Prediction method for vulnerable areas to extreme weather based on geographic big data

Abstract

The present invention relates to the field of image and text processing technology, and in particular, provides a prediction method for areas vulnerable to extreme weather based on geographic big data. The method includes analyzing the spatiotemporal evolution characteristics of rainfall and land use type changes according to preprocessed data sets, identifying the relationship between precipitation and land use types in different regions; collecting temperature and altitude data sets, analyzing the occurrence patterns of extreme weather in different altitudes; establishing corresponding monitoring and early warning mechanisms according to the relationship between precipitation and land use types and the occurrence patterns of extreme weather; defining the signs of rainstorm disasters through corresponding monitoring and early warning mechanisms, and using relevant data to perform critical analysis of rainstorm disaster conditions; predicting areas vulnerable to rainstorm disasters according to the critical analysis of rainstorm disaster conditions, and enriching the systematic modeling and comprehensive analysis of different geographical features, improving the prediction ability of extreme weather, and reducing property losses.

Description

Technical Field

[0001] The present invention relates to the technical field of image and text processing, and in particular to a prediction method for areas vulnerable to extreme weather based on geographic big data. Background Art

[0002] With the advent of the big data era, the types and quantities of geographic observation data have increased significantly, providing a rich material basis for studying comprehensive geographical issues. The effective use of geographic big data can describe and simulate the complex nonlinear characteristics of the real world through statistical physics indicators and deep learning methods. However, how to effectively use these massive data is still a key issue that needs to be solved.

[0003] Existing technologies mainly focus on analyzing single climate or land use characteristics in specific time periods and regions, lacking systematic modeling and comprehensive analysis of different geographical characteristics. In addition, existing analysis methods often fail to consider the impact of the interaction between altitude and climate on the formation of extreme weather, resulting in insufficient prediction capabilities for extreme weather, and ultimately causing property losses in areas vulnerable to extreme weather. Summary of the invention

[0004] In view of this, the present invention provides a prediction method for areas vulnerable to extreme weather based on geographic big data, which is used to enrich the systematic modeling and comprehensive analysis of different geographical features, improve the ability to predict extreme weather, and reduce property losses.

[0005] In a first aspect, the present invention provides a method for predicting areas vulnerable to extreme weather based on geographic big data, the method comprising:

[0006] Step 1, collect the data set of rainfall and land use type, preprocess the data set, and obtain the preprocessed data set;

[0007] Step 2: Analyze the spatiotemporal evolution characteristics of precipitation and land use type changes based on the preprocessed data set, and identify the relationship between precipitation and land use type in different regions;

[0008] Step 3: Collect temperature and altitude data sets to analyze the occurrence patterns of extreme weather in different altitudes; establish corresponding monitoring and early warning mechanisms based on the relationship between precipitation and land use types and the occurrence patterns of extreme weather;

[0009] Step 4: Define the signs of rainstorm disasters through corresponding monitoring and early warning mechanisms, and use relevant data to conduct critical analysis of rainstorm disaster conditions;

[0010] Step 5: Based on the critical analysis of rainstorm disaster conditions, predict areas vulnerable to rainstorm disasters.

[0011] Optionally, step 1 includes:

[0012] The parameters of the rainfall dataset include longitude, latitude, year, time, daily rainfall, and number of stations; the daily rainfall data and the number of stations in the region for each year are extracted, and missing values ​​are filled with 0; the parameters of the land use type dataset include longitude, latitude, cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio, among which the sum of the cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio is 1.

[0013] Optionally, the step 2 includes:

[0014] Firstly, the longitude and latitude were divided into 9 different longitude and latitude regional blocks according to low longitude, middle longitude, high longitude, low latitude, middle latitude and high latitude. The daily rainfall was converted into the average monthly precipitation, and the precipitation changes in 9 different longitude and latitude regional blocks were observed. The changes in land use types in 9 different longitude and latitude regional blocks over the past 30 years were also observed.

