Rainfall runoff path prediction method and system, electronic device and storage medium

Abstract

The application provides a rainfall catchment path prediction method and system, electronic equipment and storage medium, and relates to the technical field of data processing. The digital elevation model of the monitoring area is gridded, the maximum and minimum elevation values in the digital elevation model are identified, the catchment starting grid and the catchment ending grid are obtained, the grid with the minimum elevation value in the adjacent grid of the catchment starting grid is selected as a new center grid, the grid with the minimum elevation value in the adjacent grid of the new center grid is selected as the next new center grid in a cycle, and the selection of the new center grid is the catchment ending grid. Starting from the catchment starting grid, the catchment starting grid and all the selected center grids are connected in turn according to the order in which all the center grids are selected, and the predicted catchment path is obtained. Since the method is based on the digital elevation model, it is not affected by other factors, so the prediction result is more accurate and the prediction stability is higher.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, system, electronic device, and storage medium for predicting rainfall confluence paths. Background Technology

[0002] During floods or periods of heavy rainfall, it is necessary to monitor the runoff of precipitation to understand the potential inundation. Rainwater does not flow uniformly across the surface; instead, it converges and flows along specific paths (runoff paths) under the influence of gravity and topography. Predicting runoff paths allows for precise identification of the main direction, intensity, and final convergence area of ​​the water flow. Based on this, it is possible to more accurately predict which areas will be flooded, as well as the depth, extent, and potential rate of flooding, achieving precise spatial location of risk.

[0003] Existing methods utilize historical rainfall, water level, flow rate, and inundation monitoring data to train models using machine learning or deep learning algorithms, identify the relationship between rainfall characteristics and confluence paths and confluence results, and use this information to predict future confluence path conditions.

[0004] The models described above are typically pre-trained based on historical data. Their predictive ability for extreme rainfall events exceeding the range of historical data is questionable. Furthermore, insufficient or unrepresentative historical data can distort model parameters, leading to significant discrepancies between predicted and actual results and low prediction accuracy. Summary of the Invention

[0005] The problem that this invention aims to solve is that existing methods for path prediction using deep learning are based on historical data. If the historical data is insufficient, the prediction results will have large deviations and low accuracy.

[0006] To address the above problems, in a first aspect, the present invention provides a method for predicting rainfall confluence paths, comprising:

[0007] Obtain a digital elevation model of the monitored area, the digital elevation model including the elevation value of each terrain feature;

[0008] Grid the digital elevation model of the monitored area;

[0009] Identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting and ending grids of the confluence.

[0010] The grid with the smallest elevation value among the adjacent grids of the starting point grid is selected as the new center grid. The grid with the smallest elevation value among the adjacent grids of the new center grid is selected as the next new center grid, until the selected new center grid is the ending point grid of the confluence.

[0011] Starting from the confluence origin grid, the confluence origin grid and all selected center grids are connected sequentially in the order in which they are selected to obtain the predicted confluence path.

[0012] Optionally, the process of gridding the digital elevation model of the monitored area includes:

[0013] Based on the different properties of land cover, the digital elevation model of the monitoring area is divided into different land surface regions, which include water-covered regions, vegetation-covered regions, bare land regions, and artificial regions.

[0014] Different surface regions are gridded using corresponding parameters;

[0015] Analyze the area of ​​each incomplete grid to be merged at the boundary of different surface regions. When the area of ​​the grid to be merged is less than half the area of ​​a complete grid in the same surface region, merge the incomplete grid with a complete grid in the adjacent same surface region.

[0016] Optionally, identifying the maximum and minimum elevation values ​​in the digital elevation model and marking them accordingly as the confluence start-point grid and confluence end-point grid includes:

[0017] Identify the maximum and minimum elevation values ​​in the digital elevation model, and record the grid containing the maximum elevation value as the confluence starting point grid;

[0018] By combining SAR images, determine whether there is water in the grid where the minimum elevation value is located;

[0019] If a water body exists in the grid where the minimum elevation value is located, identify the water body coverage area;

[0020] Extract the boundary of the water body coverage area, mark the grids that the boundary passes through as the confluence endpoint grids, and eliminate the grids within the water body coverage area;

[0021] If there is no water body in the grid where the minimum elevation value is located, then the grid where the minimum elevation value is located is directly recorded as the confluence endpoint grid.

