Remote thunderstorm activity path movement prediction method and related device

Abstract

The invention discloses a long-distance thunderstorm activity path movement prediction method and a related device, and belongs to the technical field of thunderstorm monitoring. According to the method, lightning positioning data, weather radar data and ground meteorological data are subjected to deep fusion and cooperative verification, thunderstorm cloud recognition is carried out, and the limitation of single data source early warning is overcome. Carrying out centroid calculation on the identified thunderstorm cloud, and determining a thunderstorm cloud moving path; and upstream thunderstorm cloud can be found as early as possible and the moving track of the upstream thunderstorm cloud can be continuously And the integrated learning model is combined to predict the moving path, so that sufficient decision and response time can be provided before the thunderstorm cloud reaches the protection area. The whole process is from data fusion, thunderstorm cloud identification and path tracking to final prediction and early warning, highly automatic operation is realized, dependence on personal experience of a predictor is greatly reduced, objectivity and consistency of an early warning result are ensured, and effective technical support is provided for deployment and application in actual lightning protection engineering.

Description

Technical Field

[0001] This invention belongs to the field of thunderstorm monitoring technology and relates to a method and related device for predicting the movement of thunderstorm activity paths over long distances. Background Technology

[0002] Lightning is a violent atmospheric discharge phenomenon that accompanies severe convective weather and has immense destructive power. The powerful current and intense heat generated by lightning can directly destroy power facilities, disrupt communication networks, cause fires, and even explosions, posing a serious challenge to the safe operation of critical infrastructure such as petrochemicals, aerospace, and rail transportation. Secondly, lightning electromagnetic pulses can cause severe interference and even permanent damage to increasingly sophisticated electronic information systems and equipment. Furthermore, direct lightning strikes pose a significant threat to the safety of outdoor workers, aerospace vehicles, and the public.

[0003] Early warning is crucial for effectively responding to lightning disasters. Traditional lightning warning technologies can be broadly categorized into two types: the first is warnings based on lightning location systems. These systems deploy multiple detection stations to monitor the electromagnetic wave signals emitted by lightning, enabling relatively accurate determination of the time, location, intensity, and type (cloud-to-ground or ground-to-ground) of lightning occurrence. However, this technology is essentially a "post-event" monitoring method, meaning it only issues an alarm after lightning has already occurred. While it reflects the past and present state of thunderstorm activity, it struggles to effectively predict the future movement and development trends of thunderstorm systems, resulting in very limited lead time. By the time a warning is issued, the thunderstorm cloud may already be very close to or protected by a target, leaving insufficient time for preventative measures and potentially leaving no room for preparedness. The second type is warnings based on weather radar. Weather radar emits electromagnetic waves and receives echoes from precipitation particles (such as rain, snow, and hail), effectively detecting the macroscopic structure, intensity, and direction of movement within thunderstorm clouds. Radar can identify echo characteristics with strong convective development potential early on, thus providing a degree of predictive capability. However, radar observation also has its inherent limitations: on the one hand, radar echoes mainly reflect information about precipitation particles, while their indicative role in the crucial electrification and discharge processes in thunderstorm clouds is relatively indirect, which may lead to inaccurate judgments on the intensity and frequency of lightning activity itself, i.e., "strong echoes do not necessarily accompany strong lightning"; on the other hand, radar data is easily affected by ground obstruction, distance attenuation, and interference from non-meteorological echoes (such as super-refraction), which affects its detection accuracy and reliability.

[0004] Currently, one approach in the industry is to attempt a simple overlay display of lightning location data and weather radar data. Operators subjectively infer the movement path and intensity changes of thunderstorm clouds based on their personal experience by comprehensively interpreting the two data sources. However, this method has significant drawbacks. Lightning location data and radar data originate from different detection principles and equipment, and they inherently differ in data format, spatiotemporal resolution, and update frequency. Simple overlay does not solve the problem of data synchronization and alignment in time and space, resulting in "time lag" and "position difference" in the description of the same thunderstorm cloud, affecting the accuracy of judgment. Furthermore, the accuracy of warnings highly depends on the forecaster's personal experience and analytical skills, lacking objective, unified, and quantifiable judgment standards, making it difficult to achieve automated and operationally accurate warnings, and prone to misjudgment or omission due to human fatigue or negligence. In addition, thunderstorm clouds are not static entities; their life cycle encompasses multiple stages such as generation, development, maturity, and dissipation, accompanied by complex evolutions such as movement, splitting, and merging. Existing technologies struggle to automatically and continuously track the complete life cycle of a single thunderstorm cloud cluster, especially to accurately characterize its evolutionary path. Without precise quantification of historical movement paths, any prediction of future paths will be crude and unreliable.

