Forest lightning fire intelligent monitoring and early warning method and related device

Abstract

The invention provides a forest lightning fire intelligent monitoring and early warning method and a related device, and relates to the field of meteorological observation. The electronic device obtains a lightning stroke position of a to-be-verified lightning stroke; wherein the to-be-verified lightning stroke represents the lightning stroke with the lightning stroke intensity lower than the intensity threshold value; obtaining ignition auxiliary factors of the lightning stroke position according to the lightning stroke position; wherein the ignition auxiliary factors represent non-thunder and lightning factors influencing the ignition probability; and determining the ignition risk of the lightning stroke position according to the ignition auxiliary factors. Therefore, after the ignition auxiliary factors are incorporated into the risk assessment system, the risk judgment does not only depend on the single index of lightning stroke intensity, but is combined with the multi-dimensional information for comprehensive analysis, so that the misjudgment rate is effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of meteorological observation, and more specifically, to an intelligent monitoring and early warning method for forest lightning fires and related devices. Background Art

[0002] In recent years, global climate change has led to frequent extreme weather events, and forest lightning fires have become one of the core disasters threatening ecological security. Currently, lightning fire monitoring mainly relies on a combination of satellite heat source detection and ground-based manual inspections. Although satellite technology can cover a wide area, it is limited by cloud cover and revisit cycles (usually 12-24 hours), resulting in a high rate of missed reports of smoldering fires and incipient fires. For example, relevant reports indicate that the missed report rate of satellite monitoring in complex terrain exceeds 40%. At the same time, traditional lightning location systems can only provide ground-to-ground lightning location information and cannot simultaneously obtain lightning energy parameters, resulting in the inability to distinguish between high-risk ignition lightning strikes and ordinary discharge events. The singleness of this data dimension makes it difficult for risk assessment models to accurately quantify the critical conditions for lightning ignition.

[0003] Therefore, the existing technical system has significant shortcomings in monitoring accuracy, risk assessment and emergency response, resulting in delayed fire detection and low prevention and control efficiency, and a breakthrough solution is urgently needed. Summary of the Invention

[0004] In order to overcome at least one of the deficiencies in the prior art, the present application provides a method and related apparatus for intelligent monitoring and early warning of forest lightning fires, specifically comprising:

[0005] In a first aspect, the present application provides a method for intelligent monitoring and early warning of forest lightning fires, the method comprising:

[0006] Obtaining a lightning strike location of a lightning strike to be verified, wherein the lightning strike to be verified represents a lightning strike with a lightning strike intensity lower than an intensity threshold;

[0007] Obtaining, according to the lightning strike location, a fire auxiliary factor at the lightning strike location, wherein the fire auxiliary factor represents a non-lightning factor that affects the probability of fire;

[0008] The fire risk at the lightning strike location is determined according to the fire auxiliary factors.

[0009] In a second aspect, the present application provides an intelligent monitoring and early warning device for forest lightning fires, the device comprising:

[0010] a lightning strike location module, configured to obtain a lightning strike location of a lightning strike to be verified, wherein the lightning strike to be verified represents a lightning strike with a lightning strike intensity lower than an intensity threshold;

[0011] an ignition factor module, configured to obtain an ignition auxiliary factor at the lightning strike location according to the lightning strike location, wherein the ignition auxiliary factor represents a non-lightning factor that affects the probability of ignition;

[0012] The risk assessment module is used to determine the fire risk of the lightning strike location based on the fire auxiliary factors.

[0013] In a third aspect, the present application provides a storage medium storing a computer program, which implements the intelligent monitoring and early warning method for forest lightning fires when the computer program is executed by a processor.

[0014] In a fourth aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements the intelligent monitoring and early warning method for forest lightning fires.

[0015] Compared with the prior art, this application has the following beneficial effects:

[0016] The present application provides an intelligent monitoring and early warning method for forest lightning fires and related devices. The electronic device obtains the location of a lightning strike to be verified; the lightning strike to be verified represents a lightning strike with an intensity below a threshold; based on the lightning strike location, an ignition auxiliary factor at the lightning strike location is obtained; the ignition auxiliary factor represents a non-lightning factor that affects the probability of ignition; and based on the ignition auxiliary factor, the ignition risk at the lightning strike location is determined. By incorporating the ignition auxiliary factor into the risk assessment system, risk assessment no longer relies solely on the single indicator of lightning strike intensity, but instead conducts a comprehensive analysis based on multi-dimensional information, effectively reducing the misjudgment rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 One of the flow charts of the intelligent monitoring and early warning method for forest lightning fires provided in the embodiment of the present application;

[0019] Figure 2 A schematic diagram of a single-station stereoscopic antenna array provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of lightning strike intensity provided in an embodiment of the present application;

[0021] Figure 4 This is a second flow chart of the intelligent monitoring and early warning method for forest lightning fires provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of the intelligent monitoring and early warning device for forest lightning fires provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] To make the purpose, technical solutions, and advantages of the embodiments of the present application (hereinafter referred to as the present embodiments) clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0027] In the description of this application, it should be noted that the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be understood as indicating or implying relative importance. In addition, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0028] Based on the above statement, as introduced in the background technology, the existing technology system has significant shortcomings in monitoring accuracy, risk assessment and emergency response, resulting in delayed fire detection and low prevention and control efficiency, and urgently needs a breakthrough solution.

[0029] Based on the discovery of the above technical problems, the following technical solutions are proposed after creative work to solve or improve the above problems. It should be noted that the defects existing in the solutions in the above prior art are the results obtained after practice and careful study. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of this application for the above problems below should be regarded as contributions to this application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0030] In view of this, this embodiment provides a method for intelligent monitoring and early warning of forest lightning fires. Figure 1 As shown, the method includes:

[0031] S1, obtaining the lightning strike position of the lightning strike to be verified.