[0022] Optionally, the step of selecting the grid with the smallest elevation value among the adjacent grids of the confluence starting point grid as the new center grid, and cyclically selecting the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid, includes:

[0023] If there are multiple starting grids for the confluence, sort the multiple starting grids according to the distance between the starting grid and the ending grid in descending order to obtain the sequence of starting grids for the confluence.

[0024] Convergence path prediction is performed starting from each convergence starting grid in the order of the convergence starting grid sequence.

[0025] Starting from the second confluence origin grid, during the confluence path prediction process, if the grid with the smallest elevation value among the adjacent grids of the new central grid has been selected in the previous confluence path prediction, then analyze the elevation difference between the grid with the smallest elevation value and the grid with the second-to-last elevation value.

[0026] If the elevation difference is less than or equal to the preset difference, the grid with the second-to-last elevation value is selected as the next new center grid.

[0027] If the elevation difference is greater than the preset difference, the grid with the smallest elevation value will still be selected as the next new center grid.

[0028] Optionally, the step of selecting the grid with the smallest elevation value among the adjacent grids of the confluence starting point grid as the new center grid, and cyclically selecting the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid, includes:

[0029] When there are multiple grids with the smallest elevation values ​​among the grids adjacent to the central grid, the grids with the smallest elevation values ​​are selected according to a preset priority to determine the next new central grid. The preset priority order is as follows: grids that maintain the confluence trend unchanged, grids that were not selected in the previous confluence path prediction, grids with the shortest distance to the confluence endpoint grid, and grids on the horizontal side of the central grid.

[0030] Optionally, after obtaining the predicted confluence path by sequentially connecting the confluence origin grid and all selected center grids in the order in which all center grids are selected, starting from the confluence origin grid, the method further includes:

[0031] After predicting the confluence path from multiple confluence origin grids, the grid with the highest elevation value and the selected grid are excluded.

[0032] From the remaining grids in the digital elevation model, the grid with the largest elevation value is selected sequentially as the new starting point grid for confluence path prediction, until all grids have been selected.

[0033] Optionally, after obtaining the predicted confluence path by sequentially connecting the confluence origin grid and all selected center grids in the order in which all center grids are selected, starting from the confluence origin grid, the method further includes:

[0034] Acquire new SAR images and identify new water body coverage areas;

[0035] Based on the new water body coverage, update the confluence endpoint grid and eliminate confluence paths within the new water body coverage to simplify the predicted confluence paths.

[0036] Secondly, the present invention also provides a rainfall confluence path prediction system, comprising:

[0037] The digital elevation model acquisition module is used to acquire the digital elevation model of the monitored area, which includes the elevation value of each terrain feature.

[0038] The model meshing module is used to mesh the digital elevation model of the monitored area;

[0039] The model elevation value analysis module is used to identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting point grid and the ending point grid, respectively.

[0040] The confluence path analysis module is used to select the grid with the smallest elevation value among the adjacent grids of the confluence starting grid as the new center grid, and cyclically select the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid.

[0041] The confluence path prediction module is used to connect the confluence origin grid and all selected center grids sequentially, starting from the confluence origin grid, in the order in which all center grids are selected, to obtain the predicted confluence path.

[0042] Thirdly, the present invention provides an electronic device, including a memory and a processor;

[0043] The memory is used to store computer programs;

[0044] The processor is configured to implement the rainfall confluence path prediction method as described in the first aspect when executing the computer program.

[0045] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the rainfall confluence path prediction method as described in the first aspect.

