A flood collaborative forecasting management system and method based on big data analysis

Abstract

The application relates to a flood cooperative forecasting management system and method based on big data analysis, and belongs to the technical field of big data analysis. The method comprises the following steps: obtaining a grid slope set of a target monitoring river basin according to overhead terrain data, obtaining a sub-river basin grid set and a sub-river basin set according to the grid slope set, and the division of the sub-river basin can help improve the accuracy of the location of the flood breach position of the target monitoring river basin; constructing a sub-river basin terrain parameter set according to the sub-river basin set, performing feature extraction on the sub-river basin terrain parameter set to obtain a sub-river basin terrain feature set, and obtaining referenceable flood data by analyzing the sub-river basin terrain feature set, so as to solve the problem of data scarcity of the target monitoring river basin, improve the referenceability of the data, process the referenceable flood data and a real-time monitoring data set through a flood risk assessment model to obtain a flood risk coefficient, obtain a flood forecasting list according to the flood risk coefficient, and improve the management efficiency of flood forecasting.

Description

Technical Field

[0001] This invention belongs to the field of big data analytics technology, specifically relating to a flood collaborative forecasting management system and method based on big data analytics. Background Technology

[0002] Currently, flood forecasting technologies used in flood-prone areas rely on extensive historical data to build flood prediction models and predict the probability of flooding in a basin. However, for areas where floods are infrequent, there is not a large amount of historical data available for research and reference. This results in the lack of flood forecasting models, leading to untimely flood warnings, short evacuation time for residents, and consequently, disasters and economic losses. Summary of the Invention

[0003] To address the aforementioned problems in existing technologies, this invention provides a flood collaborative forecasting management system and method based on big data analysis. Based on topographic data, the target monitoring basin is divided and systematically numbered to obtain a set of sub-basins. Flow, water level, and precipitation information of the sub-basins are collected to obtain a real-time monitoring dataset. A set of sub-basin topographic parameters is constructed based on the sub-basin set. Features are extracted from the sub-basin topographic parameter set to obtain a set of sub-basin topographic features. Reference flood data is obtained by analyzing the sub-basin topographic feature set. Based on the reference flood data and the real-time monitoring dataset, a flood risk coefficient is obtained through a flood risk assessment model. A flood forecast list is generated based on the flood risk coefficient and uploaded to the terminal.

[0004] The objective of this invention can be achieved through the following technical solutions:

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

[0006] S1: Based on the topographic data, obtain the grid slope set of the target monitoring watershed. Process the grid slope set to obtain the sub-watershed grid set. Number the sub-watershed grid set in a unified manner to obtain the sub-watershed set.

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

[0008] S3: Construct a set of sub-basin topographic parameters based on the set of sub-basins, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features;

[0009] S4: Process the reference flood data and the real-time monitoring dataset through the flood risk assessment model to obtain the flood risk coefficient, obtain the flood forecast list based on the flood risk coefficient, and upload the flood forecast list to the terminal.

[0010] Preferably, the specific steps for obtaining the grid slope set of the target monitoring watershed based on top-view terrain data are as follows:

[0011] Step A1: Acquire an overhead topographic map of the target monitoring watershed using remote sensing technology. Rasterize the topographic map 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], where I represents the maximum row number and J represents the maximum column number;

[0012] Step A2: In the topographic map, obtain the data corresponding to grid a. ij The set of adjacent grid cells is obtained by taking all adjacent grid cells, denoted 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 Indicates the relationship with grid a ij For any adjacent raster cell, calculate raster cell a. ij With grid a xy grid slope Where d represents the grid spacing, and the grid spacing is 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;

[0013] Step A3: Calculate the adjacent grid set W(a) ij Each grid cell in the grid is related to grid cell a. ij The grid slope between the grids is determined, 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 slope selection for all grid cells is completed, resulting in a grid slope set, denoted as P = {D(a ij )|i∈[1, I], j∈[1, J]}.

