Lightning position prediction method and device and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to a lightning position prediction method and device and a storage medium. Comprising the following steps: determining a target area, and dividing the target area into a plurality of grids; counting a statistical result of lightning events occurring in each grid in a preset time window according to a statistical period; in each statistical period, performing position aggregation processing on the plurality of grids according to a statistical result to obtain a lightning density map corresponding to the target area in each statistical period; performing time clustering processing on the lightning clusters in each lightning density map based on a time sequence relationship of the statistical period, and determining a moving path of each lightning cluster on a time sequence of the statistical period; and predicting the position of each lightning cluster at the future moment based on the moving path of each lightning cluster on the statistical period time sequence. According to the embodiment of the invention, the accuracy of predicting the lightning position can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a lightning location prediction method, device and storage medium. Background Art

[0002] Lightning is a strong electrical discharge that occurs randomly in the atmosphere. It is highly destructive and can cause forest fires, power line failures, etc., thus posing a serious threat to nature and human society. Therefore, studying the characteristics of lightning and conducting effective prediction and early warning are important tasks in disaster prevention and mitigation.

[0003] At present, the prediction of lightning location usually uses radar to collect real-time data, and then conducts machine learning based on the collected data to predict the future lightning location. However, since radar echoes usually reflect the process of the storm, they cannot accurately reflect lightning. Therefore, the current lightning location prediction method has a low accuracy rate in predicting lightning location. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a lightning location prediction method, device and storage medium, which can improve the accuracy of predicting the lightning location.

[0005] In a first aspect, the present application provides a method for predicting the location of lightning, comprising: determining a target area and dividing the target area into multiple grids; obtaining statistical results of lightning events occurring in each grid within a preset time window according to a statistical period; performing position aggregation processing on multiple grids according to the statistical results in each statistical period to obtain a lightning density map corresponding to the target area in each statistical period; one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred; based on the time series relationship of the statistical period, performing time clustering processing on the lightning clusters in each lightning density map to determine the moving path of each lightning cluster in the statistical period time series; based on the moving path of each lightning cluster in the statistical period time series, predicting the position of each lightning cluster at a future moment.

[0006] In some embodiments, the statistical results include the occurrence of lightning events in the grid and the absence of lightning events in the grid; in each statistical period, multiple grids are positionally aggregated according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period, including: for the target area corresponding to any statistical period, a target grid is determined in the target area, and the following first aggregation operation is performed on the target grid until all target grids have been subjected to the first aggregation operation to obtain a lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the first aggregation operation includes: taking the target grid as a centroid grid, aggregating neighbor grids for the centroid grid based on the eight-neighborhood method, and taking the neighbor grid as a new centroid grid, continuing to aggregate neighbor grids for the centroid grid based on the eight-neighborhood method until all centroid grids do not have neighbor grids, and determining a grid group consisting of the centroid grid and the neighbor grid as a lightning cluster in the lightning density map; the neighbor grid is a grid for which the statistical result is that a lightning event occurs in the grid.

[0007] In some embodiments, the statistical results include lightning events occurring in the grid and lightning events not occurring in the grid; in each statistical period, multiple grids are subjected to position aggregation processing according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period, including: for the target area corresponding to any statistical period, a target grid is determined in the target area, and the following second aggregation operation is performed on the target grid until all target grids have been subjected to the second aggregation operation, so as to obtain an initial lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the second aggregation operation includes: The target grid is taken as the centroid grid, and the neighborhood grids are aggregated for the centroid grid based on the eight-neighborhood method. The neighborhood grid is taken as the new centroid grid, and the neighborhood grids are continuously aggregated for the centroid grid based on the eight-neighborhood method until all the centroid grids have no neighbor grids. The grid group composed of the centroid grid and the neighborhood grid is determined as an initial lightning cluster in the lightning density map; the neighborhood grid is the grid in which the lightning event occurs as a statistical result; the similarity of any two initial lightning clusters in the initial lightning density map is determined, and the initial lightning clusters with similarity greater than the similarity threshold are merged into an ultimate lightning cluster, so as to obtain the lightning density map corresponding to the target area within the statistical period.

[0008] In some embodiments, determining the similarity between any two initial lightning clusters in the initial lightning density map includes: determining the shortest distance between a grid in a first initial lightning cluster and a grid in a second initial lightning cluster, and determining the reciprocal of the shortest distance as the similarity between the two initial lightning clusters; the first initial lightning cluster and the second initial lightning cluster are different initial lightning clusters in the two initial lightning clusters.

[0009] In some embodiments, based on the time series relationship of the statistical period, time clustering processing is performed on the lightning clusters in each lightning density map to determine the moving path of each lightning cluster in the statistical period time series, including: taking the time series relationship of the statistical period as a guide, for two lightning density maps in any adjacent time series statistical period, the following third aggregation operation is performed to determine the moving path of the lightning cluster in the lightning density map in the adjacent time series statistical period; the third aggregation operation includes: determining the distance between each lightning cluster in the two lightning density maps corresponding to the adjacent time series statistical period; determining two lightning clusters with a distance less than a distance threshold as the same lightning cluster, and determining the position of the lightning cluster that is earlier in the time series as the first position of the lightning cluster, and determining the position of the lightning cluster that is later in the time series as the second position of the lightning cluster; determining the moving path of the lightning cluster in the adjacent time series statistical period as moving from the first position to the second position; determining the moving path of each lightning cluster in the statistical period time series based on the time series relationship of the statistical period and the moving path of the lightning cluster in the lightning density map in all adjacent time series statistical periods.

[0010] In some embodiments, the moving path includes the position of the lightning cluster in the lightning density map corresponding to each statistical period; based on the moving path of each lightning cluster in the statistical period time series, predicting the position of each lightning cluster at a future moment, including: for each lightning cluster, determining the moving speed of the lightning cluster in the target statistical period set corresponding to the target time window; the target statistical period set is the statistical period set closest to the target time window in time series, and the target time window includes multiple future moments; inputting the moving speed of the lightning cluster in the target statistical period set into a preset speed prediction model to predict the speed of the lightning cluster in the target time window; based on the position of the lightning cluster in the target statistical period set, and the speed of the lightning cluster in the target time window, determining the position of the lightning cluster corresponding to the target time window.

[0011] In some embodiments, before the moving speed of the lightning clusters in the target statistical period set is input into a preset speed prediction model, the prediction method also includes: determining the moving speed of each lightning cluster between adjacent statistical periods based on the position of the lightning cluster in the lightning density map corresponding to each statistical period; based on the time series relationship of the statistical periods, taking the moving speed of the lightning clusters in the first statistical period set as input and the moving speed of the lightning clusters in the second statistical period set as input, constructing and training to generate a preset speed prediction model; the time series of the statistical periods in the first statistical period set are all arranged before the statistical periods in the second statistical period set in the time series relationship; the first statistical period set includes at least three statistical periods with adjacent time series, and the second statistical period set includes at least two statistical periods with adjacent time series.

[0012] In some embodiments, the location of the lightning cluster includes the boundary grid location; after predicting the location of each lightning cluster at a future time, the prediction method further includes: collecting the actual boundary grid location of each lightning cluster at a future time; based on the predicted boundary grid location and the actual boundary grid location of each lightning cluster, counting the number of hits of the lightning cluster in the prediction result; when the predicted boundary grid location of the lightning cluster overlaps with the actual boundary grid location, determining that the lightning cluster in the prediction result has hit; or, when the ratio of the predicted boundary grid area of ​​the lightning cluster to the actual boundary grid area is greater than a ratio threshold, determining that the lightning cluster in the prediction result has hit; determining the accuracy of the speed prediction model based on the number of hits and the total number of lightning clusters in the prediction result; and optimizing the speed prediction model based on the accuracy.