[0046] This invention provides a method, system, electronic device, and storage medium for predicting rainfall runoff paths. Compared with existing technologies, it has the following advantages:

[0047] The digital elevation model (DEM) of the monitored area is gridded. By identifying the maximum and minimum elevation values ​​in the DEM, confluence starting point grids and confluence ending point grids are obtained. The grid with the smallest elevation value among the adjacent grids of the confluence starting point grid is selected as the new center grid. This process is repeated until the selected new center grid is the confluence ending point grid. Through this step-by-step analysis, the next flow direction of the water can be theoretically and accurately located. Then, starting from the confluence starting point grid, the confluence starting point grid and all selected center grids are connected sequentially according to the order in which they were selected to obtain the predicted confluence path. This allows for the early prediction of the water flow confluence path in the early stages of precipitation, enabling the early implementation of rescue measures, such as deploying diversion devices or roadblocks along the confluence path to change the direction of water flow and prevent flooding of key protected areas. Because this method is based on the DEM, it is not affected by other factors, resulting in more accurate and stable predictions. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a rainfall confluence path prediction method provided in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of the structure of a rainfall runoff path prediction system provided in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application are described clearly and completely. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0054] like Figure 1 As shown in the embodiment of this application, a rainfall confluence path prediction method includes:

[0055] S1: Obtain the digital elevation model of the monitored area, which includes the elevation value of each terrain feature.

[0056] S2: Grid the digital elevation model of the monitored area.

[0057] S3: Identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting and ending grids of the confluence.

[0058] S4: Select the grid with the smallest elevation value among the adjacent grids of the confluence starting point grid as the new center grid, and cyclically select the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid.

[0059] S5: Starting from the confluence origin grid, connect the confluence origin grid and all selected center grids in sequence according to the order in which all center grids are selected to obtain the predicted confluence path.

[0060] In this optional embodiment, the digital elevation model (DEM) of the monitored area is gridded. By identifying the maximum and minimum elevation values ​​in the DEM, confluence starting point grids and confluence ending point grids are obtained. The grid with the smallest elevation value among the adjacent grids of the confluence starting point grid is selected as the new center grid. This process is repeated until the selected new center grid is the confluence ending point grid. Through this step-by-step analysis, the next flow direction of the water can be theoretically and accurately located. Then, starting from the confluence starting point grid, the confluence starting point grid and all selected center grids are connected sequentially according to the order in which they are selected to obtain the predicted confluence path. This allows for the prediction of the water flow confluence path in advance during the early stages of precipitation, enabling the early implementation of rescue measures, such as deploying diversion devices or roadblocks along the confluence path to change the direction of water flow and prevent key protected areas from being flooded. Because this method is based on the DEM and is not affected by other factors, the prediction results are more accurate and the prediction stability is higher.

[0061] The following is a detailed description of each step.

[0062] S1: Obtain the digital elevation model of the monitored area, which includes the elevation value of each terrain feature.

[0063] S2: Grid the digital elevation model of the monitored area. This step specifically includes the following:

[0064] S21: Based on the different properties of land cover, the digital elevation model of the monitored area is divided into different land surface regions, wherein the land surface regions include water-covered regions, vegetation-covered regions, bare land regions, and artificial regions.

[0065] S22: Grid different surface regions using corresponding parameters.

[0066] Specifically, for example, water-covered areas may not be gridded, or they may be coarsely gridded without further refinement. However, vegetated areas (such as forests, grasslands, farmland, parks, etc.) and bare land areas (such as wasteland, fallow farmland, etc.) are gridded with more detail, while artificial areas (such as roads or squares) are gridded with fine detail, thus enabling targeted gridding for different areas.

[0067] S23: Analyze the area of ​​each incomplete grid to be merged at the boundary of different surface regions. When the area of ​​the grid to be merged is less than half the area of ​​a complete grid in the same surface region, merge the incomplete grid with a complete grid in the adjacent same surface region.

[0068] Specifically, since the shape of each region may be irregular, the grid formed within a region is uniform during gridding. However, at the boundaries of regions, the boundary shapes are irregular, resulting in incomplete grids. For example, there may be some incomplete grids at the boundary of an artificial region. The area of ​​these grids may be half, one-third, or even smaller than that of a complete grid. Analyzing these smaller incomplete grids as individual grids not only increases the number of grids but also makes individual analysis meaningless because the elevation values ​​of these small grids are basically not different from those of the surrounding grids. Therefore, they can be merged with any adjacent complete grid, thereby reducing the number of grids, improving analysis speed, and increasing the contact area between the boundary grids and other region grids. This reduces the difficulty of selecting the center point when predicting the confluence path and improves the accuracy of path planning.

[0069] S3: Identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting and ending grids of the confluence.