[0015] Optionally, the step 3 includes:

[0016] The parameters of the temperature data set include longitude, latitude, and temperature; the parameters of the altitude data set include longitude, latitude, and altitude. The area is divided into three areas according to the altitude, namely, the area with an altitude below 500 meters is the low altitude area, the area with an altitude greater than 500 meters and less than 1500 meters is the medium altitude area, and the area with an altitude greater than 1500 meters is the high altitude area. The longitude and latitude points located in the three areas are randomly sampled to draw the relationship between precipitation and temperature in different regions.

[0017] Optionally, step 4 includes:

[0018] Areas with annual rainfall greater than 800 mm are defined as areas with severe rainstorm disasters, and the Pearson correlation coefficient is used to analyze the impact of the interaction between altitude and land use type on rainstorm disaster conditions, where grassland and shrubs are positively correlated with rainfall, and altitude, cultivated land, woodland and wetland are negatively correlated with rainfall. Optionally, step 5 includes:

[0019] With rainfall as the dependent variable and altitude, cultivated land, woodland, grassland, shrubs, and wetland as independent variables, we used K nearest neighbor, random forest, and support vector machine modeling to output accuracy, ROC curve, and AUC value.

[0020] The accuracy rate indicates the proportion of correct predictions, and the specific formula is: ; Among them, TP means correctly predicted as a positive example, TN means correctly predicted as a negative example, FP means incorrectly predicted as a positive example, and FN means incorrectly predicted as a negative example; each point of the ROC curve represents a threshold, and the classifier will give each sample a score. If the score is greater than the specified threshold, the current sample is defined as a positive sample, otherwise it is considered a negative sample; the AUC value is the area covered by the ROC curve. The larger the AUC value, the better the classification effect of the classifier.

[0021] In a second aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the prediction method for vulnerable areas to extreme weather based on geographic big data in the first aspect or any possible implementation of the first aspect.

[0022] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to execute the method for predicting areas vulnerable to extreme weather based on geographic big data in the first aspect or any possible implementation of the first aspect.

[0023] In the technical solution provided by the present invention, the method includes collecting a data set of rainfall and land use type, preprocessing the data set to obtain a preprocessed data set; analyzing the spatiotemporal evolution characteristics of rainfall and land use type changes based on the preprocessed data set, and identifying the relationship between precipitation and land use type in different regions; collecting temperature and altitude data sets, and analyzing the occurrence patterns of extreme weather in regions with different altitudes; establishing a corresponding monitoring and early warning mechanism based on the relationship between precipitation and land use type and the occurrence pattern of extreme weather; defining signs of rainstorm disasters through the corresponding monitoring and early warning mechanism, and using relevant data to perform a critical analysis of rainstorm disaster conditions; based on the critical analysis of rainstorm disaster conditions, predicting areas with vulnerable rainstorm disaster capabilities, the method enriches the systematic modeling and comprehensive analysis of different geographical features, improves the ability to predict extreme weather, and reduces property losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1A flow chart of a method for predicting areas vulnerable to extreme weather based on geographic big data provided by an embodiment of the present invention;

[0026] Figure 2 The average monthly precipitation map for different longitudes and latitudes in the past five years provided by the embodiment of the present invention;

[0027] FIG3 (a) is a 30-year land use type map of a low-latitude and low-longitude region provided by an embodiment of the present invention;

[0028] FIG3( b ) is a 30-year land use type map of a low-latitude mid-longitude region provided by an embodiment of the present invention;

[0029] FIG3 (c) is a 30-year land use type map of a low-latitude and high-longitude region provided by an embodiment of the present invention;

[0030] FIG3( d ) is a 30-year land use type map of a high-latitude and low-longitude region provided by an embodiment of the present invention;

[0031] FIG3( e ) is a 30-year land use type map of a high-latitude and high-longitude region provided by an embodiment of the present invention;

[0032] FIG3( f ) is a 30-year land use type map of a high-latitude mid-longitude region provided by an embodiment of the present invention;

[0033] FIG3( g ) is a 30-year land use type map of a mid-latitude and low-longitude region provided by an embodiment of the present invention;

[0034] FIG3( h ) is a 30-year land use type map of a mid-latitude and high-longitude region provided by an embodiment of the present invention;

[0035] FIG3 (i) is a 30-year land use type map of a mid-latitude and mid-longitude region provided by an embodiment of the present invention;

