Multi-source disaster-pregnant data fusion preprocessing method and system and storage medium
Through the multi-source pregnancy disaster data fusion preprocessing method, the problem of insufficient fusion of multi-source data is solved, efficient and accurate lightning prediction is achieved, more reliable data support is provided, and the scientific nature of lightning protection and disaster prevention is improved.
Patent Information
- Application Number
- CN202510170673.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-17
- Publication Date
- 2025-05-23
AI Technical Summary
In the existing lightning prediction technology, the fusion of multi-source data is insufficient, resulting in a simple prediction method model, a high false alarm rate, and deep learning-based methods lack effective fusion of multi-source data, which affects the prediction accuracy and timeliness.
The multi-source pregnancy disaster data fusion preprocessing method is adopted to obtain lightning monitoring data, satellite remote sensing data and radar observation data, and data quality control, missing data processing, interpolation and normalization processing, obtain a unified spatial and temporal resolution, and store it in the form of grayscale images to achieve effective fusion of multi-source data.
It improves the accuracy and reliability of lightning prediction, simplifies the calculation process, makes it easy to achieve rapid data fusion results, and supports more scientific lightning protection and disaster prevention.
Smart Images
Figure CN120030098A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of lightning disaster risk prediction, and in particular relates to a multi-source disaster-prone data fusion preprocessing method, system and storage medium. Background Art
[0002] Lightning is a violent discharge phenomenon in the atmosphere, with high voltage, large current, and strong electromagnetic radiation characteristics. It is a kind of weather with serious disastrous effects and has been listed as "one of the 10 most serious natural disasters". Lightning disasters seriously threaten people's production and life safety. Researching lightning prediction technology and improving the accuracy and timeliness of lightning prediction have great application value in formulating proactive disaster prevention and mitigation measures and ensuring production and life safety.
[0003] In the past, lightning prediction based on lightning monitoring data was mainly based on atmospheric electric field instruments or lightning location systems, which issued warning information after thunderstorm clouds were electrified or lightning occurred. Lightning prediction methods based on numerical meteorological models are limited by the large amount of calculation in physical models and insufficient computing power. Their warning results are rough, time-consuming, and inefficient. With the development of computer methods such as random forests and neural networks, lightning approach warning technology based on machine learning has begun to develop in the direction of high efficiency and accuracy. Methods based on deep learning mainly use satellite images (stars), radar combined reflectivity (air), ground flashes (ground) and other data, but the prediction parameters used by existing deep learning models are relatively single or the fusion of multi-source data is insufficient, resulting in a simple forecasting method model and a high false alarm rate. Summary of the invention
[0004] In view of this, the present invention provides a multi-source disaster-pregnancy data fusion preprocessing method, system and storage medium. It is used to fuse satellite-air-ground multi-source data of different temporal and spatial resolutions to obtain data with unified temporal and spatial resolution, and use it for lightning prediction. This method can effectively fuse different data, using satellite remote sensing data to reflect large-scale cloud movement information, using radar observation data to reflect precipitation particle information in the cloud, and using lightning monitoring data to provide real-time lightning occurrence conditions. After the above data is fused and applied to lightning prediction, it can improve the prediction accuracy and reliability, and provide more scientific and reliable data support for lightning protection and disaster prevention.
[0005] The technical solution adopted by the present invention is: a multi-source disaster data fusion preprocessing method, comprising:
[0006] Obtain multi-source disaster data, including lightning monitoring data, satellite remote sensing data, and radar observation data;
[0007] Performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data;
[0008] Interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution; grid the processed lightning monitoring data and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution;
[0009] Normalize the multi-source disaster data after obtaining a unified temporal and spatial resolution;
[0010] The normalized multi-source disaster-prone data are stored in a predetermined manner or format for use in lightning prediction.
[0011] Furthermore, the data quality control method of the lightning monitoring data is: the lightning monitoring data with the number of participating positioning stations less than a preset threshold is eliminated.
[0012] Furthermore, the missing data processing method of satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the previous and next adjacent times are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of this period is discarded.
[0013] Furthermore, obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of the satellite remote sensing data by bilinear interpolation to match the spatial resolution of the radar observation data, and temporally interpolating the radar observation data by linear interpolation to maintain a consistent temporal resolution with the satellite remote sensing data.