[0005] In summary, there is an urgent need to develop a method that can automatically and objectively identify and track thunderstorm cloud clusters and accurately predict their future movement paths, thereby providing protected areas with sufficient lead time and high reliability of lightning warning information to support managers in taking timely and effective preventive measures. Summary of the Invention

[0006] The purpose of this invention is to provide a method and related apparatus for predicting the movement of long-distance thunderstorm activity paths, so as to solve the technical problem that the prediction of thunderstorm clouds in the prior art is not accurate enough and cannot meet the prevention needs of management personnel.

[0007] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a method for predicting the movement of long-distance thunderstorm activity paths, comprising the following steps: Acquire lightning location data and weather radar data within the lightning activity monitoring range to identify thunderstorm clouds; The centroid of the identified thunderstorm clouds is calculated to obtain the centroid calculation results; The movement path of the thunderstorm cloud was determined based on the centroid calculation results; Acquire surface meteorological data, input the surface meteorological data and the thunderstorm cloud movement path into a pre-established thunderstorm path prediction model, and predict the future movement path of the thunderstorm cloud.

[0008] Furthermore, the lightning location data includes at least the longitude, latitude, amplitude, and lightning type; the weather radar data includes at least the echo intensity, echo top height, and vertical cumulative liquid water.

[0009] Furthermore, the step of acquiring lightning location data and weather radar data within the lightning activity monitoring range and identifying thunderstorm clouds specifically includes: Unify the format and time precision of lightning location data and weather radar data, and then align the time of lightning location data and weather radar data to complete the data preprocessing; Based on the preprocessed data, the DBSCAN clustering algorithm was used to identify and number the different clusters of thunderstorm clouds.

[0010] Furthermore, the step of calculating the centroid of the identified thunderstorm cloud to obtain the centroid calculation result specifically includes: using a spatiotemporal joint weighting method, combining spatial local density weights and time decay weights to calculate the centroid; wherein, points with high spatial local density are assigned higher weights, and points that occur later are assigned higher weights; the formula for calculating the centroid of the thunderstorm cloud is:

[0011]

[0012]

[0013]

[0014] In the formula, The latitude of the centroid of the thunderstorm cloud after weighted calculation; The longitude of the thunderstorm cloud centroid after weighted calculation; For thunderstorm clouds i The joint weight of the lightning record points; Spatial density weights for each lightning record point; The time decay weight for each lightning record point; N is the number of lightning record points within the thunderstorm cloud cluster; The original latitude of the centroid of the thunderstorm cloud; The original longitude of the center of mass of the thunderstorm cloud; This is the time difference between this point and the latest recorded point within the cluster.

[0015] Furthermore, the step of determining the movement path of the thunderstorm cloud based on the centroid calculation results specifically includes: The spatiotemporal proximity algorithm is used to track the centroid of each thunderstorm cloud cluster under different time windows. The centroid positions of each thunderstorm cloud cluster under consecutive time windows are connected to obtain the movement path of the thunderstorm cloud.

[0016] Furthermore, the ground meteorological data includes at least air pressure, wind direction, wind speed, temperature, and relative humidity.

[0017] Furthermore, the construction process of the thunderstorm path prediction model includes: Based on the ensemble learning model, historical thunderstorm cloud centroid location data and surface meteorological data are input into the ensemble learning model for training, resulting in a thunderstorm path prediction model.

[0018] Secondly, the present invention provides a long-distance thunderstorm activity path prediction system, comprising: The thunderstorm cloud identification module is used to acquire lightning location data and weather radar data within the lightning activity monitoring range and identify thunderstorm clouds; The centroid calculation module is used to calculate the centroid of the identified thunderstorm clouds and obtain the centroid calculation results. The path determination module is used to determine the path of the thunderstorm cloud based on the centroid calculation results. The prediction module is used to acquire surface meteorological data, input the surface meteorological data and the thunderstorm cloud movement path into a pre-established thunderstorm path prediction model, and predict the future movement path of the thunderstorm cloud.