[0036] Figure 4 A graph showing the relationship between precipitation and temperature in a medium and low altitude area for one year provided by an embodiment of the present invention;

[0037] Figure 5 A graph showing the relationship between precipitation and temperature in a medium-high altitude area for one year provided by an embodiment of the present invention;

[0038] Figure 6 A graph showing the relationship between precipitation and temperature in a medium- and high-altitude area for one year provided by an embodiment of the present invention;

[0039] FIG. 7 (a) is a diagram showing the altitude when heavy rain occurs, provided by an embodiment of the present invention;

[0040] FIG7( b ) is a diagram of farmland conditions during rainstorms provided by an embodiment of the present invention;

[0041] FIG7 (c) is a diagram of forest conditions during a rainstorm provided by an embodiment of the present invention;

[0042] FIG. 7 (d) is a diagram of grassland conditions during a rainstorm provided by an embodiment of the present invention;

[0043] FIG7 (e) is a diagram of bushes during a rainstorm provided by an embodiment of the present invention;

[0044] FIG7( f ) is a diagram of wetland conditions during heavy rain provided by an embodiment of the present invention;

[0045] Figure 8 The ROC curve diagram provided by the embodiment of the present invention;

[0046] Fig. 9 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0048] It should be clear that 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.

[0049] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings.

[0050] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0051] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0052] Figure 1 A flowchart of a method for predicting areas vulnerable to extreme weather based on geographic big data provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0053] Step 1, collect the data set of rainfall and land use type, preprocess the data set, and obtain the preprocessed data set;

[0054] In the embodiment of the present invention, step 1 includes:

[0055] The parameters of the rainfall dataset include longitude, latitude, year, time, daily rainfall, and number of stations; the daily rainfall data and the number of stations in the region for each year are extracted, and missing values ​​are filled with 0; the parameters of the land use type dataset include longitude, latitude, cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio, among which the sum of the cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio is 1.

[0056] Step 2: Analyze the spatiotemporal evolution characteristics of precipitation and land use type changes based on the preprocessed data set, and identify the relationship between precipitation and land use type in different regions;

[0057] In the embodiment of the present invention, step 2 includes:

[0058] First, the longitude and latitude are combined in pairs to divide them into 9 different longitude and latitude regional blocks, as shown in Table 1; the daily rainfall is converted into the average monthly precipitation, and the precipitation changes in 9 different longitude and latitude regional blocks are observed, and the changes in land use types in 9 different longitude and latitude regional blocks over 30 years are observed.

[0059] Table 1 Latitude and longitude regional blocks

[0060] ;

[0061] In the embodiment of the present invention, Figure 2As shown in the figure, by observing the changes in precipitation in 9 regions, it was found that the monthly average precipitation in low-latitude and low-longitude regions was significantly ahead, and the precipitation in low-latitude regions was generally higher than that in mid- and high-latitude regions. In addition, low-longitude and low-latitude regions have high rainfall all year round, and the precipitation in low-longitude and mid- and high-latitude regions is greatly affected by the climate change of the year, which provides a solid theoretical basis for the prevention of extreme weather.

[0062] In the embodiment of the present invention, as shown in FIG. 3 (a) to FIG. 3 (i), the changes in land use types in 9 different longitude and latitude regional blocks over 30 years are observed. For low longitude areas, the proportion of grassland is far ahead, with a significant gap with other types of vegetation types, and the changes are relatively stable over the past 30 years. For medium and high longitude areas, although the proportion of grassland has always been high, it has been on a downward trend overall, and the proportion of forest land has continued to increase over the past 30 years, and even high longitude and high latitude areas eventually have almost the same proportion as grassland. For the proportion of cultivated land, a relatively high proportion level is maintained in medium and high longitude areas, and it has remained generally stable over the past 30 years, with a slight increase. It is finally found that rainfall and land use types are closely related to the longitude and latitude of the area in which they are located. The annual rainfall in areas with perennial rain and perennial drought will not change much, while other areas may have significant changes according to the climate of the year, and drought and waterlogging prevention and control are needed in advance. Some types of land use will also change with changes in longitude and latitude. Mastering the appropriate land use type is also crucial for soil consolidation, sand prevention, and flood prevention.