[0014] Furthermore, the lightning monitoring data is gridded and aligned in space and time with the interpolated satellite remote sensing data and radar observation data. When the discrete lightning data of the lightning monitoring data is gridded, the lightning location points with an accuracy of 100 meters are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
[0015] Furthermore, the method for storing multi-source disaster data in a predetermined manner or format is as follows:
[0016] The normalized satellite remote sensing data, radar observation data and lightning monitoring data are respectively multiplied by predetermined coefficients and mapped to a numerical range of 0 to 255, and stored in the form of grayscale images.
[0017] The present invention also discloses a multi-source disaster data fusion preprocessing system, including a data acquisition module, a preprocessing module, an interpolation unification module, a normalization processing module and a storage module.
[0018] Data acquisition module, used to obtain multi-source disaster data, including lightning monitoring data, satellite remote sensing data and radar observation data;
[0019] A preprocessing module, used for performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data;
[0020] The interpolation unification module is used to interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution, grid the processed lightning monitoring data, and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution;
[0021] The normalization processing module is used to normalize the multi-source disaster data after obtaining a unified spatiotemporal resolution;
[0022] The storage module is used to store the normalized multi-source disaster-pregnancy data in a predetermined manner or format for use in lightning prediction.
[0023] Furthermore, the data quality control method of the lightning monitoring data is: the lightning monitoring data with the number of participating positioning stations less than a preset threshold is eliminated.
[0024] Furthermore, the missing data processing method of satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the previous and next adjacent times are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of this period is discarded.
[0025] Furthermore, obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of the satellite remote sensing data by bilinear interpolation to match the spatial resolution of the radar observation data, and temporally interpolating the radar observation data by linear interpolation to maintain a consistent temporal resolution with the satellite remote sensing data.
[0026] Furthermore, the lightning monitoring data is gridded and aligned in space and time with the interpolated satellite remote sensing data and radar observation data. When the discrete lightning data of the lightning monitoring data is gridded, the lightning location points with an accuracy of 100 meters are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
[0027] Furthermore, the method for storing multi-source disaster data in a predetermined manner or format is as follows:
[0028] The normalized satellite remote sensing data, radar observation data and lightning monitoring data are respectively multiplied by predetermined coefficients and mapped to a numerical range of 0 to 255, and stored in the form of grayscale images.
[0029] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-source disaster-prone data fusion preprocessing method are implemented.
[0030] The present invention obtains and fuses data with uniform temporal and spatial resolution, respectively using satellite remote sensing data to reflect large-scale cloud movement information, radar observation data to reflect precipitation particle information in the cloud, and lightning monitoring data to provide real-time lightning conditions. Applied to lightning prediction, it can improve prediction accuracy and reliability. The calculation process is relatively simple and easy to implement, and the data fusion result can be quickly obtained. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0032] Figure 1 It is a flow chart of Embodiment 1 of the multi-source disaster data fusion preprocessing method of the present invention;
[0033] Figure 2 This is a functional module diagram of a second embodiment of a multi-source disaster data fusion preprocessing system of the present invention;
[0034] Figure 3 It is the images of different channels of satellite (including visible light, water vapor and infrared channels);
[0035] Figure 4 It is the radar combined reflectivity image. DETAILED DESCRIPTION
[0036] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0037] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0038] Embodiment 1:
[0039] like Figure 1 As shown, a multi-source disaster-pregnant data fusion preprocessing method includes obtaining multi-source disaster-pregnant data, including lightning monitoring data of a lightning monitoring network, satellite remote sensing data, and radar observation data;
[0040] Performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data;
[0041] Interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution; grid the processed lightning monitoring data and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution;
[0042] Normalize the multi-source disaster data after obtaining a unified temporal and spatial resolution;
[0043] The normalized multi-source disaster-prone data are stored in a predetermined manner or format for use in lightning prediction.
[0044] In the above technical solution, the lightning monitoring data includes the time of lightning occurrence, longitude, latitude, and number of participating positioning stations. As shown in the following table:
[0045] Table 1 Example of lightning monitoring data (including the time, latitude and longitude of lightning occurrence)
[0046] time Microseconds latitude longitude Number of participating positioning stations 21:20:21 2804791 29.103894 105.059658 2 21:20:23 221116 29.432289 91.774612 7 21:20:23 221293 29.303452 91.62205 15 21:20:25 1430403 29.151595 105.10164 2 21:20:25 3190804 29.166534 105.087603 7 21:20:25 3747653 29.162258 105.085361 23 21:20:25 6138372 29.132312 105.113735 6 21:20:25 6590998 29.133157 105.112463 7 21:20:26 2964764 30.344877 92.540879 9 21:20:26 2991063 29.199563 105.162618 19 21:20:27 8449831 29.384269 91.606833 8 21:20:28 619837 29.39498 91.625346 4 21:20:28 927344 29.395301 91.625251 3 21:20:28 5781953 28.398339 100.852021 8 21:20:29 4824370 29.091413 105.164682 5 21:20:30 1497839 29.650652 105.263556 9
[0047] In this embodiment, the lightning monitoring data comes from the wide-area lightning monitoring network, including the time of lightning occurrence, longitude, latitude, and number of participating positioning stations (with a time resolution of microseconds and a spatial resolution of hundreds of meters). The lightning monitoring data is used to reflect the real-time occurrence of lightning.