[0032] The lightning strike to be verified refers to a lightning strike with an intensity lower than an intensity threshold.

[0033] S2, according to the lightning strike location, obtain the ignition auxiliary factor of the lightning strike location.

[0034] Among them, the auxiliary factors of fire represent the non-lightning factors that affect the probability of fire.

[0035] S3, determine the fire risk at the lightning strike location based on fire auxiliary factors.

[0036] In this way, after incorporating fire auxiliary factors into the risk assessment system, risk judgment no longer relies solely on the single indicator of lightning strike intensity, but instead conducts a comprehensive analysis based on multi-dimensional information, thereby effectively reducing the misjudgment rate.

[0037] In this embodiment, the electronic device for implementing the intelligent monitoring and early warning method for forest lightning fires may be, but is not limited to, a mobile terminal, a computer, and a server, etc. Among them, the computer may be, but is not limited to, a tablet computer, a laptop computer, and a desktop computer. The server may be a single server or a server group. The server group may be centralized or distributed (for example, the server may be a distributed system). In some embodiments, the server may be local or remote relative to the user terminal. In some embodiments, the server may be implemented on a cloud platform; as an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (Community Cloud), a distributed cloud, an inter-cloud (Inter-Cloud), a multi-cloud (Multi-Cloud), etc., or any combination thereof. In some embodiments, the server may be implemented on an electronic device having one or more components.

[0038] In order to make the solution provided by this embodiment clearer, the following uses a server as an electronic device to implement the method. Figure 1 Each step of the method shown is described in detail. However, it should be understood that the operations of the flowchart can be implemented in any order, and steps that have no logical contextual relationship can be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of this application. Figure 1 As shown, the method includes:

[0039] S1, obtaining the lightning strike position of the lightning strike to be verified.

[0040] In this embodiment, the server can use a single-station stereoscopic antenna array to perform three-dimensional positioning of lightning. Figure 2 As shown, this single-station stereoscopic antenna array contains seven very high frequency (VHF) antennas, arranged in a three-dimensional configuration according to specific requirements, forming an ultra-short baseline interferometer array. This design fully utilizes the systematic error distribution characteristics of different antenna combinations, allowing systematic errors to be internally offset, thereby achieving high-precision single-station three-dimensional positioning. Using this single-station stereoscopic antenna array, the server can reconstruct the three-dimensional spatial coordinates of the lightning channel, including longitude, latitude, and altitude information, to accurately locate the lightning strike location.

[0041] It's important to note that compared to traditional multi-station systems, this single-station design eliminates the need for multi-station clock synchronization and complex data transmission mechanisms, significantly reducing hardware costs. It also allows for flexible deployment in complex terrains such as mountainous and forested areas. To further improve positioning efficiency, a GPU parallel computing architecture and streaming data processing framework were introduced, significantly reducing signal processing time to minutes, enabling real-time output of lightning locations.

[0042] Furthermore, it should be understood that a high lightning strike intensity indicates a high risk of fire. For such a strike with a distinct energy signature, it is easy to determine whether a fire will occur. Therefore, this embodiment focuses on strikes with average intensity, meaning that the "unverified" strikes represent strikes with an intensity below the intensity threshold. The determination of whether a "unverified" strike will cause a fire requires consideration of various environmental factors. To this end, this embodiment evaluates the lightning strike intensity based on two dimensions: the peak return current and the duration of the strike, with corresponding thresholds set for each.

[0043] In order to synchronously obtain the lightning strike intensity, the server can use the fast electric field change measuring instrument (dE / dt sensor) integrated at the same site of the single-station stereoscopic antenna array to measure the lightning strike intensity. It should be noted that this instrument records the electric field waveform of the lightning return stroke with microsecond resolution and aligns the electric field waveform with the timing through Beidou / GPS high-precision time synchronization (error ≤ 20 nanoseconds). Figure 3As shown, the server inverts the peak return current (Ipeak) and the duration of the long continuous current (T_LCC) based on the collected data. This not only accurately locates the three-dimensional spatial trajectory of lightning, but also quantifies its ignition potential. For example, lightning strikes with Ipeak ≥ 50kA and T_LCC ≥ 40ms are considered high-risk lightning strikes, while lightning strikes with 30kA ≤ Ipeak < 50kA or 20ms ≤ T_LCC < 40ms are considered pending lightning strikes.

[0044] Based on the description of step S1 in the above embodiment, the following is Figure 1 Explanation of step S2 in FIG.

[0045] S2, according to the lightning strike location, obtain the ignition auxiliary factor of the lightning strike location.

[0046] Among them, the fire-assisting factors represent non-lightning factors that affect the probability of fire. In this embodiment, the fire-assisting factors include the environmental fire risk index and the fire risk suppression index. The environmental fire risk index is used to assess the ease of inducing fire, while the fire risk suppression index is used to assess the difficulty of ignition. Therefore, these two factors jointly determine whether a fire will occur. In view of this, this embodiment provides the following optional implementation of step S2:

[0047] S2-1, obtain the vegetation dryness, combustible moisture content and slope coefficient at the lightning strike location.

[0048] It should be understood that although satellite remote sensing technology can provide large-scale, periodic observation data, in actual application, it is difficult to obtain complete remote sensing information of the target area due to cloud cover and revisit period limitations. Specifically, satellite remote sensing relies on clear sky conditions for data collection, and areas prone to forest lightning fires are usually accompanied by complex weather conditions, such as cloud cover or rainfall processes. These factors can significantly interfere with the satellite's direct observation of the surface. For example, when the cloud layer is thick, the satellite cannot penetrate the cloud layer to obtain key parameters of the surface vegetation status, such as the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST), resulting in data loss.

[0049] In view of this, this embodiment also provides the following optional implementation of step S2-1:

[0050] S2-1-1, divide the target area where the lightning strike location belongs into multiple sub-areas.