[0063] Step 3: Collect temperature and altitude data sets to analyze the occurrence patterns of extreme weather in different altitudes; establish corresponding monitoring and early warning mechanisms based on the relationship between precipitation and land use types and the occurrence patterns of extreme weather;

[0064] In the embodiment of the present invention, step 3 includes:

[0065] The parameters of the temperature data set include longitude, latitude, and temperature; the parameters of the altitude data set include longitude, latitude, and altitude. The area is divided into three areas according to the altitude, namely, the area with an altitude below 500 meters is the low altitude area, the area with an altitude greater than 500 meters and less than 1500 meters is the medium altitude area, and the area with an altitude greater than 1500 meters is the high altitude area. The longitude and latitude points located in the three areas are randomly sampled to draw the relationship between precipitation and temperature in different regions.

[0066] In the embodiment of the present invention, Figures 4 to 6As shown in the figure, the relationship between precipitation and temperature in low-medium altitude areas, medium-medium altitude areas, and medium-high altitude areas are drawn respectively. The horizontal axis is the number of days in a year, and the vertical axis is the corresponding rainfall and temperature. In order to facilitate the viewing of trends, it is necessary to merge the rainfall map and the temperature map. The line graph of the rainfall is used as the base, and the line graph of the temperature map is merged. Finally, it is found that the rainfall in low-medium altitude areas is concentrated in the middle months of each year, approximately from May to August, and there is less rainfall in other months; in medium-medium altitude areas, the occurrence of extreme rainstorms is irregular, and the area needs to be alert to extreme rainstorms that may come at any time throughout the year; in medium-high altitude areas, the occurrence of rainstorms and extreme weather is more concentrated in June and July than in lower altitude areas. With the difference in altitude, the temperature and rainfall differences in each region will be very different. It is very necessary to prepare for extreme weather according to local conditions. Through comparison, it is found that before the occurrence of extreme rainstorms, it may be accompanied by continuous high temperatures.

[0067] In the embodiment of the present invention, according to the relationship diagram between precipitation and temperature in different regions, it is found that the rainfall at low altitudes is concentrated in the middle months of each year, approximately from May to August, and there is less rainfall in other months; in the middle altitude region, the occurrence of extreme rainstorms is irregular, and the region needs to be alert to extreme rainstorms that may come at any time throughout the year; in high altitude regions, the occurrence of rainstorms and extreme weather is more concentrated in June and July than in lower altitude regions. With the difference in altitude, the temperature and rainfall in each region will be very different. It is very necessary to prepare for extreme weather according to local conditions. Through comparison, it is found that before the occurrence of extreme rainstorms, it may be accompanied by continuous high temperature.

[0068] Step 4: Define the signs of rainstorm disasters through corresponding monitoring and early warning mechanisms, and use relevant data to conduct critical analysis of rainstorm disaster conditions;

[0069] In the embodiment of the present invention, step 4 includes:

[0070] Areas with annual rainfall greater than 800 mm were defined as areas with severe rainstorm disasters. The Pearson correlation coefficient was used to analyze the impact of the interaction between altitude and land use type on rainstorm disaster conditions, as shown in Table 2. Grassland and shrubs were positively correlated with rainfall, while altitude, cultivated land, woodland and wetland were negatively correlated with rainfall.

[0071] Table 2

[0072] ;

[0073] In the embodiment of the present invention, as shown in FIG. 7 (a) to FIG. 7 (f), the altitude, cultivated land, forest land, grassland, bushes, and wetland conditions when heavy rain occurs are visualized. The vertical coordinate of the altitude schematic diagram is meters and the horizontal coordinate is the index. The vertical coordinate of the other schematic diagrams is the proportion and the horizontal coordinate is the index. It is found that the altitude where heavy rain extreme weather occurs is usually above 500 meters, concentrated at an altitude of 550 meters. The proportion of cultivated land is usually between 0 and 0.5, concentrated in the 0 ratio interval, and occasionally occurs in the medium and high ratio areas. The proportion of forest land is usually in the 0 to 0.14 area, which is prone to heavy rain weather, and most of it is concentrated in the 0.04 ratio area. The proportion of grassland is generated in the 0.3 to 1 area, and most of it is concentrated in the 0.8 ratio area. The proportion of bushes is usually in the 0 to 0.5 range, and most of it is concentrated around the ratio of 0.1. The proportion of wetlands is usually between 0 and 0.02, and most of it is concentrated near 0. Finally, it is concluded that the critical conditions for rainstorm disasters are approximately 550 meters above sea level, 0% cultivated land, 0.04% forest land, 0.8% grassland, 0.1% bush, and 0% wetland. Areas that meet multiple conditions above need to pay attention to the occurrence of extreme weather in a timely manner.