[0013] In a second aspect, the present application provides a lightning position prediction device, comprising: a determination module, for determining a target area and dividing the target area into multiple grids; a statistical module, for counting the statistical results of lightning events occurring in each grid within a preset time window according to a statistical period; a position processing module, for performing position aggregation processing on multiple grids according to the statistical results within each statistical period, and obtaining a lightning density map corresponding to the target area within each statistical period; one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and one lightning cluster includes at least one grid where a lightning event has occurred; a time processing module, for performing time clustering processing on the lightning clusters in each lightning density map based on the time series relationship of the statistical period, and determining the moving path of each lightning cluster in the statistical period time series; a prediction module, for predicting the position of each lightning cluster at a future moment based on the moving path of each lightning cluster in the statistical period time series.

[0014] In some embodiments, the statistical results include the occurrence of lightning events in the grid and the absence of lightning events in the grid; the position processing module is specifically used to determine the target grid in the target area corresponding to any statistical period, and perform the following first aggregation operation on the target grid until all target grids have been subjected to the first aggregation operation, and obtain a lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the first aggregation operation includes: taking the target grid as the centroid grid, aggregating neighbor grids for the centroid grid based on the eight-neighborhood method, and taking the neighbor grid as the new centroid grid, continuing to aggregate neighbor grids for the centroid grid based on the eight-neighborhood method until all centroid grids do not have neighbor grids, and determining the grid group composed of the centroid grid and the neighbor grid as a lightning cluster in the lightning density map; the neighbor grid is a grid whose statistical result is the occurrence of lightning events in the grid.

[0015] In some embodiments, the statistical results include the occurrence of lightning events in the grid and the absence of lightning events in the grid; the position processing module includes an aggregation submodule and a merging submodule; the aggregation submodule is used to determine the target grid in the target area corresponding to any statistical period, and perform the following second aggregation operation on the target grid until all target grids have been subjected to the second aggregation operation, thereby obtaining an initial lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the second aggregation operation includes: taking the target grid as the centroid grid, based on the eight-neighbor The domain method aggregates the neighborhood grid for the centroid grid, and takes the neighborhood grid as the new centroid grid. The neighborhood grid is continuously aggregated for the centroid grid based on the eight-neighborhood method until all centroid grids have no neighbor grids. The grid group composed of the centroid grid and the neighborhood grid is determined as an initial lightning cluster in the lightning density map; the neighborhood grid is the grid in which the lightning event occurs as a statistical result; the merging submodule is used to determine the similarity of any two initial lightning clusters in the initial lightning density map, and merge the initial lightning clusters with similarity greater than the similarity threshold into an ultimate lightning cluster to obtain the lightning density map corresponding to the target area within the statistical period.

[0016] In some embodiments, the merging submodule is specifically used to determine the shortest distance between the grid in the first initial lightning cluster and the grid in the second initial lightning cluster, and determine the reciprocal of the shortest distance as the similarity between the two initial lightning clusters; the first initial lightning cluster and the second initial lightning cluster are different initial lightning clusters in the two initial lightning clusters.

[0017] In some embodiments, the time processing module is specifically used to: take the time series relationship of the statistical period as a guide, for two lightning density maps in any adjacent time series statistical period, perform the following third aggregation operation to determine the moving path of the lightning cluster in the lightning density map in the adjacent time series statistical period; the third aggregation operation includes: determining the distance between each lightning cluster in the two lightning density maps corresponding to the adjacent time series statistical period; determining two lightning clusters with a distance less than a distance threshold as the same lightning cluster, and determining the position of the lightning cluster that is earlier in the time series as the first position of the lightning cluster, and determining the position of the lightning cluster that is later in the time series as the second position of the lightning cluster; determining the moving path of the lightning cluster in the adjacent time series statistical period as moving from the first position to the second position; based on the time series relationship of the statistical period and the moving path of the lightning cluster in the lightning density map in all adjacent time series statistical periods, determine the moving path of each lightning cluster in the statistical period time series.

[0018] In some embodiments, the moving path includes the position of the lightning cluster in the lightning density map corresponding to each statistical period; the prediction module includes a construction submodule, a determination submodule, and a prediction submodule; the determination submodule is used to determine, for each lightning cluster, the moving speed of the lightning cluster in the target statistical period set corresponding to the target time window; the target statistical period set is the statistical period set closest to the target time window in time sequence, and the target time window includes multiple future moments; the prediction submodule is used to input the moving speed of the lightning cluster in the target statistical period set into a preset speed prediction model to predict the speed of the lightning cluster in the target time window; the determination submodule is also used to determine the position of the lightning cluster corresponding to the target time window based on the position of the lightning cluster in the target statistical period set and the speed of the lightning cluster in the target time window.

[0019] In some embodiments, the lightning position prediction device also includes a construction module; a determination module, which is also used to determine the movement speed of each lightning cluster between adjacent statistical periods based on the position of the lightning cluster in the lightning density map corresponding to each statistical period; a construction module, which is used to construct and train a preset speed prediction model based on the time series relationship of the statistical periods, taking the movement speed of the lightning clusters in the first statistical period set as input and the movement speed of the lightning clusters in the second statistical period set as input; the time series of the statistical periods in the first statistical period set are all arranged before the statistical periods in the second statistical period set in the time series relationship; the first statistical period set includes at least three statistical periods with adjacent time series, and the second statistical period set includes at least two statistical periods with adjacent time series.

[0020] In some embodiments, the location of the lightning cluster includes the boundary grid location; the lightning location prediction device also includes an acquisition module; the acquisition module is used to collect the actual boundary grid location of each lightning cluster at a future moment after predicting the location of each lightning cluster at a future moment; the statistical module is also used to count the number of hits of the lightning cluster in the prediction result based on the predicted boundary grid location and the actual boundary grid location of each lightning cluster; when the predicted boundary grid location of the lightning cluster coincides with the actual boundary grid location, it is determined that the lightning cluster in the prediction result has hit; or when the ratio of the predicted boundary grid area of ​​the lightning cluster to the actual boundary grid area is greater than a ratio threshold, it is determined that the lightning cluster in the prediction result has hit; the determination module is also used to determine the accuracy of the speed prediction model based on the number of hits and the total number of lightning clusters in the prediction result; the construction module is also used to optimize the speed prediction model based on the accuracy.

[0021] In a third aspect, the present application provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, a method for predicting a lightning location as in any embodiment of the first aspect is implemented.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, comprising: a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, a method for predicting a lightning position as in any embodiment of the first aspect is implemented.

[0023] In a fifth aspect, the present application provides a computer program product, comprising: when the computer program product is run on a computer, the computer is enabled to implement a method for predicting a lightning position as in any embodiment of the first aspect.