[0051] It should be understood that this division operation can provide a spatial basic unit for environmental information assessment in the target area. By dividing the target area into multiple sub-areas, it can ensure that the subsequent analysis of vegetation dryness can reflect local differences more finely.

[0052] S2-1-2, obtaining first environmental information of multiple sub-areas based on the remote sensing image of the target area.

[0053] In this embodiment, the server can use the periodic observation data provided by satellite remote sensing technology (such as Landsat-8 and Sentinel-2) to invert and obtain the first environmental information of multiple sub-regions. The first environmental information here specifically includes parameters such as the Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST), and surface soil moisture. These data have the advantage of wide coverage and can reveal the overall state of vegetation and macro-thermal environment characteristics in the target area. For example, the combination of a decrease in NDVI and an increase in LST can mark potential drought areas. However, it should be pointed out that since satellite data is subject to cloud cover and revisit period limitations (about once every 5 days), its timeliness and spatial continuity may not fully meet the real-time warning needs.

[0054] S2-1-3, interpolating the discrete environmental information measured by sensors deployed in the target area to obtain second environmental information of multiple sub-areas.

[0055] To compensate for the lack of satellite data, this implementation also incorporates a ground-based IoT node network. Temperature and humidity sensors (e.g., SHT45, with an accuracy of ±1.5% RH), combustible moisture content detectors (electrode method, with a range of 0-30%), and micro-meteorological stations are deployed in key forest areas. These sensors can collect local environmental parameters at a frequency of minutes and transmit them in real time via the LoRaWAN protocol.

[0056] For spatially discrete data collected by sensors, the server can use Kriging interpolation to spatialize the discrete environmental information measured by ground sensors, generating secondary environmental information for multiple subregions. This effectively fills the gaps in space and time between satellite observations and provides a high-resolution ground reference for subsequent data fusion.

[0057] S2-1-4, using the second environmental information of the multiple sub-areas to adjust the first environmental information of the multiple sub-areas to obtain environmental information of the multiple sub-areas.

[0058] In this step, the server uses a Kriging interpolation-machine learning hybrid algorithm to achieve deep fusion of the two types of data. Specifically, the server uses a random forest model to establish a nonlinear mapping relationship between satellite spectral characteristics (NDVI, LST, shortwave infrared bands) and ground-based measured data, and dynamically corrects the satellite inversion results. For example, when the satellite cannot obtain data in a certain area due to cloud interference, the model predicts the current ground environmental information based on the spectral characteristics of the adjacent time period and real-time ground data, thereby ensuring the continuity and high confidence of the monitoring field. Therefore, the adjusted environmental information of multiple sub-regions combines the advantages of satellite remote sensing and ground sensor data, which can significantly improve the accuracy of vegetation dryness assessment.

[0059] S2-1-5, determining the target sub-area to which the lightning strike location belongs from multiple sub-areas.

[0060] In this embodiment, based on the previously generated multiple sub-region environmental information, the server combines the three-dimensional coordinate information of the lightning strike location to determine the specific target sub-region to which the lightning strike location belongs.

[0061] S2-1-6, based on the environmental information of the target sub-area, obtain the dryness of the vegetation at the lightning strike location.

[0062] Due to the environmental information of the target sub-area, the dryness of vegetation at the lightning strike location can be obtained by multiplying NDVI and LST, taking into account factors such as NDVI, LST, and moisture content of combustibles.

[0063] Based on the description of the method for obtaining vegetation dryness in step S2-1 in the above embodiment, step S2 further includes:

[0064] S2-3, integrate vegetation dryness, combustible moisture content and slope coefficient to obtain the environmental fire risk index.

[0065] It should be understood that the Environmental Fire Risk Index (EFI) is intended to comprehensively reflect the impact of the surface environment on the probability of lightning fires, and its calculation process relies on the quantification and weighting of multiple key factors.

[0066] During the above steps, the server first uses vegetation dryness as input data. Vegetation dryness, represented by the product of NDVI and LST, measures the overall health and dryness of vegetation within the target area. Declining NDVI and increasing LST typically indicate drier vegetation, effectively identifying potentially high-risk areas.

[0067] Secondly, the server further factors in the moisture content of combustible materials into its calculations. It's important to note that a moisture content of 15% or less is considered high-risk, indicating that surface vegetation or other combustible materials are highly flammable. Therefore, in the Environmental Fire Risk Index calculation formula, the moisture content of combustible materials is calculated as "1-moisture content," with the lower the moisture content, the greater its weight.

[0068] The server also considers terrain slope. In this embodiment, the slope coefficient is calculated by weighting the terrain slope. For example, when the slope is greater than 30°, the fire spreads significantly faster, and its fire risk value is automatically weighted by 20%. This weighting design fully considers the impact of terrain characteristics on fire spread behavior.

[0069] Based on the above description, the calculation formula of EFI is:

[0070] EFI = (1-moisture content) × slope coefficient × vegetation dryness

[0071] or

[0072] EFI = (moisture content - 1) × slope coefficient × vegetation dryness.

[0073] Finally, the server classifies the environmental fire risk level based on the calculated results. When EFI ≥ 8.0, it is marked as "Extremely High Environmental Risk," indicating that the area has a very high fire hazard; while when EFI < 3.0, it is judged as "Low Risk," indicating that the possibility of fire is low.

[0074] Based on the description of the environmental fire risk index in the above embodiment, the fire risk suppression index will be described below. In this embodiment, the fire risk suppression index is one of the first suppression index, the second suppression index, and the third suppression index, and these suppression indices correspond to different rainfall conditions.