[0070] S31: Identify the maximum and minimum elevation values ​​in the digital elevation model, and record the grid containing the maximum elevation value as the confluence starting point grid.

[0071] S32: Combine SAR images to determine whether there is water in the grid where the minimum elevation value is located.

[0072] S33: If there is a water body in the grid where the minimum elevation value is located, identify the water body coverage area.

[0073] S34: Extract the boundary of the water body coverage area, record all grids that the boundary passes through as the confluence endpoint grids, and eliminate the grids within the water body coverage area.

[0074] Specifically, the surface receiver can generate high-resolution images by receiving echo signals reflected from ground objects. Different objects or surfaces with different roughness exhibit varying backscattering intensities to microwaves. Using a threshold segmentation method based on the backscattering intensity and a preset threshold, water and non-water bodies are identified. For example, if the preset threshold is set to -20dB, areas with backscattering intensities greater than -20dB are classified as non-water bodies, while areas with backscattering intensities less than or equal to -20dB are classified as water bodies. This allows for the identification of water areas in SAR images. By identifying water-covered areas on the surface through SAR images, these water bodies may be long-standing natural water bodies. Such water bodies are typically located in low-lying areas with water-collecting capacity. Therefore, for these inherently existing water bodies, the internal grid can be eliminated, focusing only on the boundaries. By retaining the boundary grid of the water body, the relationship between the grids of other adjacent areas and the grids at the water body boundary can be analyzed to determine whether water flows from other areas towards the water body.

[0075] S35: If there is no water body in the grid where the minimum elevation value is located, then the grid where the minimum elevation value is located is directly recorded as the confluence endpoint grid.

[0076] Specifically, by combining SAR images and further analyzing the surface conditions at the location of the minimum elevation value, the natural water body coverage area can be identified. This simplifies the gridding of the water body coverage area, reduces the number of grids, and improves the timeliness of the analysis. By focusing the analysis of the water body coverage area on the grids at the boundaries, the flow into the water coverage area can be monitored through the relationship between the boundary grids and the grids of adjacent areas, facilitating subsequent monitoring of the water body coverage area.

[0077] S4: Confluence Path Prediction: Select the grid with the smallest elevation value among the adjacent grids of the confluence starting point grid as the new center grid, and cyclically select the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence endpoint grid.

[0078] Specifically, by continuously selecting new central grids, the path of water flow confluence can be gradually explored until the confluence endpoint grid in a low-lying area is reached. However, the following points need to be noted during the confluence path prediction process:

[0079] S411: If there are multiple starting grids for the confluence, sort the multiple starting grids according to the distance between the starting grid and the ending grid in descending order to obtain the sequence of starting grids for the confluence.

[0080] S412: Predict the confluence path starting from each confluence starting grid in the order of the confluence starting grids in the confluence starting grid sequence.

[0081] Specifically, for example, if there are three grids with the highest elevation values, there are three confluence starting point grids. A potential problem arises: which grid to start exploring the confluence path from? Logically, one could start exploring the path simultaneously from all three starting points. However, this could lead to overlapping confluence paths, resulting in redundant analysis. If some grids are repeatedly selected, the probability of selecting other grids decreases, slowing down the overall analysis and reducing the amount of effective analysis. To avoid these problems, multiple confluence starting point grids can be analyzed sequentially. When predicting the confluence path, if multiple grids adjacent to the central grid have the lowest elevation values, these grids are selected according to a preset priority to determine the next new central grid. The preset priority order is as follows: grids that maintain the confluence trend, grids not selected in previous confluence path predictions, grids with the shortest distance to the confluence endpoint grid, and grids horizontally adjacent to the central grid. The confluence direction is the direction from the previous center grid to the new center grid. Since the center grid is constantly updated, the confluence direction may also change after each selection of a new center grid. Maintaining the confluence trend means that the newly generated confluence direction does not project a confluence direction component with the opposite direction to the previous confluence direction. That is, maintaining the confluence trend means that the new confluence direction is exactly the same as the previous confluence direction, the new confluence direction projects a confluence direction component with the same direction as the previous confluence direction, and the new confluence direction projects a zero component on the previous confluence direction (i.e., the two confluence directions are perpendicular).

