A meteorological disaster early warning method and system based on meteorological early warning aircraft

Abstract

The present invention discloses a meteorological disaster early warning method and system based on a meteorological early warning aircraft, which relates to the technical field of heavy rain early warning. The area where heavy rain is to be predicted is divided into a number of sub-areas. The meteorological early warning aircraft predicts the sub-areas to obtain the expected rainfall, and calculates the probability of secondary disasters in the sub-areas; and judges whether secondary disasters occur in the sub-areas; collects the population density, groundwater level and sewer capacity of the sub-areas to construct a data set to obtain the affected value, and combines the expected rainfall in each sub-area and whether secondary disasters occur, determines the risk level of heavy rain impact in the sub-area, and issues a corresponding early warning through the meteorological early warning aircraft; can consider the impact of heavy rain and other possible secondary disasters caused by heavy rain, reduce the losses caused by disasters; and can make detailed considerations on the areas, ensure that low-risk areas will not be over-prevented, reduce resource waste, and at the same time, high-risk areas have sufficient emergency support and are not exposed to danger, thereby enhancing the overall protection effect.

Description

Technical Field

[0001] The present invention relates to the technical field of rainstorm warning, and in particular to a meteorological disaster warning method and system based on a meteorological early warning aircraft. Background Art

[0002] A meteorological early warning aircraft is a device used to collect and analyze atmospheric data. It can monitor and predict meteorological changes in real time. It combines radar, satellite, temperature, humidity, wind speed and other data to quickly identify conditions that may lead to extreme weather, such as typhoons, rainstorms, lightning, etc. Before the occurrence of potentially dangerous weather, through data analysis and model prediction, the meteorological early warning aircraft can issue early warning information to provide guidance for disaster prevention and mitigation for relevant departments and the public. In particular, in summer, when rainstorms are frequent, rainstorms can cause various impacts and affect residents' property and personal safety. Therefore, through the meteorological early warning aircraft, the city's rainstorms in the future can be predicted, and early warnings can be issued in a timely manner to notify residents and relevant departments to take preventive measures to reduce the impact of rainstorms.

[0003] However, when weather early warning aircraft issue heavy rain warnings for a certain area, they usually only focus on the intensity of the heavy rain and ignore the secondary disasters that may accompany it, such as landslides and mudslides. If only the impact of heavy rain is considered and other secondary disasters that may occur are ignored, it may lead to incomplete prevention measures and increase the losses caused by disasters. In addition, the heavy rain warning range of general weather early warning aircraft is usually large, lacking detailed consideration of the region; unified warnings may lead to excessive precautions and waste of resources in some low-risk areas, while high-risk areas may be exposed to danger due to insufficient prevention and emergency support, thereby weakening the overall protection effect. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and to provide a meteorological disaster warning method and system based on a meteorological early warning aircraft.

[0005] In a first aspect of the present invention, a meteorological disaster warning method based on a meteorological early warning aircraft is first proposed, the method comprising:

[0006] The area to be predicted for heavy rain is divided into several sub-areas, and the rainfall in each sub-area in a preset time period in the future is predicted by the meteorological early warning machine as the expected rainfall in each sub-area;

[0007] For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated in combination with the historical records of secondary disasters in the sub-region;

[0008] If the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster will occur in the corresponding sub-area;

[0009] The population density, groundwater level and sewer capacity of each sub-region are obtained and used as data points of the corresponding sub-region to obtain a data set, and the data set is clustered to determine the affected value of each sub-region;

[0010] The rainstorm impact risk level of each sub-region is determined based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and the rainstorm impact risk level of each sub-region is sent to the meteorological early warning aircraft for early warning.

[0011] Optionally, the steps of obtaining the number of mountains in the sub-region, the regional image, and calculating the probability of secondary disasters in the sub-region in combination with the historical records of secondary disasters in the sub-region are:

[0012] Get the number of mountains in the sub-area, and get the slope and volume of each mountain, determine the preset slope impact value and preset volume impact value of each mountain, and calculate the terrain impact value of the sub-area. The calculation formula is:

[0013] ;

[0014] In the formula, is the terrain influence value of the sub-region, is the number of mountains in the sub-region, is the order number of the mountain. Indicates Preset slope impact value of each mountain, For the Preset volume impact value of each mountain;

[0015] The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, regional image and historical records of secondary disasters in the sub-region.

[0016] Optionally, the step of calculating the probability of secondary disaster occurrence in the sub-region according to the terrain impact value of the sub-region, the regional image and the secondary disaster occurrence history record is:

[0017] Obtain satellite images of the sub-area, and extract near-infrared band pixel values ​​and red light band pixel values ​​of each pixel from the satellite images to obtain vegetation indexes of corresponding pixels;

[0018] The vegetation index of each pixel is compared with a preset vegetation index threshold. If the vegetation index is greater than the preset vegetation index threshold, the corresponding pixel is a vegetation pixel;

[0019] Calculate the mean vegetation index of all vegetation pixels as the vegetation impact value;

[0020] The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, vegetation impact value and historical record of secondary disasters in the sub-region.

[0021] Optionally, the step of calculating the probability of secondary disaster occurrence in the sub-region according to the terrain impact value, vegetation impact value and secondary disaster occurrence history record of the sub-region is:

[0022] According to historical records, the total number of rainstorms that occurred in the sub-area within a preset period in the past is obtained, and the number of secondary disasters that occurred after each rainstorm is obtained. The number of secondary disasters that occurred is divided by the total number of rainstorms to obtain the disaster triggering ratio;

[0023] The terrain impact value, vegetation impact value and disaster initiation ratio of the sub-region are normalized to obtain the probability of secondary disasters in the corresponding sub-region. The calculation formula is:

[0024] ;

[0025] In the formula, is the probability of secondary disasters, , , are the normalized terrain impact value, vegetation impact value and disaster initiation ratio, , , They are , , Preset scaling factor, and , , Both are greater than 0.