[0024] Compared with the prior art, the technical solution provided by the present application has the following advantages: First, the target area is determined and divided into multiple grids. After that, the statistical results of the occurrence of lightning events in each grid within the preset time window are counted according to the statistical period, and within each statistical period, the multiple grids are positionally aggregated according to the statistical results to obtain a lightning density map corresponding to the target area within each statistical period. Among them, one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred. Finally, based on the time series relationship of the statistical period, the lightning clusters in each lightning density map are time clustered to determine the moving path of each lightning cluster in the statistical period time series, and based on the moving path of each lightning cluster in the statistical period time series, the position of each lightning cluster at a future moment is predicted. In this way, on the one hand, the position of each lightning cluster in the future can be predicted based on the statistical results of lightning events occurring in each grid within the preset time window, avoiding the use of data collected by radar to predict the lightning position, thereby improving the accuracy of predicting the lightning position; on the other hand, the grids can be aggregated horizontally in the position dimension first to determine the lightning clusters, and then the lightning clusters can be aggregated vertically in the time dimension to determine the various positions of the lightning clusters in the time dimension, and then the positions of the lightning clusters in the future can be predicted based on these positions. In the process of predicting the lightning position, the temporal and spatial laws of lightning are effectively combined, further improving the accuracy of predicting the lightning position. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0027] Figure 1 One of the flow charts of the method for predicting lightning positions provided in the embodiment of the present application;

[0028] Figure 2 One of the schematic diagrams of the lightning density map provided in the embodiment of the present application;

[0029] Figure 3 A second schematic diagram of a lightning density map provided in an embodiment of the present application;

[0030] Figure 4 The third schematic diagram of the lightning density map provided in the embodiment of the present application;

[0031] Figure 5 A second flow chart of a method for predicting lightning locations provided in an embodiment of the present application;

[0032] Figure 6 A fourth schematic diagram of a lightning density map provided in an embodiment of the present application;

[0033] Figure 7 A third flowchart of a method for predicting lightning locations provided in an embodiment of the present application;

[0034] Figure 8 A fourth flowchart of a method for predicting lightning locations provided in an embodiment of the present application;

[0035] Fig. 9 A fifth flowchart of a method for predicting lightning locations provided in an embodiment of the present application;

[0036] Fig.10 Flow chart of the lightning location prediction method provided in the embodiment of the present application.

[0037] Fig.11 Schematic diagram of the seventh flow chart of the method for predicting lightning positions provided in the embodiment of the present application;

[0038] Fig.12 A schematic diagram of the structure of a lightning location prediction device provided in an embodiment of the present application;

[0039] Fig.13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] Thunderstorm activities pose a major threat to the safe operation of power systems, and more than 60% of transmission line failures are caused by lightning strikes. Lightning is one of the direct manifestations of thunderstorm activities. According to its discharge type, lightning is mainly divided into cloud-to-ground lightning and cloud-to-ground lightning (also known as ground lightning). Accurately predicting the location of lightning can help provide real-time lightning path monitoring and early warning services for power systems, promote differentiated protection strategies for transmission lines based on lightning early warning technology, and reduce economic losses caused by lightning strikes. At present, lightning protection planning for power systems mainly relies on lightning density and daily distribution of lightning. However, these traditional indicators fail to fully reflect the spatiotemporal evolution characteristics of individual thunderstorm activities.

[0043] In addition, the current prediction of lightning locations usually uses radar to collect real-time data, and then performs machine learning based on the collected data to predict future lightning locations. However, since radar echoes usually reflect the process of the storm, they cannot accurately reflect lightning. Therefore, the current lightning location prediction method has a low accuracy rate in predicting lightning locations.

[0044] In response to the above problems, the embodiments of the present application provide a method, device and storage medium for predicting the location of lightning. The method includes: first, determining a target area and dividing the target area into multiple grids. Afterwards, statistical results of lightning events occurring in each grid within a preset time window are counted according to the statistical period, and within each statistical period, multiple grids are subjected to position aggregation processing according to the statistical results to obtain a lightning density map corresponding to the target area within each statistical period. Among them, one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and one lightning cluster includes at least one grid where a lightning event has occurred. Finally, based on the time series relationship of the statistical period, the lightning clusters in each lightning density map are subjected to time clustering processing to determine the moving path of each lightning cluster in the statistical period time series, and based on the moving path of each lightning cluster in the statistical period time series, the position of each lightning cluster at a future moment is predicted. In this way, on the one hand, the position of each lightning cluster at a future moment can be predicted based on the statistical results of lightning events occurring in each grid within a preset time window, thereby avoiding the problem of signal attenuation or distortion within the detection range caused by terrain or building obstruction when using radar collected data to predict the lightning position, thereby improving the accuracy of predicting the lightning position; on the other hand, the grids can be aggregated horizontally in the position dimension first to determine the lightning clusters, and then the lightning clusters can be aggregated vertically in the time dimension to determine the various positions of the lightning clusters in the time dimension, and then the positions of the lightning clusters in the future can be predicted based on these positions. In the process of predicting the lightning position, the temporal and spatial laws of lightning are effectively combined, thereby further improving the accuracy of predicting the lightning position.

[0045] The method for predicting the lightning position provided in the embodiment of the present application is mainly applicable to the scenario of predicting the lightning position at a future moment when the lightning speed at a historical moment is known. The method for predicting the lightning position provided in the embodiment of the present application can be executed by a prediction device for the lightning position, and the prediction device for the lightning position can be hardware or software. When the prediction device for the lightning position is hardware, it can be various electronic devices with a function of running the prediction of the lightning position, including but not limited to computers, computers, tablet computers, etc. When the prediction device for the lightning position is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules, or it can be implemented as a single software or software module. It is not specifically limited here.

[0046] Figure 1 A flowchart of a method for predicting lightning locations provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method for predicting lightning positions may include the following steps.

[0047] S11. Determine a target area and divide the target area into multiple grids.

[0048] First, determine the target area. Specifically, when lightning occurs, the area within a preset distance around the area where the lightning occurs is determined as the target area. The value of the preset distance is preset, for example, a default value, or a value set by relevant personnel according to actual conditions.

[0049] Secondly, the target area is divided into multiple grids. Specifically, the target area can be divided into multiple grids according to the longitude and latitude of the target area. For example, the size of the grid is set to a grid with longitude and latitude of 0.01°, that is, the grid size is 0.01°×0.01°; the target area can also be divided into multiple grids according to a preset size, such as a square with a size of 1×1 kilometer (km), a triangle with a height of 1km, a regular hexagon with a side of 1km, etc.

[0050] S12. Counting the statistical results of lightning events occurring in each grid within a preset time window according to the statistical period.

[0051] The duration of the statistical period and the preset time window are both preset, for example, default values, or values ​​set by relevant personnel according to actual conditions. For another example, the statistical period is 6 minutes (min) and the preset time window is 30 minutes. The statistical results include lightning events that occur in the grid and lightning events that do not occur in the grid.

[0052] Specifically, the statistical result of the lightning event occurring in each grid within the preset time window according to the statistical period can be counted by using a dedicated acquisition device according to the statistical period. For example, the acquisition device can be a short-baseline Very Low Frequency (VLF) / Low Frequency (LF) three-dimensional lightning detection network (VLF / LF Lightning Detection Network), a VHF interferometer lightning detection system, etc.

[0053] S13. In each statistical period, position aggregation processing is performed on multiple grids according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period.

[0054] Among them, one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred.

[0055] Specifically, for a certain statistical period, the adjacent grids with lightning events in the grid can be aggregated into the same lightning cluster to obtain a lightning density map corresponding to the target area in the statistical period. Figure 2 is the statistical result of lightning events in each grid in the target area within a statistical period. Figure 2 As shown, grids 1-19 are grids where lightning events occurred during the statistical period, and the remaining grids are grids where no lightning events occurred during the statistical period. It can be seen that if the grids in grids 1-12 are adjacent to each other, then grids 1-12 can be aggregated into the same lightning cluster; similarly, if the grids in grids 13-19 are adjacent to each other, then grids 13-19 can be aggregated into the same lightning cluster.