[0048] In the above technical solution, the satellite remote sensing data includes brightness temperature of different satellite channels and satellite channel difference information. In this embodiment, the satellite channels include: water vapor channel and infrared channel.
[0049] In this embodiment, the infrared channel and channel difference of the geostationary satellite reflecting convective clouds are selected. Since the visible light channel has no effective observation at night and cannot be used for nighttime lightning prediction, in order to establish an all-weather lightning prediction method, the visible light channel is not considered as a lightning prediction factor.
[0050] In this embodiment, the sunflower 8 / 9 geostationary satellite ( Figure 3 As shown in the figure, the geostationary satellite infrared channels and channel differences reflecting convective clouds are selected. The satellite infrared channels selected to reflect convection include: channels 8, 9, and 10, water vapor channels at different altitudes in the troposphere, channels 11, 13, 14, 15, and 16, and channel difference information such as 8-10, 8-13, 9-14, 10-13, (11-14)-(14-15), 15-13, 15-14, 16-13, and 16-14. The temporal resolution is 10 minutes and the spatial resolution is 0.05°.
[0051] In the above technical solution, if Figure 4 As shown, the radar observation data includes radar combined reflectivity for reflecting the information of precipitation particles in the cloud.
[0052] In this embodiment, the temporal and spatial resolutions are 6 minutes and 0.01°, respectively.
[0053] The data quality control method of lightning monitoring data is as follows: the lightning monitoring data with the number of participating positioning stations less than the preset threshold M (M is generally greater than or equal to 3) are eliminated.
[0054] The missing data processing method for satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the adjacent times before and after are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of that period is discarded.
[0055] In this embodiment, the satellite system maintenance is performed at 0240 and 1440 every day, resulting in fixed loss of satellite images; in addition, satellite images at certain times in the satellite storage server are occasionally lost. For the times when satellite image data is lost, linear interpolation is performed using the data of the time before and after the lost data. For satellite remote sensing data that is lost for more than two consecutive times, no interpolation is performed and it is no longer considered in the subsequent process of establishing a lightning prediction data set.
[0056] Obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of satellite remote sensing data through bilinear interpolation to match the spatial resolution of radar observation data, and temporally interpolating radar observation data through linear interpolation to maintain a consistent temporal resolution with that of satellite remote sensing data.
[0057] In this embodiment, the satellite remote sensing data with a spatial resolution of 0.05° is interpolated to 0.01° using a bilinear interpolation method, which corresponds to the spatial resolution of the radar observation data; the radar observation data with a temporal resolution of 6 minutes is interpolated to 10 minutes using a linear interpolation method, which corresponds to the temporal resolution of the satellite remote sensing data.
[0058] The method for gridding lightning monitoring data and aligning them with the interpolated satellite remote sensing data and radar observation data in space and time is as follows: when gridding the discrete lightning data of lightning monitoring data, the lightning location points with a hundred-meter accuracy are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
[0059] In this embodiment, the discrete lightning location data with a spatial accuracy of hundreds of meters is rasterized, and the spatial distribution resolution is 0.01°, which corresponds to the spatial resolution of radar observation data; and statistics are calculated on a 10-minute grid, which corresponds to the temporal resolution of satellite remote sensing data.
[0060] The normalization processing of lightning monitoring data in the interpolated multi-source disaster data includes: firstly binarizing the gridded lightning monitoring data and counting the lightning occurrence according to the 0.01° grid: if lightning occurs in the grid, it is set to 1, otherwise it is set to 0; and Gaussian blurring is performed on the binarized matrix to obtain a smoother lightning distribution.