[0026] Optionally, the steps of obtaining the population density, groundwater level and sewer capacity of each sub-region as data points of the corresponding sub-region are:

[0027] Obtain the population density, building density and area of ​​the sub-region, and normalize the population density, building density and area to obtain the life impact;

[0028] Divide the sub-region into several sub-regions, obtain the groundwater level of each sub-region, calculate the distance between the groundwater level of each sub-region and the corresponding surface, calculate the mean of the distances between the groundwater level of all sub-regions and the corresponding surface, and take the reciprocal of the mean as the groundwater level impact degree;

[0029] Obtain the capacity of each sewer in the sub-area, calculate the mean capacity of the sewer, and use the inverse of the mean as the sewer capacity impact;

[0030] The life impact, groundwater level impact, and sewer capacity impact of the sub-region are taken as the data points of the corresponding sub-region.

[0031] Optionally, the step of clustering the data set to determine the affected value of each sub-region is:

[0032] The steps to cluster the data set according to the K-means clustering method are as follows:

[0033] Step 1: Use the elbow method to determine the optimal number of clusters K for the data set;

[0034] Step 2: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center, traverse the K initial cluster centers, and assign it to the cluster corresponding to the nearest initial cluster center;

[0035] Step 3: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center.

[0036] Step 4: Repeat steps 2 and 3 until the cluster center no longer changes, and obtain the final cluster and the final cluster center;

[0037] The final clusters and the final cluster centers are mapped to three-dimensional coordinates to obtain the affected values ​​of each sub-region.

[0038] Optionally, the final clusters and the final cluster centers are mapped to three-dimensional coordinates to obtain the affected values ​​of each sub-region including:

[0039] Calculate the weight coefficient of each final cluster, the calculation formula is: ,in Expressed as The weight coefficients of the final clusters, Represented as the number of all data points in the dataset, Indicates The number of data points in the final clusters;

[0040] Calculate the distance of each data point in each final cluster to the coordinate origin in three-dimensional coordinates to obtain the preliminary coordinate distance of the data point, and multiply the preliminary coordinate distance of the data point by the weight coefficient corresponding to the final cluster in which the data point is located to obtain the actual coordinate distance of the data point;

[0041] The actual coordinate distance of each data point is taken as the affected value of the corresponding sub-area.

[0042] Optionally, determining the rainstorm impact risk level of each sub-region according to the affected value of each sub-region, the expected rainfall, and whether a secondary disaster occurs in the corresponding sub-region includes:

[0043] If no secondary disaster occurs in the sub-region, the sub-region's affected value and pending rainfall are normalized to obtain the rainstorm impact risk level coefficient;

[0044] Compare the rainstorm impact risk level coefficient of the sub-area with the preset rainstorm impact risk level coefficient stage threshold;

[0045] If the rainstorm risk level coefficient is less than the preset first threshold of the rainstorm risk level coefficient, the rainstorm risk level of the sub-area is recorded as a low risk level, and the meteorological early warning aircraft issues a low risk warning;

[0046] If the rainstorm impact risk level coefficient is not less than the preset first threshold value of the rainstorm impact risk level coefficient but less than the preset second threshold value of the rainstorm impact risk level coefficient, the rainstorm impact risk level of the sub-area is recorded as a medium risk level, and the meteorological early warning aircraft issues a medium risk warning;

[0047] If the rainstorm impact risk level coefficient is not less than the preset rainstorm impact risk level coefficient second threshold, the rainstorm impact risk level of the sub-area is recorded as a high risk level, and the meteorological early warning aircraft issues a high risk warning;

[0048] If a secondary disaster occurs in a sub-region, the rainstorm impact risk level of the sub-region will be directly recorded as a high-risk level, and the meteorological early warning aircraft will issue a high-risk warning and a special warning for the occurrence of secondary disasters at the same time.

[0049] In a second aspect of the present invention, a meteorological disaster warning system based on a meteorological early warning aircraft is proposed, the system comprising:

[0050] Prediction module: divide the area to be predicted for heavy rain into several sub-areas, and use the meteorological early warning machine to predict the rainfall in each sub-area in the preset time period in the future as the expected rainfall in each sub-area;

[0051] Disaster probability module: For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated based on the historical records of secondary disasters in the sub-region;

[0052] Judgment module: if the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster occurs in the corresponding sub-area;

[0053] Affected module: Obtain the population density, groundwater level and sewer capacity of each sub-region and use them as data points of the corresponding sub-region to obtain a data set, and cluster the data set to determine the affected value of each sub-region;

[0054] Early warning module: Determine the rainstorm risk level of each sub-region based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and send the rainstorm risk level of each sub-region to the meteorological early warning aircraft for early warning.

[0055] Beneficial effects of the present invention:

[0056] The present invention proposes a meteorological disaster warning method and system based on a meteorological early warning aircraft, which can take into account the impact of heavy rain and other possible secondary disasters caused by heavy rain, so that preventive measures are not comprehensive and the losses caused by disasters are reduced; and can make detailed considerations on regions to ensure that low-risk areas will not be over-prevented and reduce waste of resources. At the same time, high-risk areas have sufficient emergency support and are not exposed to danger, thereby enhancing the overall protection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 It is a flow chart of a meteorological disaster early warning method based on a meteorological early warning aircraft;

[0059] Figure 2 This is a framework diagram of a meteorological disaster warning system based on a meteorological early warning aircraft. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0062] The embodiment of the present invention provides a meteorological disaster warning method based on a meteorological early warning aircraft. Figure 1 , Figure 1 A flow chart of a meteorological disaster warning method based on a meteorological early warning aircraft provided in an embodiment of the present invention. The method comprises the following steps:

[0063] The area to be predicted for heavy rain is divided into several sub-areas, and the rainfall in each sub-area in a preset time period in the future is predicted by the meteorological early warning machine as the expected rainfall in each sub-area;

[0064] For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated in combination with the historical records of secondary disasters in the sub-region;

[0065] If the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster will occur in the corresponding sub-area;

[0066] The population density, groundwater level and sewer capacity of each sub-region are obtained and used as data points of the corresponding sub-region to obtain a data set, and the data set is clustered to determine the affected value of each sub-region;

[0067] The rainstorm impact risk level of each sub-region is determined based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and the rainstorm impact risk level of each sub-region is sent to the meteorological early warning aircraft for early warning.