[0075] It can be understood that the inhibitory effect of rainfall on lightning fires has obvious time-effectiveness differences. For example, the current heavy rainfall can effectively reduce the dryness of surface combustibles, thereby significantly suppressing the probability of fire; while rainfall in the future period may indirectly reduce the fire risk through a humid environment, but its actual effect depends on the intensity and time distribution of rainfall. In addition, historical rainfall will also affect the moisture content of surface combustibles, thereby changing the possibility of fire. Therefore, a method is needed to distinguish the different effects of current, future and historical rainfall on fire suppression, that is, step S2 also includes:

[0076] S2-4, obtain the current rainfall intensity at the lightning strike location.

[0077] During these steps, the server uses real-time radar inversion data to determine the current rainfall intensity at the lightning strike location. Rainfall intensity refers to the amount of precipitation per unit time (measured in millimeters per hour, mm / h). This intensity is calculated using dual-polarization radar technology to dynamically analyze the phase distribution and evolution of precipitation particles, combined with radar echo signals.

[0078] S2-5: If the current rainfall intensity is greater than the first intensity threshold, a first suppression index is obtained.

[0079] In this step, the server compares the current rainfall intensity with a first intensity threshold. It should be understood that the first intensity threshold is defined as 2 mm / h. If the current rainfall intensity exceeds this threshold, it is determined that the current rainfall has a significant suppressive effect on fire, and a first suppression index is directly output. For example, if radar inversion indicates that the current rainfall intensity at the lightning strike location reaches or exceeds 2 mm / h, the fire risk is reset to zero, indicating that the current rainfall is sufficient to suppress the occurrence of a fire.

[0080] S2-6: If the current rainfall intensity is less than or equal to the first intensity threshold, obtain the rainfall intensity of the lightning strike location in the future period.

[0081] If the current rainfall intensity is less than or equal to the first intensity threshold, the rainfall intensity of the lightning strike location in the future period is further obtained, and its prediction range usually covers the next 30 minutes. During the execution of the above steps, the server can combine lightning location data, dual-polarization radar observations, and Weather Research and Forecasting (WRF) numerical model extrapolation results to construct a three-dimensional motion model of the thunderstorm cloud body, thereby generating a moving path in the future period, and combining the rainfall intensity prediction value to determine whether there is a fire risk. Therefore, this embodiment also provides the following optional implementation of step S2-6:

[0082] S2-6-1, obtain the movement trajectory of thunderstorms in the future period.

[0083] Among them, the lightning strike to be verified is caused by a thunderstorm. It should be understood that as a severe convective weather phenomenon, the coverage of a thunderstorm is not fixed, but constantly moves and develops with the movement of the atmosphere. During the actual monitoring process, it was found that although most lightning strikes are located within the coverage of thunderstorms, there are also some lightning strikes that occur outside the range of thunderstorms. These lightning strikes outside the range of thunderstorms are usually special, especially in arid or rainy areas. Such lightning strikes are more likely to cause forest fires. This is because when a lightning strike occurs outside the coverage of a thunderstorm, there is a lack of the inhibitory effect of accompanying precipitation, making it easier for surface combustibles to be ignited.

[0084] However, it's worth noting that the path of a thunderstorm has a significant impact on the subsequent development of such a lightning strike. If a thunderstorm's path happens to pass through the lightning strike location, the subsequent precipitation may have the effect of extinguishing or suppressing the fire. Based on this observation, predicting the movement of thunderstorms becomes particularly important. Therefore, by accurately predicting the movement of a thunderstorm, it is possible to determine in advance whether the lightning strike point will be covered by subsequent precipitation, providing a more accurate basis for fire risk assessment.

[0085] For example, if it is predicted that the thunderstorm's movement path will not pass through the lightning strike point, the fire risk at the lightning strike point will increase significantly; conversely, if the thunderstorm's movement path does pass through the lightning strike point and is accompanied by effective precipitation, the fire risk will be greatly reduced or even zero.

[0086] Because thunderstorm motion significantly impacts future precipitation distribution and fire risk assessment, accurately predicting thunderstorm motion is crucial for achieving precise prevention and control. In studying thunderstorm movement patterns, it was discovered that the spatiotemporal distribution of lightning clusters in lightning location data reflects the macroscopic motion trends of the thunderstorm's convective core, providing fundamental information for its overall migration patterns. Dual-polarization radar observations are used to analyze the vertical structural evolution of particles such as hail and graupel within clouds, revealing details of microphysical changes within thunderstorm clouds. The WRF numerical model assimilates real-time atmospheric stratification data to simulate future wind fields and water vapor transport, providing dynamic atmospheric environment support for thunderstorm path prediction.

[0087] It's important to note that traditional radar extrapolation relies solely on historical echo movement trends, ignoring the interaction between microphysical changes within thunderstorm clouds and the atmospheric energy field, resulting in path prediction errors exceeding 10 kilometers. To overcome this limitation, this embodiment dynamically fuses the three types of data described above using an ensemble Kalman filter algorithm to generate a three-dimensional motion trajectory for thunderstorm clouds. This 3D trajectory not only incorporates path information but also encompasses the spatiotemporal distribution of precipitation, compressing the path prediction error to less than 1 kilometer with a temporal resolution of 5 minutes.

[0088] From the macroscopic motion trends reflected in lightning location data, to the microscopic structural changes revealed by dual-polarization radar observations, to the atmospheric dynamics simulated by the WRF model, each input provides critical support for predicting thunderstorm tracks. The server ensures high accuracy and timeliness of thunderstorm track predictions through dynamic fusion combined with the Kalman filter algorithm.

[0089] S2-6-2: If the motion trajectory passes through the lightning strike location, the rainfall intensity at the lightning strike location in the future period can be obtained based on the thunderstorm.

[0090] In this embodiment, as an optional implementation, the server may obtain the phase distribution of rainfall particles in a thunderstorm; and according to the phase distribution, a matching inversion model is selected to calculate the rainfall intensity.

[0091] It's important to note that accurately assessing lightning fire risk requires dynamic monitoring of the phase distribution and evolution of precipitation particles within thunderstorm clouds. This example utilizes dual-polarization radar technology to provide a detailed analysis of thunderstorm microstructure, providing a basis for predicting rainfall intensity.

