A method and system for predicting the risk of high wind meteorological disasters based on quantitative models

Abstract

The present invention discloses a method and system for predicting the risk of high wind meteorological disasters based on a quantitative model. The method comprises obtaining historical data, including geographic location, environmental data, meteorological data, and disaster data. The geographic location includes latitude, longitude, and altitude. The environmental data includes vegetation index and terrain type. The meteorological data includes wind speed, air pressure, and temperature. The method classifies the geographic location and disaster data to obtain risk areas. First data is obtained based on the risk areas. Second data is obtained based on the correlation between the environmental data and the disaster data. The method fuses the first and second data to obtain a dynamic risk score. A risk prediction model is established based on the risk score, meteorological data, and disaster data. The method inputs the data to be predicted into the risk prediction model to obtain a prediction result. The present invention provides a more scientific and efficient decision support tool for risk prediction and management of high wind meteorological disasters through a quantitative model.

Description

Technical Field

[0001] The present invention relates to the field of meteorological disaster risk prediction, and in particular to a method and system for predicting the risk of gale meteorological disasters based on a quantitative model. Background Art

[0002] Currently, risk assessments for high-wind meteorological disasters rely primarily on historical data and empirical judgment, but these methods have limitations. First, historical data may not fully reflect current and future environmental changes. Second, empirical judgments are highly subjective, making them difficult to standardize and accurately assess. Furthermore, existing risk assessment models often overlook the impact of environmental factors and geographic location on disaster risk, resulting in inaccurate predictions.

[0003] To improve the accuracy and efficiency of high-wind meteorological disaster risk prediction, it is necessary to develop a new quantitative model that comprehensively considers meteorological data, environmental factors, geographic location, and historical disaster data to provide more accurate risk assessments. This paper addresses this need and proposes a quantitative model-based high-wind meteorological disaster risk prediction method. This method aims to achieve dynamic assessment and prediction of high-wind meteorological disaster risk through advanced data processing and machine learning techniques. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for predicting the risk of gale meteorological disasters based on a quantitative model.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Acquiring historical data, including geographic location, environmental data, meteorological data, and disaster data, wherein the geographic location includes latitude, longitude, and altitude, the environmental data includes vegetation index and terrain type, and the meteorological data includes wind speed, air pressure, and temperature;

[0008] Classifying the geographical location and the disaster data to obtain a risk area, obtaining first data based on the risk area, and obtaining second data based on a correlation between the environmental data and the disaster data;

[0009] fusing the first data and the second data to obtain a dynamic risk score, and establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data;

[0010] The data to be predicted is input into the risk prediction model to obtain the prediction result.

[0011] Furthermore, the geographical location and the disaster data are classified to obtain a risk area, and a method for obtaining first data according to the risk area includes:

[0012] The average disaster frequency of the disaster data is extracted, and data points are established using the geographical location and the disaster frequency. Three Gaussian distributions are preset, and the formula of the Gaussian probability density function is:

[0013]

[0014] Where x is the data point, μ k is the mean vector of the kth Gaussian distribution, D is the dimension of the data point, ε is the covariance matrix, |ε| is the determinant of the covariance matrix, a is the weight coefficient, and the formula of the probability density function of the data point is:

[0015]

[0016] where p(x) is the probability density function of x, Calculate the posterior probability:

[0017]

[0018] where x n represents the nth data point, ν is the uniform mixing parameter, and the likelihood function of the mean vector is:

[0019]

[0020] Where N is the number of data points and the likelihood function of the covariance matrix is:

[0021]

[0022] The likelihood function of the weight coefficients is:

[0023]

[0024] The risk area is divided according to the disaster frequency and the Gaussian distribution, including a high-risk area, a medium-risk area and a low-risk area, and the first data is the product of the maximum posterior probability of the data point and the average value of the disaster frequency of the corresponding risk area.

[0025] Furthermore, the method for obtaining the second data based on the correlation between the environmental data and the disaster data includes:

[0026] The terrain type is converted into a numerical number, the disaster data is predicted based on the environmental data, and a regression model is established, where the second data is the predicted value:

[0027]

[0028] in is the predicted value of the t-th decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th environmental data, I is the sample set i on the t-th decision tree, w i is the weight vector, and the regularized loss function of the regression model is:

[0029]

[0030] in represents the loss function of the kth environmental data, which is the cross entropy loss, n is the number of environmental data, T is the total number of decision trees, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and w j is the weight of decision tree j, the split gain of the decision tree:

[0031]

[0032] Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative.