[0015] Preferably, by processing the grid slope set to obtain a sub-basin grid set, and then assigning a unified number to the sub-basin grid set, the specific implementation method for obtaining the sub-basin set is as follows:

[0016] Set k slope levels, k≥2, and obtain the maximum grid slope MAX(D(a) of the grid slope set. ij )) and minimum grid slope MIN(D(a ij )) Calculate the interval width Based on the interval width, k slope grade ranges are determined. For each slope grade range, a zero matrix O is initialized. (pq) Where p and q represent the number of rows and columns, respectively, and p = i, q = j;

[0017] The set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then set the element in the m-th row and n-th column of the kth zero matrix to 1. Repeat this step until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q.

[0018] Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

[0019] Preferably, the calculation process for the sub-basin average elevation and sub-basin topographic factors is as follows:

[0020] Obtain the number of grid cells in each sub-basin grid set, and number the grid cells according to the number of grid cells. The sub-basin set is... Both r and α are positive integers, where r represents the number of raster cells and α represents the raster set number of the sub-basin. Let represent the set of sub-basin grid cells with number r for the α-th grid, and in, This represents the r-th cell elevation in the r-th cell of the α-th sub-basin raster set, and also... in, This represents the grid slope of the r-th grid in the α-th sub-basin grid set. If s = 1, it represents the grid elevation characteristic; if s = 2, it represents the grid slope characteristic.

[0021] Calculate the average elevation of the sub-basins based on the sub-basin set. in, This represents the average elevation of the α-th sub-basin raster set, and the sub-basin topographic factor is calculated based on the sub-basin set. in, The sub-basin topographic factor represents the α-th sub-basin grid set, and f represents the number of grids;

[0022] A set of sub-basin topographic parameters is constructed based on the average elevation and topographic factors of the sub-basin, and the sub-basin topographic feature set is obtained by feature extraction from the set of sub-basin topographic parameters.

[0023] Preferably, the calculation process for terrain feature similarity is as follows:

[0024] Step 1: Obtain the set of topographic features of flood-prone watersheds in the same region. Where z represents the flood-prone river basin number, b s Indicates terrain features, This represents the average elevation of the flood-prone river basin z. The topographic factor represents the flood-prone watershed z, and the set of sub-watershed topographic features is: Where v represents the sub-basin number, β s Indicates the topographic features of the sub-basin. This represents the average elevation of sub-basin v. The topographic factor representing sub-basin v is determined by the formula based on the set of topographic features and the set of topographic features of the sub-basin. The terrain feature similarity was calculated, where TZ v，z The similarity of topographic features between sub-basin v and flood-prone basin z is represented by ||·||, where ||·|| represents the modular operation.

[0025] Step 2: Obtain the topographic feature similarity between sub-basin v and each flood-prone basin through Step 1, filter out the top-value topographic feature similarity, and use the corresponding flood-prone basin as the reference basin for sub-basin v. The reference basin is numbered as e, and the historical flood data of the reference basin is obtained as the reference flood data for the target monitoring basin.

[0026] Preferably, in S4, the specific method for obtaining the flood forecast list based on the flood risk coefficient includes the following steps:

[0027] S401: The reference flood data includes reference basin number, reference basin discharge information, reference basin water level information, and reference basin precipitation. A reference flood dataset 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. Where t1 represents the historical monitoring time, e represents the reference basin number, si represents the reference basin flow characteristics, wi represents the reference basin water level characteristics, and fi represents the reference basin precipitation characteristics.

[0028] S402: Extract features from the real-time monitoring dataset to obtain a real-time monitoring data feature set. Where t represents the real-time monitoring time, 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 follows: Among them, F v This represents the flood risk coefficient of sub-basin v, where u and u0 are the serial numbers of the monitoring time.