[0056] In some embodiments, in each statistical period, multiple grids are subjected to position aggregation processing according to statistical results to obtain a lightning density map corresponding to the target area in each statistical period, which may be: for the target area corresponding to any statistical period, a target grid is determined in the target area, and the following first aggregation operation is performed on the target grid until all target grids have been subjected to the first aggregation operation to obtain a lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation. The first aggregation operation includes: taking the target grid as the centroid grid, aggregating neighbor grids for the centroid grid based on the eight-neighborhood method, taking the neighbor grid as the new centroid grid, and continuing to aggregate neighbor grids for the centroid grid based on the eight-neighborhood method until all centroid grids have no neighbor grids, and determining the grid group composed of the centroid grid and the neighbor grid as a lightning cluster in the lightning density map. Among them, the neighborhood grid is the grid in which the statistical result is a lightning event. The eight-neighborhood method aggregates the neighborhood grid by searching the eight adjacent grids (i.e., the top, bottom, left, right, and four diagonal directions) of the centroid grid to see if there is a neighborhood grid. If so, aggregate the centroid grid and the neighborhood grid. If not, stop searching and get a lightning cluster.

[0057] In the above scheme, on the one hand, the grid can be aggregated horizontally in the position dimension to identify lightning clusters in the target area, so as to provide data support for the subsequent prediction of the location of lightning clusters, avoiding the problem of signal attenuation or distortion within the detection range due to the influence of terrain or building shielding when using radar collected data to predict the location of lightning, thereby improving the accuracy of predicting the location of lightning. On the other hand, the grid can also be aggregated in combination with the eight-neighborhood method, effectively aggregating discrete grid units into continuous lightning clusters, which can better capture the overall distribution and local characteristics of spatial data, reduce the influence of noise and isolated points, and further indirectly improve the accuracy of predicting the location of lightning.

[0058] S14. Based on the time series relationship of the statistical period, time clustering processing is performed on the lightning clusters in each lightning density map to determine the moving path of each lightning cluster in the statistical period time series.

[0059] Specifically, based on the time series relationship of the statistical periods, the distance between each lightning cluster in the previous statistical period and each lightning cluster in the next statistical period of the target area is calculated, and two lightning clusters with a close distance (such as less than a distance threshold) are determined to be the same lightning cluster, thereby obtaining the moving path of the lightning cluster from the previous statistical period to the next statistical period.

[0060] For example, Figure 3 The lightning density graph corresponding to two adjacent statistical periods provided in the embodiment of the present application is as follows: Figure 3 As shown, it includes a lightning density map of a first statistical period and a lightning density map of a second statistical period, the first statistical period includes a first lightning cluster 31 and a second lightning cluster 32, and the second statistical period includes a third lightning cluster 33 and a fourth lightning cluster 34. Then, the distance between the first lightning cluster 31 and the third lightning cluster 33 and the fourth lightning cluster 34, and the distance between the second lightning cluster 32 and the third lightning cluster 33 and the fourth lightning cluster 34 are calculated respectively; the third lightning cluster 33 and the fourth lightning cluster 34 and the lightning cluster closest to the first lightning cluster 31 are determined to be the same lightning cluster as the first lightning cluster 31; the third lightning cluster 33 and the fourth lightning cluster 34 and the lightning cluster closest to the second lightning cluster 32 are determined to be the same lightning cluster as the second lightning cluster 32.

[0061] For another example, when the distance between the first lightning cluster 31 and the third lightning cluster 33 is a, and the distance between the first lightning cluster 31 and the fourth lightning cluster 34 is b, and a is less than b, and a is less than a preset threshold, the third lightning cluster 33 and the first lightning cluster 31 are determined to be the same lightning cluster, such as Figure 4 As shown, it can be obtained that the first lightning cluster 31 moves from the first position 401 in the first statistical period to the second position 402 in the second statistical period in the second statistical period; similarly, when the distance between the second lightning cluster 32 and the third lightning cluster 33 is c, and the distance between the second lightning cluster 32 and the fourth lightning cluster 34 is d, and c is greater than b, and c is less than a preset threshold, the fourth lightning cluster 34 and the second lightning cluster 32 are determined to be the same lightning cluster, such as Figure 4 As shown, it can be obtained that the second lightning cluster 32 moves from the third position 411 in the first statistical period to the fourth position 412 in the second statistical period during the second statistical period.

[0062] Based on the above method, the lightning clusters in each lightning density map are subjected to time clustering processing to obtain the moving path of each lightning cluster in all statistical periods.

[0063] S15. Predicting the position of each lightning cluster at a future moment based on the moving path of each lightning cluster in the statistical period time series.

[0064] Specifically, based on the moving paths of each lightning cluster in the statistical period time series, the method for predicting the positions of each lightning cluster in the future can be inputting the moving paths of each lightning cluster in the statistical period time series into a pre-trained position prediction model to obtain the positions of each lightning cluster in the future; or it can be calculating the moving speed of each lightning cluster based on the moving paths of each lightning cluster in the statistical period time series and the statistical period, predicting the moving speed in the future based on the historical moving speed, and then calculating the position of the lightning cluster in the future based on the moving speed in the future and the position of the current lightning cluster.

[0065] In the above scheme, first, the target area is determined and divided into multiple grids. After that, the statistical results of the occurrence of lightning events in each grid within the preset time window are counted according to the statistical period, and in each statistical period, the multiple grids are subjected to position aggregation processing according to the statistical results to obtain the lightning density map corresponding to the target area in each statistical period. Among them, one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred. Finally, based on the time series relationship of the statistical period, the lightning clusters in each lightning density map are subjected to time clustering processing, the moving path of each lightning cluster in the statistical period time series is determined, and the position of each lightning cluster in the future is predicted based on the moving path of each lightning cluster in the statistical period time series. In this way, on the one hand, the position of each lightning cluster in the future can be predicted based on the statistical results of the occurrence of lightning events in each grid within the preset time window, avoiding the use of radar collected data to predict the lightning position, and improving the accuracy of predicting the lightning position. On the other hand, the grid can be aggregated horizontally in the position dimension to determine the lightning cluster, and then the lightning cluster can be aggregated vertically in the time dimension to determine the various positions of the lightning cluster in the time dimension, and then the position of the lightning cluster in the future is predicted based on these positions. In the process of predicting the lightning position, the time law and space law of lightning are effectively combined, and the accuracy of predicting the lightning position is further improved. On the other hand, the time resolution and space resolution can be unified to predict the lightning position, that is, the embodiment of the present application provides a high-precision, high-temporal and high-space resolution lightning position prediction method, which provides an important reference for the subsequent monitoring and early warning of severe convective weather.

[0066] In some embodiments, the statistical results include the occurrence of lightning events in the grid and the absence of lightning events in the grid. Figure 5 As shown, in each statistical period, multiple grids are subjected to position aggregation processing according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period, including the following steps:

[0067] S131. For a target area corresponding to any statistical period, a target grid is determined in the target area, and the following second aggregation operation is performed on the target grid until the second aggregation operation is performed on all target grids, thereby obtaining an initial lightning density map corresponding to the target area in the statistical period.

[0068] The target grid is a grid in the target area that has not been subjected to aggregation operations. The second aggregation operation includes: taking the target grid as the centroid grid, aggregating the neighborhood grids for the centroid grid based on the eight-neighborhood method, and taking the neighborhood grid as the new centroid grid, and continuing to aggregate the neighborhood grids for the centroid grid based on the eight-neighborhood method until all centroid grids have no neighbor grids, and determining the grid group composed of the centroid grid and the neighborhood grid as an initial lightning cluster in the lightning density map; the neighborhood grid is a grid in which the statistical result is that a lightning event occurs in the grid.

[0069] S132. Determine the similarity between any two initial lightning clusters in the initial lightning density map, and merge the initial lightning clusters whose similarity is greater than a similarity threshold into an ultimate lightning cluster, to obtain a lightning density map corresponding to the target area within the statistical period.