[0061] The normalization process of the satellite remote sensing data in the interpolated multi-source disaster data includes: traversing all time periods of the interpolated satellite remote sensing data and performing normalization process according to the following formula:
[0062]
[0063] Among them, S max is the maximum value of satellite remote sensing data; S min is the minimum value of satellite remote sensing data; S norm is the normalized satellite remote sensing data.
[0064] The normalization process of the radar observation data in the interpolated multi-source disaster-pregnant data includes: the interpolated radar observation data is normalized according to the following formula:
[0065]
[0066] Among them, R max is the maximum value of radar combined reflectivity; R min is the minimum value of radar combined reflectivity; R norm is the normalized radar observation data.
[0067] Through normalization processing, the differences in the numerical ranges of radar observation data, satellite remote sensing data and lightning monitoring data are reduced.
[0068] The method for storing the normalized multi-source disaster data in a predetermined manner or format is as follows:
[0069] The PythonImage.fromarray library is used to multiply the normalized satellite remote sensing data, radar observation data, and lightning monitoring data by a predetermined coefficient of 255 and then mapped to a numerical range of 0 to 255. These data are mapped to the pixel value range of an 8-bit grayscale image and stored in the form of a grayscale image.
[0070] Embodiment 2:
[0071] like Figure 2 As shown, a multi-source disaster data fusion preprocessing system includes a data acquisition module, a preprocessing module, an interpolation unification module, a normalization processing module and a storage module.
[0072] Data acquisition module, used to obtain multi-source disaster data, including lightning monitoring data from the lightning monitoring network, satellite remote sensing data, and radar observation data;
[0073] A preprocessing module, used for performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data;
[0074] The interpolation unification module is used to interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution, grid the processed lightning monitoring data, and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution;
[0075] The normalization processing module is used to normalize the multi-source disaster data after obtaining a unified spatiotemporal resolution;
[0076] The storage module is used to store the normalized multi-source disaster-pregnancy data in a predetermined manner or format for use in lightning prediction.
[0077] The lightning monitoring data includes information on the time of lightning occurrence, longitude, latitude, and number of participating positioning stations.
[0078] The satellite remote sensing data includes the brightness temperature of different satellite channels and satellite channel difference information.
[0079] The radar observation data includes radar combined reflectivity for reflecting information of precipitation particles in clouds.
[0080] The data quality control method of lightning monitoring data is to eliminate the lightning monitoring data whose number of participating positioning stations is less than the preset threshold.
[0081] The missing data processing method for satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the adjacent times before and after are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of that period is discarded.
[0082] Obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of satellite remote sensing data through bilinear interpolation to match the spatial resolution of radar observation data, and temporally interpolating radar observation data through linear interpolation to maintain a consistent temporal resolution with that of satellite remote sensing data.
[0083] The method for gridding lightning monitoring data and aligning them with the interpolated satellite remote sensing data and radar observation data in space and time is as follows: when gridding the discrete lightning data of lightning monitoring data, the lightning location points with a hundred-meter accuracy are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
[0084] The normalization processing of the lightning monitoring data in the interpolated multi-source disaster data includes: firstly binarizing the gridded lightning monitoring data: if lightning occurs in the grid, it is set to 1, otherwise it is set to 0; and Gaussian blurring is performed on the binarized matrix to obtain a smoother lightning distribution.
[0085] The normalization process of the satellite remote sensing data in the interpolated multi-source disaster data includes: traversing all time periods of the interpolated satellite remote sensing data and performing normalization process according to the following formula:
[0086]
[0087] Among them, S max is the maximum value of satellite remote sensing data; S min is the minimum value of satellite remote sensing data; S norm is the normalized satellite remote sensing data.
[0088] The normalization process of the radar observation data in the interpolated multi-source disaster-pregnant data includes: the interpolated radar observation data is normalized according to the following formula:
[0089]
[0090] Among them, R max is the maximum value of radar combined reflectivity; R minis the minimum value of radar combined reflectivity; R norm is the normalized radar observation data.
[0091] The method for storing the normalized multi-source disaster data in a predetermined manner or format is as follows:
[0092] The normalized satellite remote sensing data, radar observation data and lightning monitoring data are respectively multiplied by predetermined coefficients and mapped to a numerical range of 0 to 255, and stored in the form of grayscale images.
[0093] Embodiment three:
[0094] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-source disaster-prone data fusion preprocessing method are implemented.
[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims of the invention.
[0100] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.