[0030] S404: Based on the preset risk threshold, select sub-basins with flood risk coefficients less than or equal to the risk threshold, sort the selected sub-basins in ascending order of flood risk coefficients, generate a flood forecast list, and upload the flood forecast list to the terminal.

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

[0032] The watershed division module obtains a set of grid slopes for the target monitoring watershed based on topographic data from above. By processing the set of grid slopes, a set of sub-watershed grids is obtained. The sub-watershed grids are then numbered in a unified manner to obtain a set of sub-watersheds.

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

[0034] The data analysis module is used to construct a set of sub-basin topographic parameters based on the set of sub-basins, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features.

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

[0036] Preferably, the specific steps for obtaining the grid slope set of the target monitoring watershed based on top-view terrain data are as follows:

[0037] Step A1: Acquire an overhead topographic map of the target monitoring watershed using remote sensing technology. Rasterize the topographic map 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], where I represents the maximum row number and J represents the maximum column number;

[0038] Step A2: In the topographic map, obtain the data corresponding to grid a. ij The set of adjacent grid cells is obtained by combining all adjacent grid cells.

[0039] Step A3: Calculate the relationship between each cell in the adjacent cell set and cell a. ij The grid slope between the grids is determined, and the largest grid slope is selected as grid a. ij The grid slope;

[0040] Step A4: Repeat steps A2 and A3 until the grid slope selection for all grids is completed, resulting in a grid slope set.

[0041] Preferably, by processing the grid slope set to obtain a sub-basin grid set, and then assigning a unified number to the sub-basin grid set, the specific implementation method for obtaining the sub-basin set is as follows:

[0042] Set k slope levels, k≥2. Calculate the interval width based on the maximum and minimum grid slopes of the obtained grid slope set. Determine the range of k slope levels based on the interval width. 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 set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then set the element in the m-th row and n-th column of the kth zero matrix to 1. Repeat this step until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q.

[0044] Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

[0045] Preferably, the specific implementation method for obtaining the flood forecast list based on the flood risk coefficient is as follows:

[0046] The reference flood data includes reference basin number, reference basin flow information, reference basin water level information, and reference basin precipitation. A reference flood dataset is constructed based on the reference flood data. Features are extracted from the reference flood data to obtain a reference flood data feature set. Features are also extracted from the real-time monitoring dataset 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 sub-basins are screened, and sub-basins with flood risk coefficients less than the risk threshold are selected. The flood risk coefficients of the sub-basins are then sorted in ascending order to generate a flood forecast list, which is then uploaded to the terminal.

[0047] The beneficial effects of this invention are as follows:

[0048] 1. By setting up a watershed division module, a grid slope set of the target monitoring watershed is obtained based on the topographic data. The grid slope set is then processed to obtain a sub-watershed grid set. The sub-watershed grid sets are then numbered in a unified manner to obtain a sub-watershed set. Dividing the sub-watersheds based on the topographic data is beneficial for flood disaster early warning of the target monitoring watershed and can help improve the accuracy of locating the location of flood breaches in the target monitoring watershed.

[0049] 2. By setting up a data analysis module, a set of sub-basin topographic parameters is constructed based on the sub-basin set. Features are extracted from the sub-basin topographic parameter set to obtain a set of sub-basin topographic features. Reference flood data is obtained by analyzing the set of sub-basin topographic features. Based on the topographic features of the sub-basins, flood-prone basins with similar topographic features are found. Historical flood data of flood-prone basins in the same region are used as reference flood data for the sub-basins. This solves the problem of data scarcity for infrequently flooded basins. The obtained reference flood data is historical flood data of flood-prone basins in the same region, ensuring that the climatic and geological characteristics between basins are similar, thus ensuring the referenceability of the data.