[0019] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the long-distance thunderstorm activity path movement prediction method described above.

[0020] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the long-distance thunderstorm activity path movement prediction method described above.

[0021] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses a method and related device for predicting the movement of long-distance thunderstorm activity paths. By deeply fusing and collaboratively verifying lightning location data, weather radar data, and ground meteorological data, thunderstorm clouds are identified, overcoming the limitations of single-data-source warnings. Centroid calculation is performed on the identified thunderstorm clouds to determine their movement paths; this allows for early detection of upstream thunderstorm clouds and continuous tracking of their trajectories. Combining an ensemble learning model to predict the movement paths provides sufficient decision-making and response time before the thunderstorm clouds reach the protected area. It can automatically identify and separate different thunderstorm cloud clusters without requiring manual setting of fixed parameters, exhibiting strong adaptability. The entire process, from data fusion, thunderstorm cloud identification, path tracking to final prediction and warning, achieves a high degree of automation, greatly reducing reliance on forecasters' personal experience and ensuring the objectivity and consistency of warning results. This provides effective technical support for deployment and application in practical lightning protection engineering. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a long-distance thunderstorm activity path movement prediction method according to the present invention; Figure 2 This is a schematic diagram of a long-distance thunderstorm activity path prediction system according to the present invention; Figure 3 This is a flowchart of a method according to an embodiment of the present invention. Detailed Implementation

[0024] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0025] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0026] See Figure 1 This invention discloses a method for predicting the movement of long-distance thunderstorm activity paths, comprising the following steps: S1, acquire lightning location data and weather radar data within the lightning activity monitoring range, and identify thunderstorm clouds; The lightning location data is obtained using a Lightning Location System (LLS), which acquires the coordinate data of lightning occurring within the lightning activity monitoring range, including the time of the lightning occurrence, the longitude, latitude, amplitude, and lightning type (cloud lightning / ground lightning), etc., with a data update frequency of ≤10min / time; The weather radar data is acquired using phased array radars (scanning frequency ≤ 1 min / time) deployed within the warning range. The acquired weather radar data within the lightning activity monitoring range includes echo intensity (dBz), echo top height (km), and vertical cumulative liquid water (kg / m2). Unify the format and time precision of lightning location data and weather radar data, and then align the time of lightning location data and weather radar data to complete the data preprocessing; Based on the preprocessed data, the DBSCAN clustering algorithm with adaptive parameters was used to identify and number the thunderstorm clouds in different clusters.

[0027] S2, perform centroid calculation on the identified thunderstorm clouds to obtain the centroid calculation results; A spatiotemporal weighted method is employed to calculate the centroid by combining spatial local density weights and temporal decay weights. Spatially, points located in dense cores have a greater impact on the final centroid position and are therefore given higher weights. Temporally, points occurring later within the time window are more representative of the current location of the thunderstorm cloud and are thus given higher weights. This spatiotemporal weighted method for calculating the centroid more accurately reflects the spatiotemporal distribution characteristics of lightning activity compared to the simple averaging method. Spatial weights highlight the core location of high-density areas, while temporal weights emphasize the importance of recent data, resulting in a more precise and dynamic centroid location. The formula for calculating the spatiotemporal weighted thunderstorm cloud centroid is as follows:

[0028]

[0029]

[0030]

[0031] In the formula, and These are the latitude and longitude of the thunderstorm cloud centroid after weighted calculation; For thunderstorm clouds i The joint weight of the lightning record points; The spatial density weight for each lightning record point is determined by the number of neighbors within a radius of ε; the more neighbors, the higher the density weight. The larger the value; The time decay weight for each lightning record point is calculated, with later-occurring lightning events receiving a higher weight. The larger the value, the greater the value; N is the number of lightning record points within the thunderstorm cloud cluster. The original latitude of the centroid of the thunderstorm cloud; The original longitude of the center of mass of the thunderstorm cloud; This is the time difference between this point and the latest recorded point within the cluster.

[0032] This spatiotemporal weighted method for calculating the centroid more accurately reflects the spatiotemporal distribution characteristics of lightning activity compared to the simple average method. The spatial weight highlights the core location of high-density areas, while the temporal weight emphasizes the importance of recent data, thus obtaining a more accurate and dynamic centroid location.