[0068] Based on the meteorological disaster warning method based on the meteorological early warning aircraft provided by the embodiment of the present invention, through the above-mentioned method, the impact of heavy rain and other possible secondary disasters caused by heavy rain can be taken into account, so that the prevention measures are comprehensive enough to reduce the losses caused by disasters; and the regions can be considered in detail to ensure that low-risk areas will not be over-prevented and reduce waste of resources. At the same time, high-risk areas have sufficient emergency support and are not exposed to danger, thereby enhancing the overall protection effect.

[0069] It should be noted that the division of the area to be predicted for heavy rain into several sub-areas may include zoning by geographical location, administrative division, terrain features or functional areas, etc. For example, a city can be divided into different administrative areas (such as districts, streets, communities) or divided according to terrain features (such as mountains, plains, river banks, etc.), which can better reflect the meteorological characteristics, rainfall conditions and differences in the impact of heavy rain in different regions; the specific division method is determined by professionals according to the actual situation and is not limited or elaborated.

[0070] In one embodiment, the prediction of the rainfall in a sub-region in a preset time period in the future by a meteorological early warning aircraft is usually achieved by combining multi-source data and numerical weather forecast models; first, the meteorological early warning aircraft receives real-time observation data from radars, satellites, and ground stations to obtain information such as the current precipitation conditions, cloud distribution, humidity, wind speed, etc. in the area; then, the internally stored numerical weather forecast models, such as global and regional high-resolution meteorological models, are used to predict the trend of atmospheric changes in the future through complex physical and dynamic calculations; the model combines historical meteorological data and machine learning algorithms to estimate the rainfall intensity and duration of the sub-region, and generates the expected distribution of future rainfall, thereby obtaining the predicted rainfall; the meteorological early warning aircraft combines these models and observation data to ultimately determine the rainfall in each sub-region in the preset time period in the future as the waiting rainfall, which serves as the basis for early warning. At present, the prediction of rainfall in a certain area belongs to mature existing technologies, which will not be elaborated or limited here; in addition, the preset time period is set by professionals according to actual conditions, which will not be limited or detailed here.

[0071] In one embodiment, the steps of obtaining the number of mountains in the sub-region, the regional image, and calculating the probability of secondary disasters in the sub-region in combination with the secondary disaster occurrence history records of the sub-region are:

[0072] Get the number of mountains in the sub-area, and get the slope and volume of each mountain, determine the preset slope impact value and preset volume impact value of each mountain, and calculate the terrain impact value of the sub-area. The calculation formula is:

[0073] ;

[0074] In the formula, is the terrain influence value of the sub-region, is the number of mountains in the sub-region, is the order number of the mountain. Indicates Preset slope impact value of each mountain, For the Preset volume impact value of each mountain;

[0075] The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, regional image and historical records of secondary disasters in the sub-region.

[0076] It should be noted that the terrain of the sub-region can be analyzed through remote sensing image data (such as satellite images) and digital elevation models (DEM), and the number of mountains can be identified by using terrain undulations; the boundaries of the mountains can be determined through image segmentation technology or slope analysis based on DEM, and then the number of mountains can be calculated; the slope of each mountain is usually provided by a digital elevation model (DEM), based on the elevation data of the mountain, by calculating the inclination angle of the mountain surface on the horizontal plane. The slope calculation formula is: ,in, is the slope of the mountain, is the elevation change, is the horizontal distance; the volume of the mountain can be estimated through DEM data and the area of ​​the mountain; by modeling the geometric model of the mountain, the total volume of the mountain is calculated according to its surface height and bottom area; the commonly used method is to estimate through three-dimensional volume integration or based on the trapezoidal rule.

[0077] The preset slope impact value is set by professionals based on actual conditions and is used to quantify the risk of secondary disasters (such as landslides and mud-rock flows) occurring in mountains with different slope ranges. Mountains with larger slopes are usually given higher impact values. The specific values ​​are determined based on actual conditions and are not limited or elaborated on.

[0078] The preset volume impact value is also set by professionals based on actual conditions, reflecting the impact of mountain volume on the occurrence of secondary disasters. Usually, larger mountains are given higher impact values. The specific values ​​are determined based on actual conditions and are not limited or elaborated.

[0079] It should be noted that the greater the terrain impact value of a sub-region, the more likely it is that the sub-region will be at risk of secondary disasters (such as landslides and mud-rock flows) caused by heavy rains, because the greater the terrain impact value, the steeper the terrain slope, the more fragile the mountain structure or the more susceptible to heavy rain erosion in the region, which increases the risk of secondary disasters (such as landslides and mud-rock flows). Especially under heavy rain weather conditions, overly steep slopes or loose soils are more likely to become unstable due to precipitation, leading to disasters such as landslides or mud-rock flows, which in turn exacerbates the disaster risk in the region.

[0080] In one embodiment, the steps of calculating the probability of secondary disasters occurring in a sub-region according to the terrain impact value of the sub-region, the regional image and the secondary disaster occurrence history record are:

[0081] Obtain satellite images of the sub-area, extract the near-infrared band pixel value and red light band pixel value of each pixel from the satellite image, and obtain the vegetation index of the corresponding pixel , the calculation formula is: ; In the formula, and They are the pixel values ​​of near infrared band and red light band respectively;

[0082] The vegetation index of each pixel is compared with a preset vegetation index threshold. If the vegetation index is greater than the preset vegetation index threshold, the corresponding pixel is a vegetation pixel;

[0083] Calculate the mean vegetation index of all vegetation pixels as the vegetation impact value;

[0084] The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, vegetation impact value and historical record of secondary disasters in the sub-region.