[0092] Specifically, the server first uses a dual-polarization radar to transmit horizontally (H) and vertically (V) polarized electromagnetic waves, receives the echo signals of the two, and calculates polarization parameters such as differential reflectivity (called Zdr), differential phase (called Kdp), and correlation coefficient (called ρhv) to reveal the shape, size, and phase characteristics of precipitation particles.

[0093] It should be understood that different types of precipitation particles exhibit unique physical properties. For example, the Zdr value of spherical raindrops approaches 0dB, while hailstones are non-spherical due to the ice covering their surface, and their Zdr value is usually negative (-1 to 0dB). Graupel (soft hail) exhibits low ρhv (<0.90) and high Kdp (>2°·km) due to its porous internal structure. -1 Based on these physical characteristics, the server uses a fuzzy logic classification algorithm to construct a rule library for distinguishing the phases of hail, graupel, raindrops, and snowflakes, enabling real-time identification of particle types within clouds with a classification accuracy exceeding 90%.

[0094] After obtaining the phase distribution of rainfall particles in a thunderstorm, it is necessary to select appropriate inversion models for different phases of particles to calculate rainfall intensity. It should be noted that the "matching inversion models" here specifically include but are not limited to the following two types:

[0095] For liquid precipitation areas, the R(Zh,Zdr) relationship based on the Zdr correction is used (for example, R = 0.017·Zdr -0.77 ·Zh 0.63 ), the Zdr parameter is introduced to reduce the impact of large raindrop deformation on the estimation.

[0096] For solid precipitation (e.g. below the graupel melt layer), the Kdp-driven R(Kdp) model is used (e.g., R = 0.032·Kdp 0.89 ) to avoid the artificially high contribution of ice phase particles to the reflectivity factor Zh.

[0097] In this way, the targeted phase inversion strategy significantly improved the accuracy of precipitation intensity estimation, reducing the error from 3 mm·h of traditional single-polarization radar to 1. -1 Above reduced to 1.5 mm·h -1It can be understood that, through the above method, the server can select the most suitable inversion model for different phases of precipitation, thereby more accurately calculating the rainfall intensity at the lightning strike location in the future period.

[0098] Based on the description of the rainfall intensity in the future period in the above embodiment, step S2 further includes:

[0099] S2-7, if the rainfall intensity in the future period is greater than the second intensity threshold, a second suppression index is obtained.

[0100] For example, based on the physical mechanism that rainwater penetration can raise the moisture content of combustibles to above 20%, if effective precipitation (intensity ≥ 2mm / h and duration ≥ 15 minutes) is expected to occur at the lightning strike location in the next 10-30 minutes, the spread of the smoldering fire will be significantly suppressed, thereby triggering the risk downgrade logic. Specifically, the downgrade weight is dynamically adjusted according to the temporal and spatial proximity of the precipitation forecast. For example, if 3mm / h of precipitation is predicted in the next 10 minutes, the risk value is attenuated by 70%. If the predicted precipitation does not occur as expected (radar real-time inversion intensity < 1mm / h), the high-risk mark is immediately restored and an emergency response is initiated.

[0101] S2-8: If the rainfall intensity in the future period is less than or equal to the second intensity threshold, obtain the historical rainfall at the lightning strike location.

[0102] S2-9, if the historical rainfall is greater than the rainfall threshold, a third suppression index is obtained.

[0103] It can be understood that historical rainfall also affects the moisture content of surface combustibles, thereby changing the likelihood of fire. For example, if the rainfall in the past 24 hours is ≥5 mm, the third suppression index can be set to 0.5.

[0104] Based on the above description of the environmental fire risk index and the fire risk suppression index, the following will continue to Figure 1 Explanation of step S3 in the following example:

[0105] S3, determine the fire risk at the lightning strike location based on fire auxiliary factors.

[0106] In this embodiment, fire-supporting factors include, but are not limited to, an environmental fire risk index and a fire risk suppression index. The environmental fire risk index characterizes the effect of surface environmental conditions at the lightning strike location on fire ignition, while the fire risk suppression index reflects the effect of precipitation or other meteorological conditions on fire ignition. These two factors together determine the overall fire risk at the lightning strike location.

[0107] Specifically, the calculation of the environmental fire risk index is based on parameters such as vegetation dryness, combustible moisture content, and terrain slope at the lightning strike location. These parameters are obtained by fusing satellite remote sensing data and ground sensor measured data, and are integrated into a unified value through a specific algorithm. The fire risk suppression index is determined based on factors such as the current and future rainfall intensity and historical rainfall at the lightning strike location. For example, if there is effective precipitation at the current or future time period at the lightning strike location, the fire risk suppression index will be significantly reduced, thereby reducing the overall fire risk. As an optional implementation method, the product of the environmental fire risk index and the fire risk suppression index is used as the fire risk at the lightning strike location.

[0108] Research has found that the fire risk assessment of forest lightning fires is a complex process, and its results are affected by many factors, including lightning intensity, surface environmental conditions, and meteorological conditions. However, in practical applications, traditional risk assessment methods are often based on fixed rules or empirical formulas, which make it difficult to fully consider the nonlinear correlations between different factors and their dynamic changes. This may lead to insufficient accuracy of risk assessment results, which in turn affects the effectiveness of subsequent early warning and emergency response. In view of this, Figure 1 On the basis of Figure 4 As shown, the forest lightning fire intelligent monitoring and early warning method provided in this embodiment also includes:

[0109] S4, the lightning strike intensity and fire auxiliary factors are processed by the pre-trained correction model to obtain the risk correction factor.

[0110] In this embodiment, the lightning strike intensity includes the return current peak value and the long continuous current duration; the fire auxiliary factors include the environmental fire risk index, precipitation probability, historical fire point density, and vegetation type code (for example, coniferous forest or broad-leaved forest).