[0082] By prioritizing grids that maintain the confluence trend, errors in confluence path prediction can be reduced. Prioritizing grids that were not selected in previous confluence path predictions avoids redundant grid selection, improving analysis efficiency. Furthermore, prioritizing grids with the shortest distance to the confluence endpoint and those horizontally aligned with the central grid provides direction for confluence path exploration, reduces analysis dead spots, and allows for orderly and continuous path exploration.

[0083] S413: Starting from the second confluence origin grid, during the confluence path prediction process, if the grid with the smallest elevation value among the adjacent grids of the new central grid has been selected in the previous confluence path prediction, then analyze the elevation difference between the grid with the smallest elevation value and the grid with the second-to-last elevation value.

[0084] S414: If the elevation difference is less than or equal to the preset difference, then select the second-to-last grid with the lowest elevation value as the next new center grid.

[0085] S415: If the elevation difference is greater than the preset difference, the grid with the smallest elevation value will still be selected as the next new center grid.

[0086] Specifically, if the grid with the smallest elevation value has already been selected during the previous path analysis, in order to reduce the number of times the grid is repeatedly selected, when the elevation difference between the grid with the smallest elevation value and the grid with the second-to-last elevation value is less than or equal to a preset difference, we can choose the grid with the second-to-last elevation value as a second-best option. This is because when the elevation values ​​of two adjacent grids are small, if water has already flowed through the grid with the smallest elevation value, other water flows will be pushed to the surrounding grids under the influence of the previous water flows. Therefore, when the elevation difference is small, choosing the grid with the second-to-last elevation value is a reasonable choice. This selection method can reduce the number of times the grid is repeatedly selected, improve the efficiency of traversing all grids, and also keep the water flow convergence trend consistent with the actual situation.

[0087] S5: Starting from the confluence origin grid, connect the confluence origin grid and all selected center grids in sequence according to the order in which all center grids are selected to obtain the predicted confluence path.

[0088] Specifically, by sequentially connecting the selected center grids between each starting grid and its corresponding ending grid, a predicted confluence path corresponding to the starting grid can be obtained.

[0089] S6: After predicting the confluence path from multiple confluence origin grids, exclude the grid with the highest elevation value and the selected grid.

[0090] S7: Select the grid with the largest elevation value from the remaining grids in the digital elevation model as the new starting grid for confluence path prediction, until all grids have been selected.

[0091] Specifically, since predicting the confluence path starting from the initial grid with the highest elevation value cannot cover all grids, the remaining grids need to be analyzed further. The grid with the highest elevation value and the previously selected grids are excluded. From the remaining grids, the grid with the highest elevation value is selected as the new confluence starting point grid. This process of predicting the confluence path is repeated, continuously selecting new confluence starting point grids until all grids have been selected. After analyzing all confluence paths from the gridded model, the concentration points of water flow can be observed holistically. If the location is an area requiring key protection, flood prevention and waterproofing measures can be implemented in advance, such as installing temporary water diversion and blocking facilities.

[0092] S8: Acquire new SAR images and identify new water body coverage areas.

[0093] S9: Update the confluence endpoint grid based on the new water body coverage and eliminate confluence paths within the new water body coverage to simplify the predicted confluence paths.

[0094] Specifically, as precipitation continues, water flows begin to converge. When the convergence reaches a certain level, surface water begins to accumulate or the water level in the original water body area begins to rise. Therefore, the water coverage area of ​​the monitoring area increases, or the original water coverage area expands. It is necessary to update the water coverage area in a timely manner, and then update the grid (convergence endpoint grid) that the boundary of the water coverage area passes through. Furthermore, the grid within the water coverage area should be further eliminated in a timely manner. This can reduce the number of grids, eliminate the confluence path within the new water coverage area, simplify the predicted confluence path, make the confluence trend easier to identify, increase the readability of the confluence path, and also improve the accuracy of the prediction.

[0095] In addition to predicting the confluence path, the confluence volume can be further predicted. The specific analysis process is as follows.

[0096] Due to the extremely complex geospatial features, after gridding, the slope length and average slope of a confluence path can be calculated based on the grid elevation values ​​traversed by the confluence path. Furthermore, the confluence time from each grid to the confluence endpoint grid can be calculated.