[0033] S3, determine the movement path of the thunderstorm cloud based on the centroid calculation results; The preferred time window size is 10 minutes. Considering the generation, dissipation, splitting, merging, and propagation of thunderstorm clouds, a thunderstorm cloud tracking algorithm with spatiotemporal proximity algorithm as its core is used to track the centroid of each cluster of thunderstorm clouds under different time windows. The centroid positions of each cluster of thunderstorm clouds under continuous time windows are connected to obtain the movement path of the thunderstorm clouds. S4. Acquire surface meteorological data, input the surface meteorological data and the thunderstorm cloud movement path into the pre-established thunderstorm path prediction model, and predict the future movement path of the thunderstorm cloud.

[0034] The ground meteorological data is obtained through ground meteorological observation stations, acquiring real-time ground meteorological observation data within the lightning activity monitoring range, including air pressure, wind direction, wind speed, temperature / air temperature, relative humidity, etc. Thunderstorm cloud centroid location data from the previous few time windows are selected and combined with ground meteorological data. The data is then input into an ensemble learning model for training. The ensemble learning model preferably adopts the XGBoost model, and the parameters are optimized using the Bayesian optimization algorithm. The optimal parameter model is selected to obtain the thunderstorm path prediction model. The thunderstorm path prediction model is then used to predict the movement position of the thunderstorm cloud centroid in the next time period.

[0035] When thunderstorm clouds appear within the area, the movement path of the thunderstorm clouds is continuously tracked. After obtaining the centroid location data of the thunderstorm clouds and the ground meteorological data for at least 3 time windows, the data is input into the thunderstorm path prediction model. The thunderstorm path prediction model is used to predict the movement direction and centroid location of the thunderstorm clouds in the future within a specified time period and to give the probability of occurrence, thus establishing a thunderstorm activity path prediction system.

[0036] See Figure 2 This invention discloses a long-range thunderstorm activity path prediction system, including a thunderstorm cloud identification module, a centroid calculation module, a path determination module, and a prediction module. The thunderstorm cloud identification module acquires lightning location data and weather radar data within the lightning activity monitoring range to identify thunderstorm clouds. The centroid calculation module performs centroid calculations on the identified thunderstorm clouds to obtain the centroid calculation results. The path determination module determines the thunderstorm cloud's path based on the centroid calculation results. The prediction module acquires surface meteorological data, inputs the surface meteorological data and the thunderstorm cloud's path into a pre-established thunderstorm path prediction model, and predicts the future path of the thunderstorm clouds.

[0037] Example: See Figure 3 This embodiment discloses a method for predicting the movement of long-distance thunderstorm activity paths, which specifically includes the following implementation steps: 1. Assume the lightning warning and protection area is a circle with a radius of 15km. Considering that the speed of lightning movement is 30-60km / h, a circle with a radius of 60km is selected as the lightning activity monitoring range, and the center of the circle is selected as the center of the lightning warning and protection area; 2. To acquire lightning location data and weather radar data within the lightning activity monitoring range, the formats of the two types of data are first standardized. Then, due to the different sampling rates of the two data acquisition modules, the time accuracy needs to be standardized to the minute level, and the format standardized to CSV. Fields include timestamp (yyyy-MM-dd HH:mm), latitude, longitude, and data type. Finally, the times of the two signals are aligned so that when a thunderstorm cloud enters the lightning activity monitoring range, both the lightning location data acquisition module and the weather radar data acquisition module can identify the thunderstorm cloud within the same time period. If, within a time window (10 minutes) in a certain area within the monitoring range, lightning location data is collected ≥10 times, and the weather radar identifies the appearance of a thunderstorm cloud within that time period, then thunderstorm weather is considered to have occurred within the lightning activity monitoring range. 3. If both lightning location data and weather radar data identify a thunderstorm cloud at a certain location within the lightning activity monitoring range, then track the thunderstorm cloud, obtain its lightning location data and weather radar data, and activate the thunderstorm activity path monitoring system. 4. Perform centroid calculation on thunderstorm clouds, connect the centroid positions of each cluster of thunderstorm clouds in a continuous time window to obtain the movement path of thunderstorm clouds; and acquire ground meteorological data. After continuously tracking thunderstorm clouds and obtaining data for 3 time windows, the thunderstorm activity path monitoring system predicts the movement direction and location of thunderstorm clouds in the future. 5. Continuously track the movement of thunderstorm clouds. After a time window, make new predictions about the direction and location of the thunderstorm clouds. Continue this process until no thunderstorm clouds are detected within the lightning activity monitoring range for three consecutive time windows. If the thunderstorm clouds are considered to have dissipated or moved outside the lightning monitoring range and will not pose a threat to the lightning warning protection area, the thunderstorm activity within the monitoring range is considered to have ended. At this point, the thunderstorm activity path monitoring system is shut down, while the lightning location data acquisition module and the ground meteorological data acquisition module continue to run, awaiting the arrival of the next thunderstorm activity.