[0085] It should be noted that the corresponding satellite images of the sub-area can be downloaded through remote sensing platforms (such as NASA Earthdata, Sentinel Hub, etc.), and the corresponding values ​​of each band, especially the pixel values ​​of red light and the pixel values ​​of the near-infrared band, can be obtained through the metadata of the satellite images; other acquisition methods may also be used, which are not limited or elaborated on; in addition, the preset vegetation index threshold is usually set by professionals according to actual conditions. For example, the preset vegetation index threshold can be set to 0.2, and vegetation indices greater than 0.2 can be judged as vegetation pixels; it can also be other numbers, which depend on the actual situation and are not limited or elaborated on.

[0086] It should be noted that the vegetation impact value of a sub-region indicates that the sub-region is less likely to be at risk of secondary disasters (such as landslides and mud-rock flows) caused by heavy rain, because a high vegetation impact value usually means that the vegetation coverage in the region is high, and the plant roots can effectively fix the soil and reduce soil and water loss. This vegetation coverage can greatly reduce the probability of disasters such as soil erosion, landslides and mud-rock flows caused by heavy rain; in addition, a high vegetation impact value usually also means that the vegetation in the area is relatively healthy and grows well. Healthy vegetation has stronger soil retention, can more effectively absorb and store precipitation, and slow down the erosion of precipitation on the surface; for example, forests or dense grasslands can reduce the scouring of water caused by heavy rain and avoid the loosening of mountains or the occurrence of mud-rock flows; while areas with low NDVI values ​​have a higher risk of disasters after heavy rain because the soil is more susceptible to erosion and collapse due to the lack of sufficient vegetation protection; therefore, the higher the vegetation impact value of a sub-region, the lower the risk of secondary disasters caused by heavy rain in the corresponding area.

[0087] In one embodiment, the steps of calculating the probability of secondary disaster occurrence in a sub-region according to the terrain impact value, vegetation impact value and secondary disaster occurrence history of the sub-region are:

[0088] According to historical records, the total number of rainstorms that occurred in the sub-area within a preset period in the past is obtained, and the number of secondary disasters that occurred after each rainstorm is obtained. The number of secondary disasters that occurred is divided by the total number of rainstorms to obtain the disaster triggering ratio;

[0089] The terrain impact value, vegetation impact value and disaster initiation ratio of the sub-region are normalized.

[0090] The probability of secondary disasters in the corresponding sub-region is obtained, and the calculation formula is:

[0091] ;

[0092] In the formula, is the probability of secondary disasters, , , are the normalized terrain impact value, vegetation impact value and disaster initiation ratio, , , They are , , Preset scaling factor, and , , Both are greater than 0.

[0093] It should be noted that , , It is set by professionals according to the actual situation. Generally, , , The sum of is 1, for example , , They can be 0.3, 0.3, 0.4 respectively, or other numbers, without specific limitation. In addition, commonly used normalization methods include Min-Max normalization, Z-Score standardization, etc. The specific method is selected by professionals according to the actual situation, and is not limited or elaborated on.

[0094] It should be noted that the preset period is set by professionals according to actual conditions, and no specific limitation or elaboration is made thereon; in addition, the total number of rainstorms that occurred in the past preset period, and the number of secondary disasters that occurred after each rainstorm, can be obtained through the disaster record database of the local relevant departments, or other acquisition methods, which are not limited or elaborated thereon;

[0095] It should be noted that the larger the disaster initiation ratio of a sub-region, the more likely the sub-region is to face the risk of secondary disasters (such as landslides and mud-rock flows) caused by heavy rains. This is because the larger the disaster initiation ratio of a sub-region, the higher the probability of secondary disasters occurring after each heavy rain. This indicates that the risk of secondary disasters in this region is more significant when heavy rains occur. A higher disaster initiation ratio implies that the natural conditions in the region may be more prone to unstable geological changes after heavy rains, further exacerbating the occurrence of disasters. Therefore, the disaster initiation ratio is an important indicator for assessing the risk of secondary disasters caused by heavy rains, and can provide a scientific basis for disaster warning, emergency response, and the formulation of disaster prevention and mitigation measures.

[0096] In one embodiment, the probability of a secondary disaster occurring in a sub-region is compared with a preset threshold value of the probability of a secondary disaster occurring. If the probability of a secondary disaster occurring is not less than the preset threshold value of the probability of a secondary disaster occurring, a secondary disaster occurs in the sub-region; if the probability of a secondary disaster occurring is less than the preset threshold value of the probability of a secondary disaster occurring, no secondary disaster occurs in the sub-region.

[0097] It should be noted that the preset secondary disaster probability threshold is set by professionals based on actual conditions and will not be limited or elaborated on in detail;

[0098] It should be noted that when the probability of secondary disasters in a sub-region is greater than or equal to the preset threshold of the probability of secondary disasters, it means that the risk of secondary disasters after heavy rain in the region is high, and landslides, mudslides and other disasters may occur. Therefore, corresponding early warning and prevention measures need to be taken to reduce disaster losses. On the contrary, when the probability of secondary disasters is less than the preset threshold, it means that the probability of disasters in the region is low, and conventional monitoring and prevention measures can be taken, but there is no need for excessive intervention. Through this threshold judgment method, areas with different risks can be effectively distinguished, thereby optimizing the allocation of resources and disaster response strategies. At the same time, the secondary disasters caused by heavy rain will not be ignored, ensuring that the prevention measures are not comprehensive enough to reduce the losses caused by disasters.