[0070] The similarity threshold is preset, for example, a default value, or a value set by relevant personnel according to actual conditions. For example, the similarity threshold is the reciprocal of the distance between the two grids.

[0071] In some embodiments, a method for determining the similarity of any two initial lightning clusters in an initial lightning density map may be: determining the shortest distance between a grid in a first initial lightning cluster and a grid in a second initial lightning cluster, and determining the reciprocal of the shortest distance as the similarity between the two initial lightning clusters; the first initial lightning cluster and the second initial lightning cluster are different initial lightning clusters among the two initial lightning clusters.

[0072] For example, Figure 6 The initial lightning density map within a statistical period provided by the embodiment of the present application. Figure 6The fifth lightning cluster 61, the sixth lightning cluster 62, and the seventh lightning cluster 63 are included. The similarity between the fifth lightning cluster 61 and the sixth lightning cluster 62 can be determined by calculating the reciprocal of the distance between the grids in the fifth lightning cluster 61 and the sixth lightning cluster 62. Similarly, the similarity between the fifth lightning cluster 61 and the seventh lightning cluster 63, and the similarity between the sixth lightning cluster 62 and the seventh lightning cluster 63 can also be calculated in sequence according to the above method. Afterwards, if the reciprocal of the distance between the grids in the fifth lightning cluster 61 and the sixth lightning cluster 62 is greater than the similarity threshold, the fifth lightning cluster 61 and the sixth lightning cluster 62 are merged into one ultimate lightning cluster, otherwise they will not be merged. Similarly, the fifth lightning cluster 61 and the seventh lightning cluster 63, and the sixth lightning cluster 62 and the seventh lightning cluster 63 are also merged according to the similarity to obtain the lightning density map within the statistical period.

[0073] In the above scheme, on the basis of aggregating the grids by the eight-neighborhood method, the initial lightning clusters are aggregated again by calculating the similarities between the initial lightning clusters, and the initial lightning clusters are aggregated into larger lightning clusters, thereby avoiding the problem that the lightning clusters determined only by the eight-neighborhood method may be many dense but discrete points. While ensuring the accuracy of aggregation, the subsequent amount of calculations is greatly reduced, saving computing resources.

[0074] In some embodiments, Figure 7 As shown, based on the time series relationship of the statistical period, the lightning clusters in each lightning density map are subjected to time clustering processing to determine the moving path of each lightning cluster in the statistical period time series, which may include the following steps:

[0075] S141. With the time series relationship of the statistical periods as a guide, for two lightning density maps in any adjacent time series statistical periods, perform the following third aggregation operation to determine the moving path of the lightning clusters in the lightning density maps in the adjacent time series statistical periods.

[0076] Among them, Figure 8 As shown, the third polymerization operation includes the following steps:

[0077] S1411. Determine the distance between each lightning cluster in two lightning density maps corresponding to adjacent time series statistical periods.

[0078] Specifically, the distance between each lightning cluster in two lightning density maps corresponding to adjacent time series statistical periods can be determined by determining the distance between the lightning clusters in adjacent time series statistical periods according to the number of grids between the same lightning cluster in two lightning density maps corresponding to adjacent time series statistical periods and the size of the grids. Figure 4In the scene shown, the second lightning cluster 32 moves from the third position 411 in the first statistical period to the fourth position 412 in the second statistical period. It can be seen that the number of grids between the third position 411 and the fourth position 412 is 5, and the distance between the third position 411 and the fourth position is 5×n, where n is the size of the grid.

[0079] S1412, determining two lightning clusters whose distance is less than a distance threshold as the same lightning cluster, determining the position of the lightning cluster that is earlier in time sequence as the first position of the lightning cluster, and determining the position of the lightning cluster that is later in time sequence as the second position of the lightning cluster.

[0080] The preset threshold is a preset value, for example, a default value, or a value determined by relevant personnel according to actual conditions. For example, the preset threshold is 10 km.

[0081] For example, in Figure 3 In the scenario shown, the position of the first lightning cluster 31 that is earlier in time within the first statistical period is determined as the first position of the lightning cluster, and the position of the third lightning cluster 33 that is later in time within the second statistical period is determined as the second position of the lightning cluster; similarly, the position of the second lightning cluster 32 that is earlier in time within the first statistical period is determined as the first position of the lightning cluster, and the position of the fourth lightning cluster 34 that is later in time within the second statistical period is determined as the second position of the lightning cluster.

[0082] S1413: Determine that the moving path of the lightning cluster in the adjacent time series statistical period is from the first position to the second position.

[0083] S142. Determine the moving path of each lightning cluster in the statistical period time series based on the time series relationship of the statistical period and the moving paths of the lightning clusters in the lightning density graph in all adjacent time series statistical periods.

[0084] Specifically, based on the above method, the third aggregation operation is performed on the lightning clusters in each lightning density map to obtain the moving path of each lightning cluster in all statistical periods.

[0085] In the above scheme, lightning clusters can be aggregated vertically in the time dimension to determine the various positions of lightning clusters in the time dimension, so as to provide data support for the subsequent prediction of the position of lightning clusters. This avoids the problem of signal attenuation or distortion within the detection range caused by terrain or building obstruction when using data collected by radar to predict the position of lightning, thereby improving the accuracy of predicting the position of lightning.

[0086] In some embodiments, the moving path includes the position of the lightning cluster in the lightning density map corresponding to each statistical period. Fig. 9As shown, based on the moving paths of each lightning cluster in the statistical period time series, the method of predicting the position of each lightning cluster at a future moment includes the following steps:

[0087] S151. For each lightning cluster, determine the moving speed of the lightning cluster within the target statistical period set corresponding to the target time window.

[0088] The target statistical period set is a statistical period set that is closest to the target time window in terms of time sequence. The target time window includes multiple future moments, and the duration of the target time window is the same as the duration of the statistical period.

[0089] The target statistical period set includes multiple statistical periods that are continuous in time series. The movement speed of a lightning cluster between each two statistical periods that are adjacent in time series may be different. Therefore, when determining the movement speed of a lightning cluster in the target statistical period set corresponding to the target time window, it is necessary to determine the movement speed of the lightning cluster between each two statistical periods that are adjacent in time series in the target statistical period set.

[0090] Specifically, the method of determining the moving speed of the lightning cluster between each two statistical periods on adjacent time series in the target statistical period set can be to determine the moving distance of the lightning cluster between the statistical periods on the two adjacent time series according to the number of grids and the size of the grids passed by the moving path of the lightning cluster in the statistical periods on the two adjacent time series. Then, the moving speed of the lightning cluster between the statistical periods on the two adjacent time series is determined according to the moving distance and the duration between the two statistical periods (that is, the duration of one statistical period).

[0091] In some embodiments, the moving speed of a lightning cluster between statistical periods in two adjacent time series may be calculated according to the following formula.

[0092]

[0093] in, It is used to indicate the moving speed of lightning cluster i between the statistical cycles of two adjacent time series. Δt is used to indicate the duration between two statistical cycles, that is, the duration of a statistical cycle. i Used to indicate the longitude of the lightning cluster in the statistical period with the later time series in two adjacent statistical periods, prev_lon i It is used to indicate the longitude of the lightning cluster in the statistical period earlier in the two adjacent statistical periods. i Used to indicate the latitude of the lightning cluster in the statistical period with the later time series in two adjacent statistical periods, prev_lat i Used to indicate the latitude of a lightning cluster in the earlier statistical period of two adjacent time series statistical periods.