[0097]

[0098] In the formula, denoted as _ ...

[0099] According to the above formula, the confluence time of each grid can be determined. Therefore, the sum of the grid areas that flow to the water body coverage area or a certain confluence endpoint grid in each time period can be calculated based on the confluence time, which is the area under constant flow:

[0100]

[0101] In the formula, The area under constant flow is expressed in units of 1. ; The duration is measured in seconds (s). The sum of the grid areas flowing to the confluence endpoint grid during the i-th time period, in units of .

[0102] The average runoff depth at each time interval corresponding to the isochronous area, reaching the water body coverage area or a certain confluence endpoint grid, i.e., the isochronous runoff depth, is:

[0103]

[0104] In the formula, The runoff depth under constant flow conditions is expressed in mm. The average runoff depth in mm is the grid average depth of the flow reaching the confluence endpoint grid during the i-th time period corresponding to the isochronous area.

[0105] The sum of the flow rates from each grid to the confluence terminal grid within the time period is:

[0106]

[0107] In the formula, The sum of the flow rates from each grid cell to the terminal grid cell of the confluence, in units of... .

[0108] The sum of the flow rates from each grid to the confluence terminal grid within each time period is:

[0109]

[0110] The above calculations can be used to predict the water flow reaching the confluence endpoint grid or the water-covered area.

[0111] like Figure 2 As shown in the embodiment of this application, a rainfall confluence path prediction system includes:

[0112] The digital elevation model acquisition module 100 is used to acquire the digital elevation model of the monitored area, wherein the digital elevation model includes the elevation value of each terrain feature.

[0113] Model meshing module 200 is used to mesh the digital elevation model of the monitored area.

[0114] The model elevation value analysis module 300 is used to identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting point grid and the ending point grid, respectively.

[0115] The confluence path analysis module 400 is used to select the grid with the smallest elevation value among the adjacent grids of the confluence starting grid as the new center grid, and cyclically select the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid.

[0116] The confluence path prediction module 500 is used to connect the confluence origin grid and all selected center grids sequentially, starting from the confluence origin grid, in the order in which all center grids are selected, to obtain the predicted confluence path.

[0117] In this embodiment, the beneficial effects of the rainfall confluence path prediction system are similar to those of the rainfall confluence path prediction method described above, and will not be repeated here.

[0118] like Figure 3 As shown in the embodiment of this application, an electronic device includes a memory 610 and a processor 620; the memory 610 is used to store a computer program; the processor 620 is used to implement the rainfall confluence path prediction method as described above when the computer program is executed.

[0119] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the rainfall confluence path prediction method as described above.

[0120] In this embodiment, the beneficial effects of the electronic device and the computer-readable storage medium are similar to those of the above-described rainfall confluence path prediction method, and will not be repeated here.

[0121] The present invention describes electronic devices that can serve as servers or clients of this application, which are examples of hardware devices that can be applied to various aspects of this application. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the application described and / or claimed herein.

[0122] Electronic devices include a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM can also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0123] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the separately described modules may or may not be physically separate. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application according to actual needs. Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0125] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting rainfall confluence paths, characterized in that, include: Obtain a digital elevation model of the monitored area, the digital elevation model including the elevation value of each terrain feature; Grid the digital elevation model of the monitored area; Identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting and ending grids of the confluence. The grid with the smallest elevation value among the adjacent grids of the starting point grid is selected as the new center grid. The grid with the smallest elevation value among the adjacent grids of the new center grid is selected as the next new center grid, until the selected new center grid is the ending point grid of the confluence. Starting from the confluence origin grid, the confluence origin grid and all selected center grids are connected sequentially in the order in which they are selected to obtain the predicted confluence path.

2. The rainfall confluence path prediction method as described in claim 1, characterized in that, The process of gridding the digital elevation model of the monitored area includes: Based on the different properties of land cover, the digital elevation model of the monitoring area is divided into different land surface regions, which include water-covered regions, vegetation-covered regions, bare land regions, and artificial regions. Different surface regions are gridded using corresponding parameters; Analyze the area of ​​each incomplete grid to be merged at the boundary of different surface regions. When the area of ​​the grid to be merged is less than half the area of ​​a complete grid in the same surface region, merge the incomplete grid with a complete grid in the adjacent same surface region.