[0099] In one embodiment, the steps of obtaining the population density, groundwater level and sewer capacity of each sub-region as data points of the corresponding sub-region are:

[0100] The population density, building density and area of ​​the sub-region are obtained, and the population density, building density and area are normalized to obtain the life impact; the calculation formula is: , where For the impact on life, , , are the normalized population density, building density and regional area, , , They are , , The preset scaling factor of , , All are greater than 0;

[0101] It should be noted that , , It is set by professionals according to the actual situation. Generally, , , The sum of is 1, for example , , They can be 0.32, 0.35, 0.33, or other numbers, respectively, and are not specifically limited. In addition, commonly used normalization methods include Min-Max normalization, Z-Score standardization, etc. The specific method is selected by professionals according to the actual situation and is not specifically limited or elaborated.

[0102] Divide the sub-region into several sub-regions, obtain the groundwater level of each sub-region, calculate the distance between the groundwater level of each sub-region and the corresponding surface, calculate the mean of the distances between the groundwater level of all sub-regions and the corresponding surface, and take the reciprocal of the mean as the groundwater level impact degree;

[0103] Obtain the capacity of each sewer in the sub-area, calculate the mean capacity of the sewer, and use the inverse of the mean as the sewer capacity impact;

[0104] The impact on life, groundwater level and sewer capacity of the sub-region are taken as the data points of the sub-region.

[0105] It should be noted that population density and building density can be obtained through statistical yearbooks, urban planning data or GIS data, and regional area can be obtained directly from maps or regional division data; groundwater level data usually comes from groundwater monitoring wells or geological exploration data, and the distance between the groundwater level and the surface can be calculated through the coordinates and depth data of the groundwater monitoring points; sewer capacity is usually determined by pipeline network data provided by urban water conservancy or infrastructure management departments; it can also be obtained through other methods, depending on the actual situation, and is not limited or elaborated.

[0106] It should be noted that the greater the impact on life in a sub-region, the greater the impact on groundwater level, and the greater the impact on waterway capacity, the greater the impact of heavy rain on the sub-region. Correspondingly, the risk of heavy rain in the sub-region is greater, and the warning level will be higher, because these factors are directly related to the possible disaster consequences after heavy rain in the region; a high impact on life usually means dense population and concentrated buildings. Once a heavy rain occurs, the risk of casualties and property losses increases significantly; a high groundwater level impact indicates that the groundwater is close to the surface, and heavy rain may cause serious geological disasters such as landslides and mudslides; a high sewer capacity impact means weak drainage capacity, and serious urban waterlogging is prone to occur after heavy rain; taking all these factors into consideration, the sub-region has a greater risk of heavy rain, and the warning level will be increased accordingly to ensure that more urgent and comprehensive response measures are taken to reduce the potential losses caused by disasters.

[0107] It should be noted that when the impact on life, groundwater level and sewer capacity of the sub-region are taken as the data points of the sub-region and these three coefficients are taken as the characteristics of the sub-region, the data points of the sub-region can be expressed as a three-dimensional vector, namely [impact on life, impact on groundwater level, impact on sewer capacity], and the corresponding data points of all sub-regions form a data set.

[0108] In one embodiment, clustering the data set to determine the affected value of each sub-region includes:

[0109] The steps to cluster the data set according to the K-means clustering method are as follows:

[0110] Step 1: Use the elbow method to determine the optimal number of clusters K for the data set;

[0111] Step 2: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center, traverse the K initial cluster centers, and assign it to the cluster corresponding to the nearest initial cluster center;

[0112] Step 3: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center.

[0113] Step 4: Repeat steps 2 and 3 until the cluster center no longer changes, and obtain the final cluster and the final cluster center;

[0114] The final clusters and the final cluster centers are mapped to three-dimensional coordinates to obtain the affected values ​​of each sub-region.

[0115] In one implementation, according to the above method, the optimal clustering results of the data set can be obtained. These clustering results can be used to identify different clusters in the data set, as well as the center and characteristics of each cluster. Such clustering results are helpful for further data analysis and interpretation.

[0116] It should be noted that clustering the data set by K-means clustering is simple and efficient, and can quickly process large-scale data sets; K-means clustering is a commonly used unsupervised learning algorithm, which is used to divide the data set into pre-defined K clusters; the goal of this algorithm is to divide the data points into K clusters, so that each data point belongs to the cluster represented by the cluster center closest to it, and the data points within the cluster are as similar as possible, while the data points between different clusters may not be similar;

[0117] Cluster analysis can help evaluate the degree of impact of heavy rain on each sub-region; if the sub-region has a greater impact on life, a greater impact on groundwater level, and a greater impact on underground waterway capacity, it means that the sub-region is more affected by heavy rain, so the corresponding protection measures of the sub-region require more resources, and the heavy rain warning level is higher; conversely, it means that the corresponding protection measures of the sub-region require so many resources, and the heavy rain warning level is lower; In addition, in this case, the K-means clustering method can assign a corresponding "affected value" to each sub-region by classifying these devices into a cluster, and according to the center point of the cluster, each sub-region can be assigned a corresponding "affected value". These affected values ​​reflect the intensity of the impact of heavy rain on the region and help determine the risk level of the region. Through the K-means clustering method, after the sub-regions are divided into multiple risk level clusters, differentiated disaster prevention and mitigation measures can be taken for each cluster. For example, high-risk areas (i.e., areas with greater impact on life, groundwater level, and sewer capacity) will receive more emergency resources and early warning support, while low-risk areas can appropriately reduce resource input. Such clustering results can effectively improve the accuracy of disaster response, avoid excessive protection or waste of resources, and improve the efficiency and pertinence of overall disaster prevention and mitigation. Through this process, the K-means clustering method not only helps to identify potential threats brought by heavy rains, but also provides a clear basis for the formulation of various disaster responses.

[0118] In addition, the impact on life, groundwater level, and sewer capacity of the sub-area show a common linear relationship. The greater the impact on life, the greater the impact on groundwater level, and the greater the impact on sewer capacity, the greater the impact index of the corresponding sub-area affected by heavy rain.