[0050] 3. By setting up a flood forecasting module, the reference flood data and the real-time monitoring dataset are processed through a flood risk assessment model to obtain flood risk coefficients. Based on the flood risk coefficients, a flood forecast list is generated and uploaded to the terminal. Based on the flood risk coefficients of the sub-basins, a flood forecast list for the target monitoring basin is obtained. By uploading the flood forecast list to the terminal, the management efficiency of flood forecasting is improved, so that regulatory authorities can dispatch and arrange emergency rescue and disaster relief and personnel evacuation work in the target monitoring basin according to the degree of urgency. Attached Figure Description

[0051] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart illustrating a flood collaborative forecasting and management method based on big data analysis according to the present invention. Detailed Implementation

[0053] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0054] Please see Figure 1 A flood collaborative forecasting and management method based on big data analysis includes the following steps:

[0055] S1: Based on the topographic data, obtain the grid slope set of the target monitoring watershed. Process the grid slope set to obtain the sub-watershed grid set. Number the sub-watershed grid set in a unified manner to obtain the sub-watershed set.

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

[0057] S3: Construct a set of sub-basin topographic parameters based on the set of sub-basins, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features;

[0058] S4: Process the reference flood data and the real-time monitoring dataset through the flood risk assessment model to obtain the flood risk coefficient, obtain the flood forecast list based on the flood risk coefficient, and upload the flood forecast list to the terminal.

[0059] It should be further explained that the target monitoring basin in this invention is a small basin lacking historical flood data. The flood forecast list is pushed to the terminal, and the regulatory department carries out emergency rescue and disaster relief deployment work based on 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 steps for obtaining the grid slope set of the target monitoring watershed based on top-view terrain data are as follows:

[0061] Step A1: Acquire an overhead topographic map of the target monitoring watershed using remote sensing technology. Rasterize the topographic map 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], where I represents the maximum row number and J represents the maximum column number;

[0062] Step A2: In the topographic map, obtain the data corresponding to grid a. ij The set of adjacent grid cells is obtained by taking all adjacent grid cells, denoted 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 Indicates the relationship with grid a ij For any adjacent raster cell, calculate raster cell a. ij With grid a xy grid slope Where d represents the grid spacing, and the grid spacing is 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;

[0063] Step A3: Calculate the adjacent grid set W(a) ij Each grid cell in the grid is related to grid cell a. ij The grid slope between the grids is determined, 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 slope selection for all grid cells is completed, resulting in a grid slope set, denoted as P = {D(a ij )|i∈[1, I], j∈[1, J]}.

[0065] Specifically, by processing the grid slope set, a sub-basin grid set is obtained. The sub-basin grid set is then systematically numbered to obtain the sub-basin set. The specific implementation method for this is as follows:

[0066] Set k slope levels, k≥2, and obtain the maximum grid slope MAX(D(a) of the grid slope set. ij )) and minimum grid slope MIN(D(a ij )) Calculate the interval width Based on the interval width, k slope grade ranges are determined. For each slope grade range, a zero matrix O is initialized. (pq) Where p and q represent the number of rows and columns, respectively, and p = i, q = j;

[0067] The set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then set the element in the m-th row and n-th column of the kth zero matrix to 1. Repeat this step until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q.

[0068] Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

[0069] It should be further explained that the advantage of dividing the target monitoring watershed into sub-watersheds based on topographic data is that it fully considers the topographic changes of the target monitoring watershed. By dividing the watershed into sub-watersheds based on graded slope values, on the one hand, it can accurately reflect the topographic changes of the target monitoring watershed. On the other hand, dividing the watershed into sub-watersheds based on topographic data is conducive to the management of the target monitoring watershed and refined flood disaster early warning, which can help improve the accuracy of locating the location of flood breaches in the target monitoring watershed.

[0070] Specifically, the calculation process for the sub-basin average elevation and sub-basin topographic factors is as follows:

[0071] Obtain the number of grid cells in each sub-basin grid set, and number the grid cells according to the number of grid cells. The sub-basin set is... Both r and α are positive integers, where r represents the number of raster cells and α represents the raster set number of the sub-basin. Let represent the set of sub-basin grid cells with number r for the α-th grid, and in, This represents the r-th cell elevation in the r-th cell of the α-th sub-basin raster set, and also... in, This represents the grid slope of the r-th grid in the α-th sub-basin grid set. If s = 1, it represents the grid elevation characteristic; if s = 2, it represents the grid slope characteristic.