[0094] S152, inputting the moving speed of the lightning cluster within the target statistical period set into a preset speed prediction model to predict the speed of the lightning cluster in the target time window.

[0095] Among them, the speed prediction model is trained according to the moving speed of lightning clusters in a set of historical statistical periods.

[0096] S153. Determine the position of the lightning cluster corresponding to the target time window based on the position of the lightning cluster within the target statistical period set and the speed of the lightning cluster in the target time window.

[0097] Specifically, the position of the lightning cluster corresponding to the target time window can be calculated according to the following formula.

[0098]

[0099] in, It is used to indicate the position of lightning cluster i in the target time window. It is used to represent the speed of lightning cluster i in the target time window, and Δt is used for the duration of the target time window, that is, the duration of a statistical cycle.

[0100] In some embodiments, the location of the lightning cluster includes the location of the lightning cluster boundary grid and the location of the centroid grid.

[0101] In the above scheme, the moving speed of the lightning cluster can be determined according to the moving path of each lightning cluster in the statistical period time series and the duration of the statistical period, and the moving speed of the lightning cluster at the future moment can be predicted according to the moving speed of the lightning cluster corresponding to the historical statistical period, and then the position of the lightning cluster at the future moment can be calculated according to the moving speed of the lightning cluster at the future moment and the position of the lightning cluster corresponding to the historical statistical period. In this way, the temporal law and spatial law of lightning are effectively combined in the process of predicting the lightning position, further improving the accuracy of predicting the lightning position.

[0102] In some embodiments, before step S152, Fig.10 As shown, the lightning position prediction method also includes the following steps:

[0103] S1521. Determine the moving speed of each lightning cluster between each adjacent statistical period based on the position of the lightning cluster in the lightning density map corresponding to each statistical period.

[0104] Specifically, the method of determining the moving speed of each lightning cluster between each adjacent statistical period is the same as the method of determining the moving speed of the lightning cluster between two adjacent statistical periods in step S151, which will not be repeated here.

[0105] S1522. Based on the time series relationship of the statistical periods, the moving speed of the lightning clusters in the first statistical period set is used as input, and the moving speed of the lightning clusters in the second statistical period set is used as input to construct and train a preset speed prediction model.

[0106] The number of statistical periods in the first statistical period set is preset and greater than 2, for example, 3. The timing of the statistical periods in the first statistical period set is arranged before the statistical periods in the second statistical period set in the timing relationship; the first statistical period set includes at least three statistical periods adjacent in timing, and the second statistical period set includes at least two statistical periods adjacent in timing.

[0107] Exemplarily, when the number of statistical cycles in the first statistical cycle set is 3, the speed prediction model can be described as the following formula:

[0108]

[0109] in, It is used to represent the predicted moving speed of lightning cluster i, It is used to indicate the speed of lightning cluster i between the two statistical cycles with the later timing among the three statistical cycles. It is used to represent the speed of lightning cluster i between the two statistical periods with the earliest timing among the three statistical periods. k is a hyperparameter of the speed prediction model, and k<1.

[0110] In some embodiments, the loss function of the speed prediction model can be expressed as the following formula:

[0111]

[0112] Among them, N is used to represent the number of samples; It is used to indicate the actual position of the lightning cluster in the target time window. Used to represent the predicted position of the lightning cluster in the target time window; the predicted position of the lightning cluster in the target time window can be calculated according to the formula in step S153.

[0113] In the above scheme, a preset speed prediction model can be pre-trained according to the speed of the lightning cluster corresponding to the historical time period, which significantly reduces the time cost and computing cost of real-time calculation while ensuring the accuracy of the model.

[0114] In some embodiments, Fig.11 As shown, after step S153, the lightning position prediction method further includes the following steps:

[0115] S161. Collect the actual boundary grid positions of each lightning cluster at future moments.

[0116] S162: Based on the predicted boundary grid position and the actual boundary grid position of each lightning cluster, counting the number of strikes of the lightning cluster in the prediction result.

[0117] Among them, when the boundary grid position of the lightning cluster prediction coincides with the actual boundary grid position, it is determined that the lightning cluster has hit in the prediction result; or when the ratio of the boundary grid area of ​​the lightning cluster prediction to the actual boundary grid area is greater than the ratio threshold, it is determined that the lightning cluster has hit in the prediction result.

[0118] S163. Determine the accuracy of the speed prediction model according to the number of hits and the total number of lightning clusters in the prediction result.

[0119] Specifically, the accuracy of the speed prediction model can be calculated according to the formula POD = hits / (hits+false), where POD is used to represent the accuracy of the speed prediction model, hits is used to represent the number of hits of the lightning cluster in the prediction result, and false is used to represent the number of misses of the lightning cluster in the prediction result.

[0120] S164. Optimize the speed prediction model according to the accuracy.

[0121] Specifically, when the accuracy is less than the accuracy threshold, the hyperparameters in the speed prediction model are adjusted, and the location of the lightning cluster is predicted again. The accuracy threshold is preset, for example, a default value, or a value set by relevant personnel according to actual conditions.

[0122] In the above scheme, the speed prediction model can be corrected in real time according to the prediction result of the lightning position, thereby further improving the accuracy of the speed prediction model.

[0123] The embodiment of the present application can divide the lightning location prediction device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0124] like Fig.12 As shown, it is a schematic diagram of the structure of a lightning position prediction device provided in an embodiment of the present application, and the lightning position prediction device includes a determination module 51, a statistics module 52, a position processing module 53, a time processing module 54, and a prediction module 55.

[0125] The determination module 51 is used to determine the target area and divide the target area into multiple grids; the statistical module 52 is used to count the statistical results of lightning events occurring in each grid within a preset time window according to the statistical period; the position processing module 53 is used to perform position aggregation processing on multiple grids according to the statistical results in each statistical period to obtain a lightning density map corresponding to the target area in each statistical period; one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred; the time processing module 54 is used to perform time clustering processing on the lightning clusters in each lightning density map based on the time series relationship of the statistical period, and determine the moving path of each lightning cluster in the statistical period time series; the prediction module 55 is used to predict the position of each lightning cluster at a future moment based on the moving path of each lightning cluster in the statistical period time series.

[0126] In the above scheme, first, the target area is determined and divided into multiple grids. After that, the statistical results of lightning events occurring in each grid within a preset time window are counted according to the statistical period, and within each statistical period, multiple grids are subjected to position aggregation processing according to the statistical results to obtain a lightning density map corresponding to the target area within each statistical period. Among them, one statistical period corresponds to a lightning density map, a lightning density map includes multiple lightning clusters, and a lightning cluster includes at least one grid where a lightning event has occurred. Finally, based on the time series relationship of the statistical period, the lightning clusters in each lightning density map are subjected to time clustering processing to determine the moving path of each lightning cluster in the statistical period time series, and based on the moving path of each lightning cluster in the statistical period time series, the position of each lightning cluster at a future moment is predicted. In this way, on the one hand, the position of each lightning cluster in the future can be predicted based on the statistical results of lightning events occurring in each grid within the preset time window, avoiding the use of data collected by radar to predict the lightning position, thereby improving the accuracy of predicting the lightning position; on the other hand, the grids can be aggregated horizontally in the position dimension first to determine the lightning clusters, and then the lightning clusters can be aggregated vertically in the time dimension to determine the various positions of the lightning clusters in the time dimension, and then the positions of the lightning clusters in the future can be predicted based on these positions. In the process of predicting the lightning position, the temporal and spatial laws of lightning are effectively combined, further improving the accuracy of predicting the lightning position.