[0119] Cluster the data set according to the K-means clustering method:

[0120] Step 1: Use the elbow method to determine the optimal number of clusters K for the data set; the elbow method is one of the common methods used to determine the optimal number of clusters K in K-means clustering. The basic idea is to find an "elbow point" by observing the relationship between the number of clusters K and the total internal deviation square sum (WCSS) of the clustering results. The K value corresponding to the "elbow point" is the position where the WCSS decreases significantly after the number of clusters increases to a certain extent. WCSS refers to the sum of the squares of the distances from each data point to the center of the cluster to which it belongs, which indicates the compactness of the clustering results.

[0121] Step 2: According to the optimal number of clusters K, randomly select K data points from the data points as the initial cluster centers of clustering. The initial cluster centers refer to the K cluster centers randomly selected before starting the clustering process. These initial cluster centers are the starting points when the algorithm starts.

[0122] Step 3: For each data point in the data set, calculate the distance between it and each initial cluster center using the Euclidean distance. For example, calculate the data point and the initial cluster centers The distance between , and its calculation formula is ,in, Represents data points In the The values ​​in the clusters, Represents the initial cluster center In the The value of the clusters, Represented as data points and the initial cluster centers The number of features is calculated, and the data points are assigned to the cluster to which the nearest cluster center belongs. Euclidean distance refers to the distance between two points in Euclidean space, and is also one of the most commonly used distance metrics. In K-means clustering, Euclidean distance is usually used to calculate the distance between data points and cluster centers.

[0123] Step 4: After traversing all data points, we get the initial clusters. For each initial cluster, we calculate the mean of the data points in it. The calculation formula is: ,in Expressed as The set of data points in a cluster, Expressed as The new cluster centers of the clusters;

[0124] Step 5: Repeat steps 3 and 4 until the cluster center no longer changes, and obtain the final cluster and the final cluster center.

[0125] It should be specifically explained that the step of assigning a data point to the cluster to which the nearest cluster center belongs is to sort the distances between the data point and each cluster center from large to small, and select the smallest distance to assign the data point to the cluster to which it belongs.

[0126] In one embodiment, the final clusters and the final cluster centers are mapped to three-dimensional coordinates to obtain the affected values ​​of each sub-region, including:

[0127] Calculate the weight coefficient of each final cluster, the calculation formula is: ,in Expressed as The weight coefficients of the final clusters, Represented as the number of all data points in the dataset, Indicates The number of data points in the final clusters;

[0128] Calculate the distance of each data point in each final cluster to the coordinate origin in three-dimensional coordinates to obtain the preliminary coordinate distance of the data point, and multiply the preliminary coordinate distance of the data point by the weight coefficient corresponding to the final cluster in which the data point is located to obtain the actual coordinate distance of the data point;

[0129] The actual coordinate distance of each data point is taken as the affected value of the corresponding sub-area.

[0130] In one implementation, cluster analysis and weighted distance calculation can comprehensively consider the risk of rainstorm impact in sub-regions and dynamically adjust the impact value of each region. By combining the weights of each cluster and considering the distribution of data points in the region, it not only improves the accuracy of the warning, but also accurately reflects the actual risks of different regions when rainstorms occur, thereby providing more detailed and scientific guidance for disaster prevention and control, and optimizing resource allocation and emergency response measures.

[0131] It should be noted that, because the impact on life, the impact on groundwater level, and the impact on sewer capacity are selected as data points for clustering, these three data points can now be used as coordinates and mapped to the three-dimensional coordinate axis, and each first energy storage device will be mapped as a point on the three-dimensional coordinate axis; after clustering is completed, all data points will be distributed in different final clusters on the three-dimensional coordinate axis. The closer the final cluster is to the original center, the smaller the impact value of the sub-region corresponding to the data point included therein is, and the less the sub-region is affected by the heavy rain. Therefore, the sub-region may not need so many resources for protective measures, and the lower the heavy rain warning level is. On the contrary, the larger the value is, the greater the impact of the sub-region is on the heavy rain. Therefore, the corresponding protective measures of the sub-region require more resources, and the higher the heavy rain warning level is; at the same time, the weight coefficient of each final cluster is calculated to correct the distance from the data point to the original center. In this way, the different importance of each final cluster can be ensured, and the influence of noise and outliers on the clustering results can be reduced to a certain extent, so that the final calculated impact value of each sub-region is more accurate.

[0132] In one embodiment, determining the rainstorm risk level of each sub-region according to the affected value of each sub-region, the expected rainfall, and whether a secondary disaster occurs in the sub-region includes:

[0133] If no secondary disaster occurs in the sub-region, the affected value and the rainfall amount of the sub-region are normalized to obtain the rainstorm impact risk level coefficient. , the calculation formula is: , where , are the affected value and the rainfall amount after normalization respectively; , They are , The preset scaling factor of , Greater than 0;

[0134] Compare the rainstorm impact risk level coefficient of the sub-area with the preset rainstorm impact risk level coefficient stage threshold;

[0135] If the rainstorm risk level coefficient is less than the preset first threshold of the rainstorm risk level coefficient, the rainstorm risk level of the sub-area is recorded as a low risk level, and the meteorological early warning aircraft issues a low risk warning;

[0136] If the rainstorm impact risk level coefficient is not less than the preset first threshold value of the rainstorm impact risk level coefficient but less than the preset second threshold value of the rainstorm impact risk level coefficient, the rainstorm impact risk level of the sub-area is recorded as a medium risk level, and the meteorological early warning aircraft issues a medium risk warning;

[0137] If the rainstorm impact risk level coefficient is not less than the preset rainstorm impact risk level coefficient second threshold, the rainstorm impact risk level of the sub-area is recorded as a high risk level, and the meteorological early warning aircraft issues a high risk warning;

[0138] If a secondary disaster occurs in a sub-region, the rainstorm impact risk level of the sub-region will be directly recorded as a high-risk level, and the meteorological early warning aircraft will issue a high-risk warning and a special warning for the occurrence of secondary disasters at the same time.