[0072] Calculate the average elevation of the sub-basins based on the sub-basin set. in, This represents the average elevation of the α-th sub-basin raster set, and the sub-basin topographic factor is calculated based on the sub-basin set. in, The sub-basin topographic factor represents the α-th sub-basin grid set, and f represents the number of grids;

[0073] A set of sub-basin topographic parameters is constructed based on the average elevation and topographic factors of the sub-basin, and the sub-basin topographic feature set is obtained by feature extraction from the set of sub-basin topographic parameters.

[0074] Specifically, the calculation process for terrain feature similarity is as follows:

[0075] Step 1: Obtain the set of topographic features of flood-prone watersheds in the same region. Where z represents the flood-prone river basin number, b s Indicates terrain features, This represents the average elevation of the flood-prone river basin z. The topographic factor represents the flood-prone watershed z, and the set of sub-watershed topographic features is: Where v represents the sub-basin number, β s Indicates the topographic features of the sub-basin. This represents the average elevation of sub-basin v. The topographic factor representing sub-basin v is determined by the formula based on the set of topographic features and the set of topographic features of the sub-basin. The terrain feature similarity was calculated, where TZ v，z The similarity of topographic features between sub-basin v and flood-prone basin z is represented by ||·||, where ||·|| represents the modular operation.

[0076] Step 2: Obtain the topographic feature similarity between sub-basin v and each flood-prone basin through Step 1, filter out the top-value topographic feature similarity, and use the corresponding flood-prone basin as the reference basin for sub-basin v. The reference basin is numbered as e, and the historical flood data of the reference basin is obtained as the reference flood data for the target monitoring basin.

[0077] It should be further explained that the set of topographic features of flood-prone watersheds in the same region refers to the set of topographic features within the larger watershed where the target monitoring watershed is located. The purpose of obtaining the set of topographic features of flood-prone watersheds in the same region is to ensure that the climate, soil type and geological structure of the watershed area can maintain a certain degree of consistency, which is beneficial to using historical flood data of flood-prone areas in the same region as reference flood data. In this embodiment, for target monitoring watersheds that do not frequently experience floods, there are disadvantages of data scarcity and insufficient experience. Due to the lack of historical data, there is a lack of historical data to build a prediction model for flood prediction. Considering the accuracy of prediction, in this embodiment, topographic feature analysis is performed on the topographic data of the target monitoring watershed to find historical flood data of reference watersheds with similar topographic features as reference flood data, which solves the problem of data scarcity in the target monitoring watershed. The reference flood data is the historical flood data of the reference watershed within a preset time period before the flood breach.

[0078] Specifically, in S4, the method for obtaining a flood forecast inventory based on the flood risk coefficient includes the following steps:

[0079] S401: The reference flood data includes reference basin number, reference basin discharge information, reference basin water level information, and reference basin precipitation. A reference flood dataset 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. Where t1 represents the historical monitoring time, e represents the reference basin number, si represents the reference basin flow characteristics, wi represents the reference basin water level characteristics, and fi represents the reference basin precipitation characteristics.

[0080] S402: Extract features from the real-time monitoring dataset to obtain a real-time monitoring data feature set. Where t represents the real-time monitoring time, 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 follows: Among them, F v This represents the flood risk coefficient of sub-basin v, where u and u0 are the serial numbers of the monitoring time.

[0082] S404: Based on the preset risk threshold, select sub-basins with flood risk coefficients less than or equal to the risk threshold, sort the selected sub-basins in ascending order of flood risk coefficients, generate a flood forecast list, and upload the flood forecast list to the terminal.