[0127] In some embodiments, the statistical results include the occurrence of lightning events in the grid and the absence of lightning events in the grid; the position processing module 53 is specifically used to determine the target grid in the target area corresponding to any statistical period, and perform the following first aggregation operation on the target grid until all target grids have been subjected to the first aggregation operation, and obtain a lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the first aggregation operation includes: taking the target grid as the centroid grid, aggregating neighbor grids for the centroid grid based on the eight-neighborhood method, and taking the neighbor grid as the new centroid grid, continuing to aggregate neighbor grids for the centroid grid based on the eight-neighborhood method, until all centroid grids do not have neighbor grids, and determining the grid group composed of the centroid grid and the neighbor grid as a lightning cluster in the lightning density map; the neighbor grid is a grid whose statistical result is the occurrence of lightning events in the grid.

[0128] In some embodiments, the statistical results include lightning events occurring in the grid and lightning events not occurring in the grid; Fig.12 As shown, the position processing module 53 includes an aggregation submodule and a merging submodule; the aggregation submodule is used to determine the target grid in the target area corresponding to any statistical period, and perform the following second aggregation operation on the target grid until all target grids have been subjected to the second aggregation operation, and obtain the initial lightning density map corresponding to the target area in the statistical period; the target grid is the grid in the target area that has not been subjected to the aggregation operation; wherein the second aggregation operation includes: taking the target grid as the centroid grid, aggregating the neighborhood grids for the centroid grid based on the eight-neighborhood method, and The neighborhood grid is used as the new centroid grid, and the neighborhood grids are continuously aggregated for the centroid grid based on the eight-neighborhood method until all the centroid grids have no neighbor grids, and the grid group composed of the centroid grid and the neighborhood grid is determined as an initial lightning cluster in the lightning density map; the neighborhood grid is the grid in which the statistical result is a lightning event; the merging submodule is used to determine the similarity of any two initial lightning clusters in the initial lightning density map, and merge the initial lightning clusters with similarity greater than the similarity threshold into an ultimate lightning cluster, so as to obtain the lightning density map corresponding to the target area within the statistical period.

[0129] In some embodiments, the merging submodule is specifically used to determine the shortest distance between the grid in the first initial lightning cluster and the grid in the second initial lightning cluster, and determine the reciprocal of the shortest distance as the similarity between the two initial lightning clusters; the first initial lightning cluster and the second initial lightning cluster are different initial lightning clusters in the two initial lightning clusters.

[0130] In some embodiments, the time processing module 54 is specifically used to: take the time series relationship of the statistical period as a guide, for two lightning density maps in any adjacent time series statistical period, perform the following third aggregation operation to determine the moving path of the lightning cluster in the lightning density map in the adjacent time series statistical period; the third aggregation operation includes: determining the distance between each lightning cluster in the two lightning density maps corresponding to the adjacent time series statistical period; determining two lightning clusters with a distance less than a distance threshold as the same lightning cluster, and determining the position of the lightning cluster that is earlier in the time series as the first position of the lightning cluster, and determining the position of the lightning cluster that is later in the time series as the second position of the lightning cluster; determining the moving path of the lightning cluster in the adjacent time series statistical period as moving from the first position to the second position; based on the time series relationship of the statistical period and the moving path of the lightning cluster in the lightning density map in all adjacent time series statistical periods, determine the moving path of each lightning cluster in the statistical period time series.

[0131] In some embodiments, the moving path includes the position of the lightning cluster in each statistical period corresponding to the lightning density map; Fig.12 As shown, the prediction module 55 includes a construction submodule, a determination submodule, and a prediction submodule; the determination submodule is used to determine, for each lightning cluster, the moving speed of the lightning cluster within the target statistical period set corresponding to the target time window; the target statistical period set is the statistical period set closest to the target time window in time sequence, and the target time window includes multiple future moments; the prediction submodule is used to input the moving speed of the lightning cluster within the target statistical period set into a preset speed prediction model to predict the speed of the lightning cluster in the target time window; the determination submodule is also used to determine the position of the lightning cluster corresponding to the target time window based on the position of the lightning cluster within the target statistical period set and the speed of the lightning cluster in the target time window.

[0132] In some embodiments, Fig.12 As shown, the lightning position prediction device also includes a construction module 57; the determination module 51 is also used to determine the moving speed of each lightning cluster between adjacent statistical periods based on the position of the lightning cluster in the lightning density map corresponding to each statistical period; the construction module 57 is used to construct and train a preset speed prediction model based on the time series relationship of the statistical periods, taking the moving speed of the lightning clusters in the first statistical period set as input and the moving speed of the lightning clusters in the second statistical period set as input; the time series of the statistical periods in the first statistical period set are all arranged before the statistical periods in the second statistical period set in the time series relationship; the first statistical period set includes at least three statistical periods with adjacent time series, and the second statistical period set includes at least two statistical periods with adjacent time series.

[0133] In some embodiments, the location of the lightning cluster includes a boundary grid location; Fig.12As shown, the lightning position prediction device also includes an acquisition module 56; the acquisition module 56 is used to collect the actual boundary grid position of each lightning cluster at a future moment after predicting the position of each lightning cluster at a future moment; the statistical module 52 is also used to count the number of lightning cluster hits in the prediction result based on the predicted boundary grid position and the actual boundary grid position of each lightning cluster; when the predicted boundary grid position of the lightning cluster coincides with the actual boundary grid position, it is determined that the lightning cluster in the prediction result hits; or when the ratio of the predicted boundary grid area of ​​the lightning cluster to the actual boundary grid area is greater than a ratio threshold, it is determined that the lightning cluster in the prediction result hits; the determination module 51 is also used to determine the accuracy of the speed prediction model according to the number of hits and the total number of lightning clusters in the prediction result; the construction module 57 is also used to optimize the speed prediction model according to the accuracy.

[0134] The lightning position prediction device provided in this embodiment can execute the lightning position prediction method provided in the above method embodiment. Its implementation principle and technical effect are similar to those of the above method and will not be repeated here.

[0135] Fig.13 An electronic device according to an exemplary embodiment may include a processor 802, and the processor 802 is used to execute application code to implement the lightning position prediction method in the present application.

[0136] The processor 802 may be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0137] like Fig.13 As shown, the electronic device may further include a memory 803. The memory 803 is used to store application program codes for executing the solution of the present application, and the execution is controlled by the processor 802.

[0138] The memory 803 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 803 may exist independently and be connected to the processor 802 via the bus 804. The memory 803 may also be integrated with the processor 802.

[0139] like Fig.13 As shown, the electronic device may further include a communication interface 801, wherein the communication interface 801, the processor 802, and the memory 803 may be coupled to each other, for example, via a bus 804. The communication interface 801 is used to exchange information with other devices, for example, to support information exchange between the electronic device and other devices.

[0140] It should be pointed out that Fig.13 The device structure shown in the figure does not constitute a limitation on the electronic device, except Fig.13 In addition to the components shown, the electronic device may include more or fewer components than shown, or combine certain components, or arrange the components differently. The electronic device provided in this embodiment can execute the lightning location prediction method provided in the above method embodiment, and its implementation principle and technical effects are similar to the above method, which will not be described in detail here.

[0141] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each process of the method for predicting the lightning position in the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0142] The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0143] An embodiment of the present application provides a computer program product, which stores a computer program. When the computer program is executed by a processor, each process of the method for predicting the lightning position in the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0144] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media that include computer-usable program code.

[0145] In the present application, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0146] In this application, memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0147] In this application, computer-readable media includes permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data and carrier waves.