3. The rainfall confluence path prediction method as described in claim 1, characterized in that, The process of identifying the maximum and minimum elevation values ​​in the digital elevation model and marking them as the starting and ending grids of the confluence includes: Identify the maximum and minimum elevation values ​​in the digital elevation model, and record the grid containing the maximum elevation value as the confluence starting point grid; By combining SAR images, determine whether there is water in the grid where the minimum elevation value is located; If a water body exists in the grid where the minimum elevation value is located, identify the water body coverage area; Extract the boundary of the water body coverage area, mark the grids that the boundary passes through as the confluence endpoint grids, and eliminate the grids within the water body coverage area; If there is no water body in the grid where the minimum elevation value is located, then the grid where the minimum elevation value is located is directly recorded as the confluence endpoint grid.

4. The rainfall confluence path prediction method as described in claim 1, characterized in that, The process of selecting the grid with the smallest elevation value among the adjacent grids of the confluence starting point grid as the new center grid, and cyclically selecting the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid, includes: If there are multiple starting grids for the confluence, sort the multiple starting grids according to the distance between the starting grid and the ending grid in descending order to obtain the sequence of starting grids for the confluence. Convergence path prediction is performed starting from each convergence starting grid in the order of the convergence starting grid sequence. Starting from the second confluence origin grid, during the confluence path prediction process, if the grid with the smallest elevation value among the adjacent grids of the new central grid has been selected in the previous confluence path prediction, then analyze the elevation difference between the grid with the smallest elevation value and the grid with the second-to-last elevation value. If the elevation difference is less than or equal to the preset difference, the grid with the second-to-last elevation value is selected as the next new center grid. If the elevation difference is greater than the preset difference, the grid with the smallest elevation value will still be selected as the next new center grid.

5. The rainfall confluence path prediction method as described in claim 4, characterized in that, Also includes: When there are multiple grids with the smallest elevation values ​​among the grids adjacent to the central grid, the grids with the smallest elevation values ​​are selected according to a preset priority to determine the next new central grid. The preset priority order is as follows: grids that maintain the confluence trend unchanged, grids that were not selected in the previous confluence path prediction, grids with the shortest distance to the confluence endpoint grid, and grids on the horizontal side of the central grid.

6. The rainfall confluence path prediction method as described in claim 4, characterized in that, After the step of sequentially connecting the starting point grid and all selected center grids in the order in which all center grids are selected to obtain the predicted confluence path, the method further includes: After predicting the confluence path from multiple confluence origin grids, the grid with the highest elevation value and the selected grid are excluded. From the remaining grids in the digital elevation model, the grid with the largest elevation value is selected sequentially as the new starting point grid for confluence path prediction, until all grids have been selected.

7. The rainfall confluence path prediction method as described in claim 1, characterized in that, After the step of sequentially connecting the starting point grid and all selected center grids in the order in which all center grids are selected to obtain the predicted confluence path, the method further includes: Acquire new SAR images and identify new water body coverage areas; Based on the new water body coverage, update the confluence endpoint grid and eliminate confluence paths within the new water body coverage to simplify the predicted confluence paths.

8. A rainfall confluence path prediction system, characterized in that, include: The digital elevation model acquisition module is used to acquire the digital elevation model of the monitored area, which includes the elevation value of each terrain feature. The model meshing module is used to mesh the digital elevation model of the monitored area; The model elevation value analysis module is used to identify the maximum and minimum elevation values ​​in the digital elevation model and mark them as the starting point grid and the ending point grid, respectively. The confluence path analysis module is used to select the grid with the smallest elevation value among the adjacent grids of the confluence starting grid as the new center grid, and cyclically select the grid with the smallest elevation value among the adjacent grids of the new center grid as the next new center grid, until the selected new center grid is the confluence ending grid. The confluence path prediction module is used to connect the confluence origin grid and all selected center grids sequentially, starting from the confluence origin grid, in the order in which all center grids are selected, to obtain the predicted confluence path.

9. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to implement the rainfall confluence path prediction method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the rainfall confluence path prediction method as described in any one of claims 1 to 7.

Images