[0074] Step 5: Based on the critical analysis of rainstorm disaster conditions, predict areas vulnerable to rainstorm disasters.

[0075] In the embodiment of the present invention, step 5 includes:

[0076] With rainfall as the dependent variable and altitude, cultivated land, woodland, grassland, shrubs, and wetland as independent variables, we used K nearest neighbor, random forest, and support vector machine modeling to output accuracy, ROC curve, and AUC value.

[0077] The accuracy rate indicates the proportion of correct predictions, and the specific formula is: ; Among them, TP means correctly predicted as a positive example, TN means correctly predicted as a negative example, FP means incorrectly predicted as a positive example, and FN means incorrectly predicted as a negative example; each point of the ROC curve represents a threshold, and the classifier will give each sample a score. If the score is greater than the specified threshold, the current sample is defined as a positive sample, otherwise it is considered a negative sample; the AUC value is the area covered by the ROC curve. The larger the AUC value, the better the classification effect of the classifier.

[0078] The accuracy is the number of samples correctly predicted by the classification divided by the total number of samples. Generally speaking, the higher the accuracy, the better the classifier. AUC is the area under the ROC curve, which can well summarize the performance of the imbalanced sample classifier.

[0079] In the embodiment of the present invention, Figure 8As shown in the figure, the random forest algorithm with the largest AUC value is selected as the optimal model, and the maximum feature number of the optimal random forest model parameters is 3 and the number of decision trees is 32 through grid search. The optimal model is saved for prediction and visualization, and it is finally found that the areas with the most vulnerable ability to cope with heavy rain disasters are concentrated in the north, especially between 30 degrees north latitude and 42 degrees north latitude. More efficient measures are needed in this region for prevention.

[0080] Each step of the embodiment of the present invention may be performed by an electronic device, which includes but is not limited to a mobile phone, a tablet computer, a portable PC, a desktop computer, etc.

[0081] In the technical solution provided by the present invention, the method includes collecting a data set of rainfall and land use type, preprocessing the data set to obtain a preprocessed data set; analyzing the spatiotemporal evolution characteristics of rainfall and land use type changes based on the preprocessed data set, and identifying the relationship between precipitation and land use type in different regions; collecting temperature and altitude data sets, and analyzing the occurrence patterns of extreme weather in regions with different altitudes; establishing a corresponding monitoring and early warning mechanism based on the relationship between precipitation and land use type and the occurrence pattern of extreme weather; defining signs of rainstorm disasters through the corresponding monitoring and early warning mechanism, and using relevant data to perform a critical analysis of rainstorm disaster conditions; based on the critical analysis of rainstorm disaster conditions, predicting areas with vulnerable rainstorm disaster capabilities, the method enriches the systematic modeling and comprehensive analysis of different geographical features, improves the ability to predict extreme weather, and reduces property losses.

[0082] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the electronic device where the computer-readable storage medium is located is controlled to execute the above-mentioned embodiment of the prediction method for vulnerable areas to extreme weather based on geographic big data.

[0083] Fig. 9 A schematic diagram of an electronic device provided by an embodiment of the present invention, such as Fig. 9 As shown, the electronic device 21 includes: a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211. When the computer program 213 is executed by the processor 211, the prediction method for areas vulnerable to extreme weather based on geographic big data in the embodiment is implemented. To avoid repetition, they are not described one by one here.