[0111] The server invokes a correction model to comprehensively analyze this data, learning the nonlinear relationships between different factors and outputting a risk correction factor ranging from 0.8 to 1.2. This factor reflects the extent to which the machine learning model has adjusted the original fire risk assessment. For example, a risk correction factor close to 1.0 indicates that the correction model considers the original assessment to be reasonable; however, a risk correction factor deviating from 1.0 indicates that a more significant correction is needed to reflect the actual situation.

[0112] In addition, to ensure that the output results of the correction model conform to the laws of physics, this embodiment introduces a physical constraint mechanism. It should be noted that the "physical constraint" here refers to limiting the range of the risk correction coefficient output by the model under specific conditions to avoid results that violate the physical mechanism of fire. For example, when the environmental fire risk index is less than 3, the correction model is prohibited from outputting high-risk results. This is because according to the physical mechanism of fire, a lower environmental fire risk index generally means a lower probability of fire, and even if the lightning strike intensity is high, it should not be assessed as a high-risk area.

[0113] S5, adjusting the fire risk using the risk correction factor to obtain an optimized fire risk.

[0114] Specifically, the adjustment process is achieved by multiplying the fire risk by a risk correction factor, so that the resulting optimized fire risk more accurately reflects the actual situation. For example, when the risk correction factor is close to 1.0, the difference between the optimized fire risk and the initial assessment result is small; however, when the risk correction factor deviates from 1.0, it indicates that a significant adjustment to the initial assessment result is necessary.

[0115] The hybrid architecture based on a pure physics-based rule model and a pure AI model provided in this embodiment balances the physical interpretability with the flexibility of a data-driven model. By comparison, the AUC value of the pure physics-based rule model is 0.75, the pure AI model is 0.85, and the hybrid architecture of this embodiment reaches 0.93, demonstrating its clear advantages in accuracy and reliability. The AUC value here refers to the comprehensive performance indicator of the model in distinguishing high-risk from low-risk events.

[0116] In summary, the above embodiments can be used to determine the risk of a forest fire caused by a lightning strike to be verified, thereby providing strong data support for assessing the fire situation.

[0117] Furthermore, it's important to note that forest lightning fire risk assessment isn't a static process; it continuously adjusts as environmental conditions rapidly change. To address this need, this embodiment also provides a minute-by-minute iterative update mechanism that uses high-frequency data streams to drive model recalculations, thereby promptly capturing changing risk trends.

[0118] Specifically, the server can receive the latest data streams from single-station stereoscopic antenna arrays, dual-polarization radars, and ground sensors every minute. These data streams cover multi-source information such as lightning location and energy parameters, three-dimensional motion trajectory of thunderstorm clouds and precipitation forecasts, as well as surface vegetation dryness, moisture content of combustibles, and terrain characteristics.

[0119] After receiving this data, the server reassesses the fire risk at each lightning strike point. It's important to note that this reassessment involves more than just updating data in a single dimension; it also considers the dynamic interactions between these dimensions. For example, if the precipitation forecast for a particular area changes, the model automatically adjusts the fire suppression index for that area, thereby impacting the overall risk assessment.

[0120] This demonstrates that through its minute-by-minute high-frequency update mechanism, the server can effectively handle complex scenarios such as rapidly evolving thunderstorm clouds and rapidly changing surface environments, significantly improving the accuracy and timeliness of risk assessments. If the fire risk in an area exceeds 0.8 for three consecutive iterations, it indicates an extremely high fire risk and is immediately marked as "extremely high risk," initiating appropriate emergency response measures. This setting ensures the rapid identification and handling of high-risk incidents.

[0121] In actual application, this embodiment divides the obtained fire risk into four levels, and takes corresponding response measures for different levels.

[0122] For low-risk areas (risk values ​​ranging from 0 to 0.3), the server only logs the information and does not trigger any alarms. Furthermore, the server triggers a monitoring enhancement mechanism, automatically mobilizing surrounding surveillance cameras to focus on the target area, increasing the image acquisition frequency to 1 frame per second, and activating an AI-powered fire and smoke recognition algorithm (based on the YOLOv7 framework) to analyze the video stream in real time for abnormal smoke or heat sources. This avoids unnecessary interference while preserving the data records required for subsequent analysis.

[0123] For medium-risk areas (risk values ​​ranging from 0.3 to 0.6), the server will push notifications to rangers' handheld devices and recommend manual inspections. Specifically, rangers can use the terminal to obtain detailed information such as the lightning strike location, surrounding environmental parameters, and navigation paths, allowing them to quickly locate and verify potential risk points.

[0124] For high-risk areas (risk value range is 0.6 to 0.8), the server automatically dispatches drones to conduct infrared scanning of the target area with a resolution of up to 0.1°C, which can identify smoldering fire spots with abnormal surface temperatures; then, the scanning results are transmitted back to the command center in real time to support further decision-making.

[0125] For extremely high-risk areas (risk values ​​greater than 0.8), the server coordinates emergency pre-positioning of firefighting resources. For example, the server calculates the optimal standby airspace for firefighting helicopters based on the predicted fire location and wind direction. Ground firefighting teams maneuver to the assembly point using dynamic routing, and a digital fire scene simulation engine is used to generate a plan for excavating containment zones. This demonstrates that through this tiered early warning mechanism, the server can flexibly adjust response strategies in different risk scenarios, thereby minimizing disaster losses.

[0126] Furthermore, the server presents the latest risk assessment results as heat maps via the GIS platform, allowing for simultaneous updates on ranger terminals and the command center's large screen. This real-time visualization not only facilitates frontline personnel's understanding of the situation but also provides decision-makers with a global perspective, enabling more efficient resource scheduling and prevention and control management.