[0139] It should be noted that , It is set by professionals according to the actual situation. Generally, , The sum of is 1, for example , They can be 0.35, 0.65, or other numbers respectively, without specific limitation. In addition, commonly used normalization methods include Min-Max normalization, Z-Score standardization, etc. The specific method is selected by professionals according to the actual situation and is not limited or elaborated on.

[0140] It should be noted that the preset stage thresholds of the rainstorm impact risk level coefficient are set by professionals based on actual conditions, and are not limited or elaborated on in detail. The preset first threshold of the rainstorm impact risk level coefficient is less than the preset second threshold of the rainstorm impact risk level coefficient.

[0141] It should be noted that after the meteorological early warning machine issues different warnings according to the risk level of rainstorm impact in the sub-region, the relevant departments and institutions can take corresponding emergency measures according to the warning level. For example: for low-risk areas, the public's daily disaster prevention publicity can be strengthened to ensure the normal operation of infrastructure, and quick cleanup after rainstorms can be done in advance; for medium-risk areas, meteorological monitoring can be strengthened, patrols and inspections can be increased, drainage systems can be ensured to be unobstructed, and emergency supplies can be deployed; and for high-risk areas, when the warning level is high, the relevant departments should immediately activate the emergency response mechanism, including personnel evacuation, traffic control, flood prevention and control, and post-disaster rescue measures, and at the same time strengthen the monitoring and emergency response of areas where secondary disasters may occur to ensure that the disaster impact caused by rainstorms is minimized.

[0142] In one implementation method, the potential threat of heavy rain to sub-regions is comprehensively considered by combining the affected value, rainfall, and whether secondary disasters occur. First, the normalized rainstorm risk level coefficient is obtained based on the affected value and expected rainfall of the sub-region. This coefficient reflects the basic risk level of the region under heavy rain conditions. On this basis, the sub-regions are graded in combination with the preset risk level threshold. If no secondary disasters occur in the region, the risk level can be determined by comparing different preset thresholds to ensure the accuracy and hierarchy of heavy rain warnings. For areas where secondary disasters occur, regardless of other factors, they are directly identified as high-risk levels and special warnings are issued. This measure can promptly remind relevant departments to take emergency response measures. Through this detailed warning mechanism, not only the accuracy and response speed of heavy rain warnings are improved, but also excessive prevention and waste of resources in low-risk areas are reduced, and sufficient emergency support is ensured in high-risk areas, thereby enhancing the overall protection effect.

[0143] Based on the same inventive concept, the embodiment of the present invention also provides a meteorological disaster warning system based on a meteorological early warning aircraft. Figure 2 , Figure 2 A framework diagram of a meteorological disaster warning system based on a meteorological early warning aircraft provided in an embodiment of the present invention, the system comprising:

[0144] Prediction module: divide the area to be predicted for heavy rain into several sub-areas, and use the meteorological early warning machine to predict the rainfall in each sub-area in the preset time period in the future as the expected rainfall in each sub-area;

[0145] Disaster probability module: For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated based on the historical records of secondary disasters in the sub-region;

[0146] Judgment module: if the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster occurs in the corresponding sub-area;

[0147] Affected module: Obtain the population density, groundwater level and sewer capacity of each sub-region and use them as data points of the corresponding sub-region to obtain a data set, and cluster the data set to determine the affected value of each sub-region;

[0148] Early warning module: Determine the rainstorm risk level of each sub-region based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and send the rainstorm risk level of each sub-region to the meteorological early warning aircraft for early warning.

[0149] A meteorological disaster warning system based on a meteorological early warning aircraft provided in an embodiment of the present invention can take into account the impact of heavy rain and other possible secondary disasters caused by heavy rain, so that the prevention measures are comprehensive enough to reduce the losses caused by disasters; and it can make detailed considerations on the regions to ensure that low-risk areas will not be over-prevented and reduce waste of resources. At the same time, high-risk areas have sufficient emergency support and are not exposed to danger, thereby enhancing the overall protection effect.

[0150] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A meteorological disaster early warning method based on a meteorological early warning aircraft, characterized in that: The following steps are involved: The area to be predicted for heavy rain is divided into several sub-areas, and the rainfall in each sub-area in the future preset time period is predicted by the meteorological early warning aircraft as the expected rainfall in each sub-area; For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated in combination with the historical records of secondary disasters in the sub-region; If the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster will occur in the corresponding sub-area; The population density, groundwater level and sewer capacity of each sub-region are obtained and used as data points of the corresponding sub-region to obtain a data set, and the data set is clustered to determine the affected value of each sub-region; The rainstorm impact risk level of each sub-region is determined based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and the rainstorm impact risk level of each sub-region is sent to the meteorological early warning aircraft for early warning.

2. A meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 1, characterized in that: The steps of obtaining the number of mountains and regional images in the sub-region and calculating the probability of secondary disasters in the sub-region in combination with the historical records of secondary disasters in the sub-region are as follows: Get the number of mountains in the sub-area, and get the slope and volume of each mountain, determine the preset slope impact value and preset volume impact value of each mountain, and calculate the terrain impact value of the sub-area. The calculation formula is: ； In the formula, is the terrain influence value of the sub-region, is the number of mountains in the sub-region, is the order number of the mountain. Indicates Preset slope impact value of each mountain, For the Preset volume impact value of each mountain; The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, regional image and historical records of secondary disasters in the sub-region.

3. A meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 2, characterized in that: The steps for calculating the probability of secondary disasters in a sub-region based on the terrain impact value, regional image and secondary disaster occurrence history of the sub-region are as follows: Obtain satellite images of the sub-area, and extract near-infrared band pixel values ​​and red band pixel values ​​of each pixel from the satellite images to obtain the vegetation index of the corresponding pixel; The vegetation index of each pixel is compared with a preset vegetation index threshold. If the vegetation index is greater than the preset vegetation index threshold, the corresponding pixel is a vegetation pixel; Calculate the mean vegetation index of all vegetation pixels as the vegetation impact value; The probability of secondary disasters in the sub-region is calculated based on the terrain impact value, vegetation impact value and historical record of secondary disasters in the sub-region.