Claims
1. A multi-source disaster data fusion preprocessing method, characterized by: Obtain multi-source disaster data, including lightning monitoring data, satellite remote sensing data, and radar observation data; Performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data; Interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution; grid the processed lightning monitoring data and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a uniform spatial and temporal resolution; Normalize the multi-source disaster data after obtaining a unified temporal and spatial resolution; The normalized multi-source disaster-prone data are stored in a predetermined manner or format for use in lightning prediction.
2. The multi-source disaster data fusion preprocessing method according to claim 1 is characterized by: The data quality control method of lightning monitoring data is to eliminate lightning monitoring data with the number of participating positioning stations less than a preset threshold.
3. The multi-source disaster data fusion preprocessing method according to claim 1 is characterized by: The missing data processing method for satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the adjacent times before and after are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of that period is discarded.
4. The multi-source disaster data fusion preprocessing method according to claim 1 is characterized by: Obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of satellite remote sensing data through bilinear interpolation to match the spatial resolution of radar observation data, and temporally interpolating radar observation data through linear interpolation to maintain a consistent temporal resolution with that of satellite remote sensing data.
5. The multi-source disaster data fusion preprocessing method according to claim 1 is characterized by: The method for gridding lightning monitoring data and aligning them with the interpolated satellite remote sensing data and radar observation data in space and time is as follows: when gridding the discrete lightning data of lightning monitoring data, the lightning location points with a hundred-meter accuracy are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
6. The multi-source disaster data fusion preprocessing method according to claim 1 is characterized by: The method of storing multi-source disaster data in a predetermined manner or format is as follows: The normalized satellite remote sensing data, radar observation data and lightning monitoring data are respectively multiplied by predetermined coefficients and mapped to a numerical range of 0 to 255, and stored in the form of grayscale images.
7. A multi-source disaster data fusion preprocessing system, characterized by: The multi-source disaster data fusion preprocessing system includes a data acquisition module, a preprocessing module, an interpolation unification module, a normalization processing module and a storage module. Data acquisition module, used to obtain multi-source disaster data, including lightning monitoring data from the lightning monitoring network, satellite remote sensing data, and radar observation data; A preprocessing module, used for performing data quality control processing on the lightning monitoring data and performing missing data processing on the satellite remote sensing data; The interpolation unification module is used to interpolate the processed satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution, grid the processed lightning monitoring data, and align them with the interpolated satellite remote sensing data and radar observation data in space and time to obtain a unified spatial and temporal resolution; The normalization processing module is used to normalize the multi-source disaster data after obtaining a unified spatiotemporal resolution; The storage module is used to store the normalized multi-source disaster-pregnancy data in a predetermined manner or format for use in lightning prediction.
8. The multi-source disaster data fusion preprocessing system according to claim 7 is characterized by: The data quality control method of lightning monitoring data is to eliminate lightning monitoring data with the number of participating positioning stations less than a preset threshold.
9. The multi-source disaster data fusion preprocessing system according to claim 7, characterized in that: The missing data processing method for satellite remote sensing data is as follows: for satellite remote sensing data with fixed missing times or occasional missing times, if it is missing only once or twice in a row, the data of the adjacent times before and after are used for interpolation; if it is missing more than twice in a row, no interpolation is performed and the data of that period is discarded.
10. The multi-source disaster data fusion preprocessing system according to claim 7, characterized in that: Obtaining a unified spatiotemporal resolution for satellite remote sensing data and radar observation data includes: refining the spatial resolution of satellite remote sensing data through bilinear interpolation to match the spatial resolution of radar observation data, and temporally interpolating radar observation data through linear interpolation to maintain a consistent temporal resolution with that of satellite remote sensing data.
11. The multi-source disaster data fusion preprocessing system according to claim 7, characterized in that: The method for gridding lightning monitoring data and aligning them with the interpolated satellite remote sensing data and radar observation data in space and time is as follows: when gridding the discrete lightning data of lightning monitoring data, the lightning location points with a hundred-meter accuracy are mapped to the same grid as the radar observation data; and the number of lightning occurrences or occurrence marks are counted according to the time resolution corresponding to the satellite remote sensing data.
12. The multi-source disaster data fusion preprocessing system according to claim 7, characterized in that: The method of storing multi-source disaster data in a predetermined manner or format is as follows: The normalized satellite remote sensing data, radar observation data and lightning monitoring data are respectively multiplied by predetermined coefficients and mapped to a numerical range of 0 to 255, and stored in the form of grayscale images.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the multi-source disaster-prone data fusion preprocessing method according to any one of claims 1 to 6 are implemented.