[0127] It should be understood that traditional forest fire risk assessment models usually rely only on static environmental parameters and cannot adapt to real-time changing meteorological conditions and surface fire risk conditions. In contrast, the present invention realizes dynamic adjustment of lightning fire risk by constructing an "energy-environment-meteorology" multi-physics field coupling model. Specifically, the server not only takes into account the lightning ignition potential (such as return current peak and long continuous current duration), but also introduces dynamic factors such as real-time precipitation forecast and surface combustible state, and achieves minute-level updates through a hybrid architecture of physical rules and machine learning.

[0128] After actual testing, real-time precipitation prediction and dynamic adjustment of energy thresholds significantly reduced the false alarm rate. For example, under the same conditions, the traditional model had a false alarm rate of up to 45%, while the present invention reduced it to 12%. This is primarily due to the server's ability to accurately distinguish between "ineffective precipitation" and "effective precipitation." For example, if a lightning strike point is located in an area with no or low-intensity precipitation, the server automatically increases its risk level; conversely, if accompanied by heavy precipitation, the risk downgrade logic is triggered.

[0129] Based on the same inventive concept as the forest lightning fire intelligent method provided in this embodiment, this embodiment also provides a forest lightning fire intelligent monitoring and early warning device, which includes at least one software function module that can be stored in a memory or solidified in an electronic device in the form of software. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software function module and computer program included in the device. Please refer to Figure 5 Functionally, the device can include:

[0130] A lightning strike location module 11 is configured to obtain a lightning strike location of a lightning strike to be verified, wherein the lightning strike to be verified refers to a lightning strike with a lightning strike intensity lower than an intensity threshold;

[0131] An ignition factor module 12 is configured to obtain an ignition auxiliary factor at the lightning strike location based on the lightning strike location, wherein the ignition auxiliary factor represents a non-lightning factor that affects the probability of ignition;

[0132] The risk assessment module 13 is used to determine the fire risk at the lightning strike location based on fire auxiliary factors.

[0133] In this embodiment, the lightning strike location module 11 is used to implement Figure 1 In step S1, the ignition factor module 12 is used to implement Figure 1 In step S2, the risk assessment module 13 is used to implement Figure 1 Therefore, for a detailed description of each of the above modules, please refer to the specific implementation of the corresponding step.

[0134] Since the method for intelligent monitoring and early warning of forest lightning fires provided in this embodiment has the same inventive concept, the intelligent monitoring and early warning device for forest lightning fires provided in this embodiment can also implement other steps or sub-steps of the method through the above modules.

[0135] Optionally, the risk assessment module 13 is further configured to:

[0136] The risk correction factor is obtained by processing the lightning strike intensity and fire auxiliary factors through the pre-trained correction model;

[0137] The fire risk is adjusted using the risk correction factor to obtain the optimized fire risk.

[0138] Optionally, the auxiliary fire factor includes an environmental fire risk index, and the fire factor module 12 is further specifically configured to:

[0139] Obtain vegetation dryness, combustible moisture content, and slope coefficient at the lightning strike location;

[0140] The environmental fire risk index is obtained by integrating vegetation dryness, combustible moisture content and slope coefficient.

[0141] Optionally, the ignition factor module 12 is further configured to:

[0142] Divide the target area where the lightning strike location belongs into multiple sub-areas;

[0143] Obtaining first environmental information of a plurality of sub-regions based on a remote sensing image of a target region;

[0144] Interpolating discrete environmental information measured by sensors deployed in the target area to obtain second environmental information of multiple sub-areas;

[0145] Adjusting the first environmental information of the plurality of sub-areas using the second environmental information of the plurality of sub-areas to obtain environmental information of the plurality of sub-areas;

[0146] determining a target sub-region to which a lightning strike position belongs from among the multiple sub-regions;

[0147] According to the environmental information of the target sub-area, the dryness of the vegetation at the lightning strike location is obtained.

[0148] Optionally, the auxiliary fire factor includes a fire risk suppression index, which is one of a first suppression index, a second suppression index, and a third suppression index. The fire factor module 12 is further specifically configured to:

[0149] Get the current rainfall intensity at the lightning strike location;

[0150] If the current rainfall intensity is greater than the first intensity threshold, a first suppression index is obtained;

[0151] If the current rainfall intensity is less than or equal to the first intensity threshold, obtaining the rainfall intensity of the lightning strike location in the future period;

[0152] If the rainfall intensity in the future period is greater than the second intensity threshold, a second suppression index is obtained;

[0153] If the rainfall intensity in the future period is less than or equal to the second intensity threshold, obtaining the historical rainfall at the lightning strike location;

[0154] If the historical rainfall is greater than the rainfall threshold, the third suppression index is obtained.

[0155] Optionally, the ignition factor module 12 is further configured to:

[0156] Obtaining the movement trajectory of the thunderstorm in the future period, wherein the lightning strike to be verified is generated by the thunderstorm;

[0157] If the motion trajectory passes through the lightning strike location, the rainfall intensity at the lightning strike location in the future period can be obtained based on the thunderstorm.

[0158] Optionally, the ignition factor module 12 is further configured to:

[0159] Obtain the phase distribution of rainfall particles in thunderstorms;

[0160] According to the phase distribution, the matching inversion model is selected to calculate the rainfall intensity.

[0161] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0162] It should also be understood that if the above embodiments are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application.

[0163] Therefore, this embodiment further provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, which, when executed by a processor, implements the intelligent forest lightning fire monitoring and early warning method provided in this embodiment. The storage medium can be any medium capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0164] This embodiment provides an electronic device for implementing an intelligent monitoring and early warning method for forest lightning fires. Figure 6 As shown, the electronic device may include a processor 22 and a memory 21. In addition, the memory 21 stores a computer program, and the processor implements the forest lightning fire intelligent monitoring and early warning method provided in this embodiment by reading and executing the computer program corresponding to the above embodiment in the memory 21.