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

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

[0085] The watershed division module obtains a set of grid slopes for the target monitoring watershed based on topographic data from above. By processing the set of grid slopes, a set of sub-watershed grids is obtained. The sub-watershed grids are then numbered in a unified manner to obtain a set of sub-watersheds.

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

[0087] The data analysis module is used to construct a set of sub-basin topographic parameters based on the set of sub-basins, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features.

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

[0089] Specifically, the steps for obtaining the grid slope set of the target monitoring watershed based on top-view terrain data are as follows:

[0090] Step A1: Acquire an overhead topographic map of the target monitoring watershed using remote sensing technology. Rasterize the topographic map 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], where I represents the maximum row number and J represents the maximum column number;

[0091] Step A2: In the topographic map, obtain the data corresponding to grid a. ij The set of adjacent grid cells is obtained by combining all adjacent grid cells.

[0092] Step A3: Calculate the relationship between each cell in the adjacent cell set and cell a. ij The grid slope between the grids is determined, and the largest grid slope is selected as grid a. ij The grid slope;

[0093] Step A4: Repeat steps A2 and A3 until the grid slope selection for all grids is completed, resulting in a grid slope set.

[0094] Specifically, by processing the grid slope set, a sub-basin grid set is obtained. The sub-basin grid set is then systematically numbered to obtain the sub-basin set. The specific implementation method for this is as follows:

[0095] Set k slope levels, k≥2. Calculate the interval width based on the maximum and minimum grid slopes of the obtained grid slope set. Determine the range of k slope levels based on the interval width. 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 set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then set the element in the m-th row and n-th column of the kth zero matrix to 1. Repeat this step until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q.

[0097] Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

[0098] Specifically, the method for obtaining a flood forecast list based on the flood risk coefficient is as follows:

[0099] The reference flood data includes reference basin number, reference basin flow information, reference basin water level information, and reference basin precipitation. A reference flood dataset is constructed based on the reference flood data. Features are extracted from the reference flood data to obtain a reference flood data feature set. Features are also extracted from the real-time monitoring dataset 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 sub-basins are screened, and sub-basins with flood risk coefficients less than the risk threshold are selected. The flood risk coefficients of the sub-basins are then sorted in ascending order to generate a flood forecast list, which is then uploaded to the terminal.

[0100] Working principle and usage process of this invention:

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

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

[0103] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0104] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, etc., or any suitable combination thereof. The computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A flood collaborative forecasting and management method based on big data analysis, characterized in that, Includes the following steps: S1: Based on the topographic data, obtain the grid slope set of the target monitoring watershed. Process the grid slope set to obtain the sub-watershed grid set. Number the sub-watershed grid set in a unified manner to obtain the sub-watershed set. S2: Collect flow, water level and precipitation information of the sub-basin set to obtain real-time monitoring dataset; S3: Construct a set of sub-basin topographic parameters based on the average elevation and topographic factors of the sub-basin, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features; Based on the similarity of topographic features between sub-basin v and each flood-prone basin, the maximum similarity of topographic features is selected, and the flood-prone basin corresponding to it is used as a reference basin for sub-basin v. The reference basin is numbered as e, and the historical flood data of the reference basin is obtained as the reference flood data for the target monitoring basin. S4: Process the reference flood data and the real-time monitoring dataset through the flood risk assessment model to obtain the flood risk coefficient, obtain the flood forecast list based on the flood risk coefficient, and upload the flood forecast list to the terminal; In S4, the specific method for obtaining the flood forecast list based on the flood risk coefficient includes the following steps: The reference flood data includes reference basin number, reference basin discharge information, reference basin water level information, and reference basin precipitation. A reference flood dataset 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. Where t1 represents the historical monitoring time, e represents the reference basin number, si represents the reference basin flow characteristics, wi represents the reference basin water level characteristics, and fi represents the reference basin precipitation characteristics. Feature extraction is performed on the real-time monitoring dataset to obtain the real-time monitoring data feature set. Where t represents the real-time monitoring time, 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 follows: Among them, F v This represents the flood risk coefficient of sub-basin v, where u and u0 are the serial numbers of the monitoring time. Based on the preset risk threshold, sub-basins with flood risk coefficients less than or equal to the risk threshold are selected, and the flood risk coefficients of the selected sub-basins are sorted in ascending order to generate a flood forecast list, which is then uploaded to the terminal.