[0038] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used in the operation of a long-distance thunderstorm activity path prediction method.

[0039] This invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the long-distance thunderstorm activity path movement prediction method in the above embodiments.

[0040] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0041] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0042] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0043] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0044] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method of predicting the movement of a thunderstorm activity path over a long distance, characterized by, The method comprises the following steps: obtaining lightning location data and weather radar data within a lightning activity monitoring range, identifying thunderstorm clouds; performing centroid calculation on the identified thunderstorm clouds to obtain a centroid calculation result; determining a thunderstorm cloud movement path according to the centroid calculation result; obtaining ground meteorological data, inputting the ground meteorological data and the thunderstorm cloud movement path into a pre-established thunderstorm path prediction model to predict a future movement path of the thunderstorm cloud.

2. The method of claim 1, wherein, The lightning location data at least includes longitude, latitude, amplitude and type of lightning; and the weather radar data at least includes echo intensity, echo top height and vertical integrated liquid water.

3. The method of claim 1, wherein, The step of obtaining lightning location data and weather radar data within a lightning activity monitoring range and identifying thunderstorm clouds specifically comprises: unifying the format and time accuracy of the lightning location data and the weather radar data, and then aligning the time of the lightning location data and the weather radar data to complete data preprocessing; based on the preprocessed data, using a DBSCAN clustering algorithm to identify different clusters of thunderstorm clouds and number them.

4. The method of claim 1, wherein, The step of performing centroid calculation on the identified thunderstorm clouds to obtain a centroid calculation result specifically comprises: using a spatio-temporal joint weighting method to calculate the centroid in combination with spatial local density weight and time decay weight; wherein points with high spatial local density are given higher weight, and points occurring later in time are given higher weight; the centroid calculation formula of the thunderstorm cloud is: wherein, is the latitude of the weighted centroid of the thunderstorm cloud; is the longitude of the weighted centroid of the thunderstorm cloud; is the joint weight of the i th lightning record point of the thunderstorm cloud cluster; is the spatial density weight of each lightning record point; is the time decay weight of each lightning record point; is the time difference between the point and the latest record point in the cluster; N is the number of lightning record points in the thunderstorm cloud cluster; is the original latitude of the centroid of the thunderstorm cloud; is the original longitude of the centroid of the thunderstorm cloud.

5. The method of claim 1, wherein the method is characterized by: The step of determining a thunderstorm cloud movement path according to the centroid calculation result specifically comprises: using a spatio-temporal proximity algorithm to track the thunderstorm cloud centroid in different time windows for each cluster of thunderstorm clouds, connecting the centroid positions of each cluster of thunderstorm clouds in consecutive time windows to obtain the movement path of the thunderstorm cloud.

6. The method of claim 1, wherein, The ground meteorological data at least includes air pressure, wind direction, wind speed, temperature and relative humidity.

7. The method of claim 1, wherein the method is characterized by: The construction process of the thunderstorm path prediction model comprises: based on an ensemble learning model, inputting historical thunderstorm cloud centroid position data and ground meteorological data into the ensemble learning model for training to obtain a thunderstorm path prediction model.

8. A long-range thunderstorm activity path movement prediction system characterized by, It comprises: a thunderstorm cloud identification module for obtaining lightning location data and weather radar data within a lightning activity monitoring range and identifying thunderstorm clouds; a centroid calculation module for performing centroid calculation on the identified thunderstorm clouds to obtain a centroid calculation result; a movement path determination module for determining a thunderstorm cloud movement path according to the centroid calculation result; a prediction module for obtaining ground meteorological data, inputting the ground meteorological data and the thunderstorm cloud movement path into a pre-established thunderstorm path prediction model to predict a future movement path of the thunderstorm cloud.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the long-distance thunderstorm activity path movement prediction method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is executed by the processor to realize the steps of the long-distance thunderstorm activity path movement prediction method according to any one of claims 1-7.

Images