[0165] Continue to see Figure 6 The electronic device further includes a communication unit 23. The memory 21, the processor 22 and the communication unit 23 are electrically connected to each other directly or indirectly via a system bus 24 to achieve data transmission or interaction.

[0166] The memory 21 may be an information recording device based on any electronic, magnetic, optical or other physical principles, for recording execution instructions, data, etc. In some embodiments, the memory 21 may be, but is not limited to, a volatile memory, a non-volatile memory, a storage drive, etc.

[0167] In some embodiments, the volatile memory may be a random access memory (RAM); in some embodiments, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, etc.; in some embodiments, the storage drive may be a magnetic disk drive, a solid-state drive, any type of storage disk (such as a CD, DVD, etc.), or a similar storage medium, or a combination thereof.

[0168] The communication unit 23 is used to send and receive data through a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service request processing system can connect to the network to exchange data and / or information.

[0169] The processor 22 may be an integrated circuit chip having signal processing capabilities, and the processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.

[0170] I understand. Figure 6 The structure shown is for reference only. Figure 6 More or fewer components than shown, or with Figure 6 Different configurations shown. Figure 6 The components shown may be implemented in hardware, software, or a combination thereof.

[0171] It should be understood that the devices and methods disclosed in the above embodiments may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented using a dedicated hardware-based system that performs a specified function or action, or may be implemented using a combination of dedicated hardware and computer instructions.

[0172] The above descriptions are merely examples of various embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for intelligent monitoring and early warning of forest lightning fires, characterized in that: The method comprises: Obtaining a lightning strike location of a lightning strike to be verified, wherein the lightning strike to be verified represents a lightning strike with a lightning strike intensity lower than an intensity threshold; Obtaining, according to the lightning strike location, a fire auxiliary factor at the lightning strike location, wherein the fire auxiliary factor represents a non-lightning factor that affects the probability of fire; The fire risk at the lightning strike location is determined according to the fire auxiliary factors.

2. The intelligent monitoring and early warning method for forest lightning fire according to claim 1 is characterized in that: The method further comprises: Processing the lightning strike intensity and the ignition auxiliary factors through a pre-trained correction model to obtain a risk correction factor; The fire risk is adjusted using the risk correction factor to obtain an optimized fire risk.

3. The intelligent monitoring and early warning method for forest lightning fire according to claim 1 is characterized in that: The fire auxiliary factor includes an environmental fire risk index. According to the lightning strike location, the environmental fire risk index of the lightning strike location is obtained, including: Obtaining vegetation dryness, combustible moisture content, and slope coefficient at the lightning strike location; The environmental fire risk index is obtained by integrating the vegetation dryness, the moisture content of the combustible material and the corresponding slope coefficient.

4. The intelligent monitoring and early warning method for forest lightning fire according to claim 3 is characterized in that: Obtaining the vegetation dryness at the lightning strike location, including: Dividing the target area to which the lightning strike location belongs into multiple sub-areas; obtaining first environmental information of the plurality of sub-areas based on the remote sensing image of the target area; interpolating discrete environmental information measured by sensors deployed in the target area to obtain second environmental information of the multiple sub-areas; Adjusting the first environmental information of the multiple sub-areas by using the second environmental information of the multiple sub-areas to obtain environmental information of the multiple sub-areas; determining a target sub-region to which the lightning strike position belongs from the multiple sub-regions; The dryness degree of vegetation at the lightning strike location is obtained according to the environmental information of the target sub-area.

5. The intelligent monitoring and early warning method for forest lightning fire according to claim 1 is characterized in that: The fire auxiliary factor includes a fire risk suppression index, which is one of a first suppression index, a second suppression index, and a third suppression index. The fire risk suppression index of the lightning strike location is obtained according to the lightning strike location, including: Obtaining the current rainfall intensity at the lightning strike location; If the current rainfall intensity is greater than a first intensity threshold, obtaining the first suppression index; If the current rainfall intensity is less than or equal to the first intensity threshold, obtaining the rainfall intensity at the lightning strike location in a future time period; If the rainfall intensity in the future period is greater than a second intensity threshold, obtaining the second suppression index; If the rainfall intensity in the future period is less than or equal to the second intensity threshold, obtaining the historical rainfall at the lightning strike location; If the historical rainfall is greater than the rainfall threshold, the third suppression index is obtained.

6. The intelligent monitoring and early warning method for forest lightning fire according to claim 5 is characterized in that: Obtaining the rainfall intensity at the lightning strike location in the future period, including: Obtaining a motion trajectory of a thunderstorm in the future period, wherein the lightning strike to be verified is generated by the thunderstorm; If the motion trajectory passes through the lightning strike location, the rainfall intensity of the lightning strike location in the future period is obtained according to the thunderstorm.

7. The intelligent monitoring and early warning method for forest lightning fire according to claim 6 is characterized in that: According to the thunderstorm, the rainfall intensity at the lightning strike location in a future period is obtained, including: Obtaining a phase distribution of rainfall particles in the thunderstorm; According to the phase distribution, a matching inversion model is selected to calculate the rainfall intensity.

8. An intelligent monitoring and early warning device for forest lightning fires, characterized in that: The device comprises: a lightning strike location module, configured to obtain a lightning strike location of a lightning strike to be verified, wherein the lightning strike to be verified represents a lightning strike with a lightning strike intensity lower than an intensity threshold; an ignition factor module, configured to obtain an ignition auxiliary factor at the lightning strike location according to the lightning strike location, wherein the ignition auxiliary factor represents a non-lightning factor that affects the probability of ignition; The risk assessment module is used to determine the fire risk of the lightning strike location based on the fire auxiliary factors.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligent monitoring and early warning of forest lightning fires according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory stores a computer program, and the computer program, when executed by the processor, implements the intelligent monitoring and early warning method for forest lightning fires according to any one of claims 1 to 7.

Images