of i×j grids is completed, a grid slope set is obtained.

9. The flood collaborative forecasting management system based on big data analysis according to claim 7 is characterized in that: By processing the grid slope set, a sub-basin grid set is obtained, and the sub-basin grid set is numbered in a coordinated manner to obtain a sub-basin set including: Set k slope levels, k ≥ 2, calculate the interval width according to the maximum grid slope and the minimum grid slope of the grid slope set obtained, determine k slope level ranges according to the interval width, and for each slope level range, initialize a zero matrix O (pq) , where p and q represent the number of rows and columns respectively, and p=i, q=j; The grid slope set is converted into a grid slope matrix of size i×j, where the matrix element is the grid slope D(a ij ), compare the upper bound of each slope level range with each matrix element of the grid slope matrix. If the grid slope D(a mn ) is less than or equal to the upper limit of the kth slope level range, then the element of the mth row and nth column of the kth zero matrix is ​​set to 1, until the upper limit of all slope level ranges is compared with the matrix elements of the grid slope matrix, and k 01 matrices of size p×q are obtained; k 01 matrices are added together to generate a slope distribution matrix with p rows and q columns whose matrix elements range from 1 to k. The grid slope matrix is ​​mapped and marked according to the matrix element positions and matrix element values ​​of the slope distribution matrix. According to the marked values ​​and positions, k sub-basin raster sets are obtained, and the sub-basin set is obtained based on the sub-basin raster sets.

10. The flood collaborative forecasting management system based on big data analysis according to claim 7, characterized in that: The flood forecast list based on the flood risk factor includes: The reference flood data includes a reference basin number, reference basin flow information, reference basin water level information and reference basin precipitation. A reference flood data set is constructed based on the reference flood data, feature extraction is performed on the reference flood data to obtain a reference flood data feature set, feature extraction is performed on the real-time monitoring data set to obtain a real-time monitoring data feature set, the reference flood data feature set and the real-time monitoring data feature set are processed by a flood risk assessment model to obtain a flood risk coefficient; based on a risk threshold, the flood risk coefficients of the sub-basins are screened to screen out sub-basins whose flood risk coefficients are less than the risk threshold, and the flood risk coefficients of the sub-basins are sorted in ascending order to generate a flood forecast list, and the flood forecast list is uploaded to a terminal.

Images