[0148] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0149] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting lightning positions, characterized in that: include: Determine a target area, and divide the target area into a plurality of grids; Count the statistical results of lightning events occurring in each grid within a preset time window according to the statistical period; In each statistical period, position aggregation processing is performed on the multiple grids according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period; one statistical period corresponds to a lightning density map, one lightning density map includes multiple lightning clusters, and one lightning cluster includes at least one grid where a lightning event has occurred; Based on the time series relationship of the statistical period, a time clustering process is performed on the lightning clusters in each lightning density map to determine the moving path of each lightning cluster in the time series of the statistical period; Based on the moving paths of the lightning clusters in the statistical period time series, the positions of the lightning clusters at future moments are predicted.

2. The prediction method according to claim 1, characterized in that: The statistical results include lightning events occurring in the grid and lightning events not occurring in the grid; in each statistical period, position aggregation processing is performed on the multiple grids according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period, including: For a target area corresponding to any statistical period, a target grid is determined in the target area, and the following first aggregation operation is performed on the target grid until all target grids have been subjected to the first aggregation operation, thereby obtaining a lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; Among them, the first aggregation operation includes: taking the target grid as the centroid grid, aggregating neighborhood grids for the centroid grid based on the eight-neighborhood method, and taking the neighborhood grid as the new centroid grid, continuing to aggregate neighborhood grids for the centroid grid based on the eight-neighborhood method until all centroid grids have no neighbor grids, and determining the grid group composed of the centroid grid and the neighborhood grid as a lightning cluster in the lightning density map; the neighborhood grid is a grid in which the statistical result is that a lightning event occurs.

3. The prediction method according to claim 1, characterized in that: The statistical results include lightning events occurring in the grid and lightning events not occurring in the grid; in each statistical period, position aggregation processing is performed on the multiple grids according to the statistical results to obtain a lightning density map corresponding to the target area in each statistical period, including: For a target area corresponding to any statistical period, a target grid is determined in the target area, and the following second aggregation operation is performed on the target grid until the second aggregation operation is performed on all target grids, so as to obtain an initial lightning density map corresponding to the target area in the statistical period; the target grid is a grid in the target area that has not been subjected to the aggregation operation; wherein the second aggregation operation includes: taking the target grid as a centroid grid, aggregating neighborhood grids for the centroid grid based on the eight-neighborhood method, and taking the neighborhood grid as a new centroid grid, continuing to aggregate neighborhood grids for the centroid grid based on the eight-neighborhood method until all centroid grids have no neighborhood grids, and determining the grid group composed of the centroid grid and the neighborhood grid as an initial lightning cluster in the lightning density map; the neighborhood grid is a grid in which a lightning event occurs as a statistical result; The similarity between any two initial lightning clusters in the initial lightning density map is determined, and the initial lightning clusters with similarity greater than a similarity threshold are merged into an ultimate lightning cluster to obtain a lightning density map corresponding to the target area within the statistical period.

4. The prediction method according to claim 3, characterized in that: Determining the similarity between any two initial lightning clusters in the initial lightning density map includes: Determine the shortest distance between the grid in the first initial lightning cluster and the grid in the second initial lightning cluster, and determine the reciprocal of the shortest distance as the similarity between the two initial lightning clusters; the first initial lightning cluster and the second initial lightning cluster are different initial lightning clusters in the two initial lightning clusters.

5. The prediction method according to claim 1, characterized in that: Based on the time series relationship of the statistical period, a time clustering process is performed on the lightning clusters in each lightning density map to determine the moving path of each lightning cluster in the time series of the statistical period, including: With the time series relationship of the statistical periods as a guide, for two lightning density maps within any adjacent time series statistical periods, the following third aggregation operation is performed to determine the moving path of the lightning cluster in the lightning density map within the adjacent time series statistical period; the third aggregation operation includes: determining the distance between the lightning clusters in the two lightning density maps corresponding to the adjacent time series statistical periods; determining the two lightning clusters whose distance is less than the distance threshold as the same lightning cluster, and determining the position of the lightning cluster that is earlier in the time series as the first position of the lightning cluster, and determining the position of the lightning cluster that is later in the time series as the second position of the lightning cluster; determining the moving path of the lightning cluster within the adjacent time series statistical period as moving from the first position to the second position; Based on the time series relationship of the statistical period and the moving paths of the lightning clusters in the lightning density graph in all adjacent time series statistical periods, the moving path of each lightning cluster in the statistical period time series is determined.

6. The prediction method according to claim 1, characterized in that: The moving path includes the position of the lightning cluster in the lightning density map corresponding to each statistical period; and the predicting the position of each lightning cluster at a future moment based on the moving path of each lightning cluster in the statistical period time series includes: For each lightning cluster, determine the moving speed of the lightning cluster within a target statistical period set corresponding to a target time window; the target statistical period set is a statistical period set closest to the target time window in terms of time sequence, and the target time window includes multiple future moments; Inputting the moving speed of the lightning cluster within the target statistical period set into a preset speed prediction model to predict the speed of the lightning cluster in the target time window; Based on the position of the lightning cluster within the target statistical period set and the speed of the lightning cluster in the target time window, the position of the lightning cluster corresponding to the target time window is determined.

7. The prediction method according to claim 6, characterized in that: Before inputting the moving speed of the lightning cluster within the target statistical period set into a preset speed prediction model, the prediction method further includes: Based on the position of the lightning cluster in the lightning density map corresponding to each statistical period, the moving speed of each lightning cluster between each adjacent statistical period is determined; Based on the time series relationship of the statistical periods, the moving speed of the lightning clusters in the first statistical period set is taken as input, and the moving speed of the lightning clusters in the second statistical period set is taken as input, and a preset speed prediction model is constructed and trained to generate; the time series of the statistical periods in the first statistical period set are all arranged before the statistical periods in the second statistical period set in the time series relationship; the first statistical period set includes at least three statistical periods with adjacent time series, and the second statistical period set includes at least two statistical periods with adjacent time series.

8. The prediction method according to claim 7, characterized in that: The location of the lightning cluster includes the boundary grid location; after predicting the location of each lightning cluster at a future time, the prediction method further includes: Collecting the actual boundary grid position of each lightning cluster at the future moment; Based on the predicted boundary grid position of each lightning cluster and the actual boundary grid position, the number of lightning cluster strikes in the prediction result is counted; when the predicted boundary grid position of the lightning cluster coincides with the actual boundary grid position, it is determined that the lightning cluster in the prediction result has struck; or when the ratio of the predicted boundary grid area of ​​the lightning cluster to the actual boundary grid area is greater than a ratio threshold, it is determined that the lightning cluster in the prediction result has struck; determining the accuracy of the speed prediction model according to the number of hits and the total number of lightning clusters in the prediction result; The speed prediction model is optimized according to the accuracy.

9. A lightning location prediction device, characterized in that: include: A determination module, used for determining a target area and dividing the target area into a plurality of grids; A statistical module is used to count the statistical results of lightning events occurring in each grid within a preset time window according to a statistical period; A position processing module is used to perform position aggregation processing on the multiple grids according to the statistical results in each statistical period to obtain a lightning density map corresponding to the target area in each statistical period; one statistical period corresponds to one lightning density map, one lightning density map includes multiple lightning clusters, and one lightning cluster includes at least one grid where a lightning event has occurred; A time processing module, used to perform time clustering processing on the lightning clusters in each lightning density map based on the time series relationship of the statistical period, and determine the moving path of each lightning cluster in the time series of the statistical period; The prediction module is used to predict the position of each lightning cluster at a future moment based on the moving path of each lightning cluster in the statistical period time series.

10. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the lightning position prediction method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: include: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting a lightning position according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that When the computer program product is executed on a computer, the computer is enabled to implement the lightning position prediction method according to any one of claims 1 to 8.

Images