4. A meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 3, characterized in that: The steps for calculating the probability of secondary disasters in a sub-region based on the terrain impact value, vegetation impact value and secondary disaster occurrence history of the sub-region are as follows: According to historical records, the total number of rainstorms that occurred in the sub-area within a preset period in the past is obtained, and the number of secondary disasters that occurred after each rainstorm is obtained. The number of secondary disasters that occurred is divided by the total number of rainstorms to obtain the disaster triggering ratio; The terrain impact value, vegetation impact value and disaster initiation ratio of the sub-region are normalized to obtain the probability of secondary disasters in the corresponding sub-region. The calculation formula is: ； In the formula, is the probability of secondary disasters, , , are the normalized terrain impact value, vegetation impact value and disaster initiation ratio, , , They are , , Preset scaling factor, and , , Both are greater than 0.

5. The meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 1, characterized in that: The steps to obtain the population density, groundwater level and sewer capacity of each sub-region as the data points of the corresponding sub-region are: Obtain the population density, building density and area of ​​the sub-region, and normalize the population density, building density and area to obtain the life impact; Divide the sub-region into several sub-regions, obtain the groundwater level of each sub-region, calculate the distance between the groundwater level of each sub-region and the corresponding surface, calculate the mean of the distances between the groundwater level of all sub-regions and the corresponding surface, and take the reciprocal of the mean as the groundwater level impact degree; Obtain the capacity of each sewer in the sub-area, calculate the mean capacity of the sewer, and use the inverse of the mean as the sewer capacity impact; The impact on life, groundwater level, and sewer capacity of the sub-region are taken as the data points of the corresponding sub-region.

6. The meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 1, characterized in that: The steps to cluster the data set to determine the affected values ​​of each sub-region are: The steps to cluster the data set according to the K-means clustering method are as follows: Step 1: Use the elbow method to determine the optimal number of clusters K for the data set; Step 2: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center, traverse the K initial cluster centers, and assign it to the cluster corresponding to the nearest initial cluster center; Step 3: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center. Step 4: Repeat steps 2 and 3 until the cluster center no longer changes, and obtain the final cluster and the final cluster center; The final clusters and the final cluster centers are mapped to three-dimensional coordinates to obtain the affected values ​​of each sub-region.

7. A meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 6, characterized in that: The final clusters and the final cluster centers are mapped to three-dimensional coordinates, and the affected values ​​of each sub-area are obtained, including: The final clusters and the final cluster centers are mapped to three-dimensional coordinates, and the affected values ​​of each sub-area are obtained, including: Calculate the weight coefficient of each final cluster, the calculation formula is: ,in Expressed as The weight coefficients of the final clusters, Represented as the number of all data points in the dataset, Indicates The number of data points in the final clusters; Calculate the distance of each data point in each final cluster to the coordinate origin in three-dimensional coordinates to obtain the preliminary coordinate distance of the data point, and multiply the preliminary coordinate distance of the data point by the weight coefficient corresponding to the final cluster in which the data point is located to obtain the actual coordinate distance of the data point; The actual coordinate distance of each data point is taken as the affected value of the corresponding sub-area.

8. The meteorological disaster early warning method based on a meteorological early warning aircraft according to claim 1, characterized in that: The risk level of rainstorm impact in each sub-region is determined based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region: If no secondary disaster occurs in the sub-region, the sub-region's affected value and pending rainfall are normalized to obtain the rainstorm impact risk level coefficient; Compare the rainstorm impact risk level coefficient of the sub-area with the preset rainstorm impact risk level coefficient stage threshold; If the rainstorm risk level coefficient is less than the preset first threshold of the rainstorm risk level coefficient, the rainstorm risk level of the sub-area is recorded as a low risk level, and the meteorological early warning aircraft issues a low risk warning; If the rainstorm impact risk level coefficient is not less than the preset first threshold of the rainstorm impact risk level coefficient but less than the preset second threshold of the rainstorm impact risk level coefficient, the rainstorm impact risk level of the sub-area is recorded as a medium risk level, and the meteorological early warning aircraft issues a medium risk warning; If the rainstorm impact risk level coefficient is not less than the preset rainstorm impact risk level coefficient second threshold, the rainstorm impact risk level of the sub-area is recorded as a high risk level, and the meteorological early warning aircraft issues a high risk warning; If a secondary disaster occurs in a sub-region, the rainstorm impact risk level of the sub-region will be directly recorded as a high-risk level, and the meteorological early warning aircraft will issue a high-risk warning and a special warning for the occurrence of secondary disasters at the same time.

9. A meteorological disaster warning system based on a meteorological early warning aircraft, used to implement a meteorological disaster warning method based on a meteorological early warning aircraft as described in any one of claims 1 to 8, characterized in that: The system comprises: Prediction module: divide the area to be predicted for heavy rain into several sub-areas, and use the meteorological early warning machine to predict the rainfall in each sub-area in the preset time period in the future as the expected rainfall in each sub-area; Disaster probability module: For each sub-region, the number of mountains and regional images of the sub-region are obtained, and the probability of secondary disasters in the sub-region is calculated based on the historical records of secondary disasters in the sub-region; Judgment module: if the probability of secondary disaster occurrence is not less than the preset secondary disaster occurrence probability threshold, a secondary disaster occurs in the corresponding sub-area; Affected module: Obtain the population density, groundwater level and sewer capacity of each sub-region and use them as data points of the corresponding sub-region to obtain a data set, and cluster the data set to determine the affected value of each sub-region; Early warning module: Determine the rainstorm risk level of each sub-region based on the affected value, expected rainfall and whether secondary disasters occur in the corresponding sub-region, and send the rainstorm risk level of each sub-region to the meteorological early warning aircraft for early warning.

Images