2. The flood collaborative forecasting and management method based on big data analysis according to claim 1, characterized in that, In S1, the specific steps for obtaining the grid slope set of the target monitoring watershed based on the top-down terrain data are as follows: A topographic map of the target monitoring watershed is acquired using remote sensing technology. This topographic map is then rasterized to obtain i×j grids, where i and j represent the row and column numbers of the rasterized data, respectively. The grid in the i-th row and j-th column is denoted as a. ij i∈[1, I], j∈[1, J], where I represents the maximum row number and J represents the maximum column number; In the topographic map, obtain the grid a. ij The set of adjacent grid cells is obtained by taking all adjacent grid cells, denoted 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 Indicates the relationship with grid a ij For any adjacent raster cell, calculate raster cell a. ij With grid a xy grid slope Where d represents the grid spacing, and the grid spacing is 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; Calculate the adjacent grid set W(a) ij Each grid cell in the grid is related to grid cell a. ij The grid slope between the grids is determined, 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, denoted as P={D(a ij )|i∈[1, I], j∈[1, J]}.

3. The flood collaborative forecasting and management method based on big data analysis according to claim 2, characterized in that, In S1, by processing the grid slope set, a sub-basin grid set is obtained. The sub-basin grid set is then systematically numbered 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) of the grid slope set. ij )) and minimum grid slope MIN(D(a ij )) Calculate the interval width Based on the interval width, k slope grade ranges are determined. For each slope grade range, a zero matrix O is initialized. (pq) Where p and q represent the number of rows and columns, respectively, and p = i, q = j; The set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then the element in the m-th row and n-th column of the kth zero matrix is ​​set to 1, until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q. Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

4. The flood collaborative forecasting and management method based on big data analysis according to claim 3, characterized in that, In S3, the calculation process for the sub-basin average elevation and sub-basin topographic factor is as follows: Obtain the number of grid cells in each sub-basin grid set, and number the grid cells according to the number of grid cells. The sub-basin set is... Both r and α are positive integers, where r represents the number of raster cells and α represents the raster set number of the sub-basin. Let represent the set of sub-basin grid cells with number r for the α-th grid, and in, This represents the r-th cell elevation in the r-th cell of the α-th sub-basin raster set, and also... in, This represents the grid slope of the r-th grid in the α-th sub-basin grid set. If s = 1, it represents the grid elevation characteristic; if s = 2, it represents the grid slope characteristic. Calculate the average elevation of the sub-basins based on the sub-basin set. in, This represents the average elevation of the α-th sub-basin raster set, and the sub-basin topographic factor is calculated based on the sub-basin set. in, Let f represent the sub-basin topographic factor of the α-th sub-basin raster set, and let f represent the number of raster cells.

5. The flood collaborative forecasting and management method based on big data analysis according to claim 4, characterized in that, In S3, the calculation process for terrain feature similarity is as follows: Obtain the set of topographic features of flood-prone watersheds in the same region. Where z represents the flood-prone river basin number, b s Indicates terrain features, This represents the average elevation of the flood-prone river basin z. The topographic factor represents the flood-prone watershed z, and the set of sub-watershed topographic features is: Where v represents the sub-basin number, β s Indicates the topographic features of the sub-basin. This represents the average elevation of sub-basin v. The topographic factor representing sub-basin v is determined by the formula based on the set of topographic features and the set of topographic features of the sub-basin. The terrain feature similarity was calculated, where TZ v，z The similarity of topographic features between sub-basin v and flood-prone basin z is represented by ||·||, where ||·|| represents the modular operation.