[0033] Furthermore, the method of fusing the first data and the second data to obtain a dynamic risk score includes:

[0034] The first data and the second data are normalized by range, and scoring weights are preset, the sum of the scoring weights is 1, wherein the scoring weight of the second data is greater than 0.5, and the scoring weights are adjusted by introducing a dynamic weight adjustment mechanism based on data confidence. The reliability of the first data and the second data is evaluated using statistical tests, and the first data and the second data are weighted and fused according to the dynamically adjusted scoring weights to obtain the risk score.

[0035] Furthermore, the method of establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data includes:

[0036] A data set is established using the risk score, the meteorological data, and the disaster data. The data set is divided into a sample set and a test set. The risk prediction model is trained using the training set. The objective function is:

[0037]

[0038] Where Θ represents all parameters of the risk prediction model, N is the number of samples, is the sequence length of the sample, y i,t is the disaster data of the i-th sample at time step t, is the predicted data of the risk prediction model, α is the coefficient of the L1 regularization term, and ξ is a constant term used to ensure numerical stability, and ξ=1×10 -8 ,

[0039] Forget Gate:

[0040]

[0041] Among them, σ is the sigmoid activation function, H is the dimension of the hidden layer, A(h t-1 ,x t ) is the attention weight vector, W g,j is the weight matrix of the forget gate, [h t-1 ,x t ] j Indicates h t-1 and x t The jth dimension, h t-1 is the hidden state of the previous time step, x t is the input of the current time step, b is the bias term,

[0042] Input gate and candidate states:

[0043]

[0044] in For the tanh activation function, the update of the unit state is:

[0045]

[0046] Among them, g t,j and r t,j are the j-th dimension outputs of the forget gate and the input gate, S t-1,j and are the j-th dimension of the previous cell state and the current candidate state, respectively,

[0047] Output gate:

[0048]

[0049] Among them, t,j is the j-th dimension output of the output gate, b S,j is the j-th dimension bias term of the unit state, and the test set is used to verify the accuracy of the risk prediction model.

[0050] A system for predicting the risk of high wind meteorological disasters based on a quantitative model, characterized by comprising:

[0051] A collection module, which acquires historical data, including geographic location, environmental data, meteorological data, and disaster data. The geographic location includes latitude, longitude, and altitude. The environmental data includes vegetation index and terrain type. The meteorological data includes wind speed, air pressure, and temperature.

[0052] a calculation module, which classifies the geographical location and the disaster data to obtain a risk area, obtains first data based on the risk area, obtains second data based on a correlation between the environmental data and the disaster data, and establishes a risk prediction model based on the risk score, the meteorological data, and the disaster data;

[0053] an optimization module, fusing the first data and the second data to obtain a dynamic risk score;

[0054] The output module inputs the data to be predicted into the risk prediction model to obtain the prediction result.

[0055] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0056] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0057] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0058] The beneficial effects of the present invention are:

[0059] This invention uses a quantitative model to accurately predict the risk of high wind meteorological disasters, improving the dynamics and accuracy of the prediction. It comprehensively considers multi-source data, enhances the scientific nature of decision support, and simplifies the operational process for practical application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flowchart of the steps of a method and system for predicting the risk of gale meteorological disasters based on a quantitative model of the present invention;

[0061] Figure 2 This is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0062] The present invention will be further described below through specific examples. The illustrative examples and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0063] The present invention provides a method and system for predicting the risk of gale meteorological disasters based on a quantitative model, comprising the following steps:

[0064] like Figure 1 As shown, in this embodiment, the following steps are included:

[0065] Acquiring historical data, including geographic location, environmental data, meteorological data, and disaster data, wherein the geographic location includes latitude, longitude, and altitude, the environmental data includes vegetation index and terrain type, and the meteorological data includes wind speed, air pressure, and temperature;

[0066] In the actual evaluation, the two sets of historical data collected at different times are:

[0067] Group 1:

[0068]

[0069] Group 2:

[0070]

[0071] The frequency of disasters refers to the number of disasters in a year, and the meteorological and environmental data are annual average data;

[0072] Classifying the geographical location and the disaster data to obtain a risk area, obtaining first data based on the risk area, and obtaining second data based on a correlation between the environmental data and the disaster data;

[0073] In the actual evaluation, the first data is: the posterior probability of region 1 for high-risk areas is 1, the posterior probability of region 2 for medium-risk areas is 1, and the posterior probability of region 3 for low-risk areas is 1.

[0074] The second data is as follows: Group 1: disasters occurred 8 times in Region 1, 5 times in Region 2, and 3 times in Region 3; Group 2: disasters occurred 8 times in Region 1, 5 times in Region 2, and 2 times in Region 3;

[0075] fusing the first data and the second data to obtain a dynamic risk score, and establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data;

[0076] In the actual assessment, the risk scores are as follows: Group 1: Region 1 is 8, Region 2 is 5, and Region 3 is 2.5;

[0077] The data to be predicted is input into the risk prediction model to obtain the prediction result.