[0084] The electronic device 21 includes, but is not limited to, a processor 211 and a memory 212. Those skilled in the art will appreciate that Fig. 9It is only an example of the electronic device 21 and does not constitute a limitation of the electronic device 21. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0085] The processor 211 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0086] The memory 212 may be an internal storage unit of the electronic device 21, such as a hard disk or memory of the electronic device 21. The memory 212 may also be an external storage device of the electronic device 21, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 21. Further, the memory 212 may also include both an internal storage unit of the electronic device 21 and an external storage device. The memory 212 is used to store computer programs and other programs and data required by network devices. The memory 212 may also be used to temporarily store data that has been output or is to be output.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A prediction method for areas vulnerable to extreme weather based on geographic big data, characterized in that: The method comprises: Step 1, collect the data set of rainfall and land use type, preprocess the data set, and obtain the preprocessed data set; Step 2: Analyze the spatiotemporal evolution characteristics of precipitation and land use type changes based on the preprocessed data set, and identify the relationship between precipitation and land use type in different regions; The step 2 comprises: firstly, dividing the longitude and latitude into 9 different longitude and latitude regional blocks according to low longitude, middle longitude, high longitude, low latitude, middle latitude, and high latitude, and combining the longitude and latitude in pairs; converting the daily rainfall into the average rainfall of each month, observing the precipitation changes of the 9 different longitude and latitude regional blocks, and observing the 30-year land use type changes of the 9 different longitude and latitude regional blocks; Step 3: Collect temperature and altitude data sets to analyze the occurrence patterns of extreme weather in different altitudes; establish corresponding monitoring and early warning mechanisms based on the relationship between precipitation and land use types and the occurrence patterns of extreme weather; Step 4: Define the signs of rainstorm disasters through corresponding monitoring and early warning mechanisms, and use relevant data to conduct critical analysis of rainstorm disaster conditions; The step 4 includes: defining areas with annual rainfall greater than 800 mm as areas with severe rainstorm disasters, and using the Pearson correlation coefficient to analyze the impact of the interaction between altitude and land use type on rainstorm disaster conditions; Step 5: Based on the critical analysis of rainstorm disaster conditions, predict areas vulnerable to rainstorm disasters; The step 5 comprises: With rainfall as the dependent variable and altitude, cultivated land, woodland, grassland, shrubs, and wetland as independent variables, we used K nearest neighbor, random forest, and support vector machine modeling to output accuracy, ROC curve, and AUC value. The accuracy rate indicates the proportion of correct predictions, and the specific formula is: ; Among them, TP means correctly predicted as a positive example, TN means correctly predicted as a negative example, FP means incorrectly predicted as a positive example, and FN means incorrectly predicted as a negative example; each point of the ROC curve represents a threshold, and the classifier will give each sample a score. If the score is greater than the specified threshold, the current sample is defined as a positive sample, otherwise it is considered a negative sample; the AUC value is the area covered by the ROC curve. The larger the AUC value, the better the classification effect of the classifier.

2. The method according to claim 1, characterized in that The step 1 comprises: The parameters of the rainfall dataset include longitude, latitude, year, time, daily rainfall, and number of stations; the daily rainfall data and the number of stations in the region for each year are extracted, and missing values ​​are filled with 0; the parameters of the land use type dataset include longitude, latitude, cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio, among which the sum of the cultivated land area ratio, forest area ratio, grassland area ratio, shrub area ratio, and wetland area ratio is 1.

3. The method according to claim 1, characterized in that The step 3 comprises: The parameters of the temperature data set include longitude, latitude, and temperature; the parameters of the altitude data set include longitude, latitude, and altitude. The area is divided into three areas according to the altitude, namely, the area with an altitude below 500 meters is the low altitude area, the area with an altitude greater than 500 meters and less than 1500 meters is the medium altitude area, and the area with an altitude greater than 1500 meters is the high altitude area. The longitude and latitude points located in the three areas are randomly sampled to draw the relationship between precipitation and temperature in different regions.

4. The method according to claim 1, characterized in that include: Grassland and shrubland are positively correlated with rainfall, while altitude, cultivated land, woodland and wetland are negatively correlated with rainfall.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for predicting areas vulnerable to extreme weather based on geographic big data as described in any one of claims 1 to 4.

6. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to execute the method for predicting areas vulnerable to extreme weather based on geographic big data as described in any one of claims 1 to 4.

Images