6. A flood collaborative forecasting and management system based on big data analysis, executing the flood collaborative forecasting and management method based on big data analysis as described in any one of claims 1-5, characterized in that, include: The watershed division module obtains a set of grid slopes for the target monitoring watershed based on topographic data from above. By processing the set of grid slopes, a set of sub-watershed grids is obtained. The sub-watershed grids are then numbered in a unified manner to obtain a set of sub-watersheds. The data acquisition module is used to collect flow information, water level information and precipitation of the sub-basin set to obtain real-time monitoring datasets; The data analysis module is used to construct a set of sub-basin topographic parameters based on the set of sub-basins, extract features from the set of sub-basin topographic parameters to obtain a set of sub-basin topographic features, and obtain reference flood data by analyzing the set of sub-basin topographic features. The flood forecasting module is used to process the reference flood data and the real-time monitoring dataset through the flood risk assessment model to obtain the flood risk coefficient, generate a flood forecast list based on the flood risk coefficient, and upload the flood forecast list to the terminal.

7. A flood collaborative forecasting and management system based on big data analysis according to claim 6, characterized in that, The grid slope set of the target monitoring watershed obtained based on top-view terrain data includes: A topographic map of the target monitoring watershed is acquired using remote sensing technology. This topographic map is then rasterized to obtain i×j grids, where i and j represent the row and column numbers of the rasterized data, respectively. The grid in the i-th row and j-th column is denoted as a. ij i∈[1, I], j∈[1, J], where I represents the maximum row number and J represents the maximum column number; In the topographic map, obtain the grid a. ij The set of adjacent grid cells is obtained by combining all adjacent grid cells. Calculate the relationship between each cell in the adjacent cell set and cell a. ij The grid slope between the grids is determined, and the largest grid slope is selected as grid a. ij The grid slope; The grid slope selection is completed for i×j grid cells, resulting in a grid slope set.

8. A flood collaborative forecasting and management system based on big data analysis according to claim 7, characterized in that, By processing the grid slope set, a sub-basin grid set is obtained. The sub-basin grid sets are then systematically numbered to obtain the following sub-basin sets: Set k slope levels, k≥2. Calculate the interval width based on the maximum and minimum grid slopes of the obtained grid slope set. Determine the range of k slope levels based on the interval width. 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 set of grid slopes is transformed into a grid slope matrix of size i×j, where the matrix elements are the grid slopes D(a). ij The upper bound of each slope grade range is compared with each element of the raster slope matrix. If the raster slope D(a) is lower than the upper bound of the upper bound of the lower ... mn If the value of the slope grade range is less than or equal to the upper bound of the kth slope grade range, then the element in the m-th row and n-th column of the kth zero matrix is ​​set to 1, until the upper bound of all slope grade ranges is compared with the matrix elements of the grid slope matrix, resulting in k 0-1 matrices of size p×q. Add k 0-1 matrices together to generate a slope distribution matrix with p rows and q columns, where the matrix elements range from 1 to k. Map and mark the raster slope matrix according to the matrix element positions and values. Obtain k sub-basin raster sets based on the marked values ​​and positions. Obtain the sub-basin set based on the sub-basin raster sets.

9. A flood collaborative forecasting and management system based on big data analysis according to claim 6, characterized in that, The flood forecast list derived from the flood risk coefficient includes: The reference flood data includes reference basin number, reference basin flow information, reference basin water level information, and reference basin precipitation. A reference flood dataset is constructed based on the reference flood data. Features are extracted from the reference flood data to obtain a reference flood data feature set. Features are also extracted from the real-time monitoring dataset 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 sub-basins are screened, and sub-basins with flood risk coefficients less than the risk threshold are selected. The flood risk coefficients of the sub-basins are then sorted in ascending order to generate a flood forecast list, which is then uploaded to the terminal.

Images