[0078] In this embodiment, the geographical location and the disaster data are classified to obtain a risk area, and a method for obtaining first data based on the risk area includes:

[0079] The average disaster frequency of the disaster data is extracted, and data points are established using the geographical location and the disaster frequency. Three Gaussian distributions are preset, and the formula of the Gaussian probability density function is:

[0080]

[0081] Where x is the data point, μ k is the mean vector of the kth Gaussian distribution, D is the dimension of the data point, ε is the covariance matrix, |ε| is the determinant of the covariance matrix, a is the weight coefficient, and the formula of the probability density function of the data point is:

[0082]

[0083] where p(x) is the probability density function of x, Calculate the posterior probability:

[0084]

[0085] where x n represents the nth data point, ν is the uniform mixing parameter, and the likelihood function of the mean vector is:

[0086]

[0087] Where N is the number of data points and the likelihood function of the covariance matrix is:

[0088]

[0089] The likelihood function of the weight coefficients is:

[0090]

[0091] The risk area is divided according to the disaster frequency and the Gaussian distribution, including a high-risk area, a medium-risk area and a low-risk area, and the first data is the product of the maximum posterior probability of the data point and the average value of the disaster frequency of the corresponding risk area.

[0092] In this embodiment, the method for obtaining the second data based on the correlation between the environmental data and the disaster data includes:

[0093] The terrain type is converted into a numerical number, the disaster data is predicted based on the environmental data, and a regression model is established, where the second data is the predicted value:

[0094]

[0095] in is the predicted value of the t-th decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th environmental data, I is the sample set i on the t-th decision tree, w i is the weight vector, and the regularized loss function of the regression model is:

[0096]

[0097] in represents the loss function of the kth environmental data, which is the cross entropy loss, n is the number of environmental data, T is the total number of decision trees, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and w j is the weight of decision tree j, the split gain of the decision tree:

[0098]

[0099] Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative.

[0100] In this embodiment, the method of fusing the first data and the second data to obtain a dynamic risk score includes:

[0101] The first data and the second data are normalized for range, and scoring weights are preset, where the sum of the scoring weights is 1. The scoring weight of the second data is greater than 0.5, and the scoring weights w1 and w2 of the first data and the second data are 0.3 and 0.7, respectively. The scoring weights are adjusted by introducing a dynamic weight adjustment mechanism based on data confidence, and the reliability of the first data and the second data is evaluated using statistical tests. The first data and the second data are weighted and fused according to the dynamically adjusted scoring weights to obtain the risk score:

[0102] R t =w1·P′ t +w2·F′ t

[0103] where R tScore the risk, P' t is the first data, F′ t is the second data.

[0104] In this embodiment, the method for establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data includes:

[0105] A data set is established using the risk score, the meteorological data, and the disaster data. The data set is divided into a sample set and a test set. The risk prediction model is trained using the training set. The objective function is:

[0106]

[0107] Where Θ represents all parameters of the risk prediction model, N is the number of samples, is the sequence length of the sample, y i,t is the disaster data of the i-th sample at time step t, is the predicted data of the risk prediction model, α is the coefficient of the L1 regularization term, and ξ is a constant term used to ensure numerical stability, and ξ=1×10 -8 ,

[0108] Forget Gate:

[0109]

[0110] Among them, σ is the sigmoid activation function, H is the dimension of the hidden layer, A(h t-1 ,x t ) is the attention weight vector, W g,j is the weight matrix of the forget gate, [h t-1 ,x t ] j Indicates h t-1 and x t The jth dimension, h t-1 is the hidden state of the previous time step, x t is the input of the current time step, b is the bias term,

[0111] Input gate and candidate states:

[0112]

[0113] in For the tanh activation function, the update of the unit state is:

[0114]

[0115] Among them, g t,j and r t,jare the j-th dimension outputs of the forget gate and the input gate, S t-1,j and are the j-th dimension of the previous cell state and the current candidate state, respectively,

[0116] Output gate:

[0117]

[0118] Among them, t,j is the j-th dimension output of the output gate, b S,j is the j-th dimension bias term of the unit state, and the test set is used to verify the accuracy of the risk prediction model.

[0119] A system for predicting the risk of high wind meteorological disasters based on a quantitative model, characterized by comprising:

[0120] A collection module, which acquires historical data, including geographic location, environmental data, meteorological data, and disaster data. The geographic location includes latitude, longitude, and altitude. The environmental data includes vegetation index and terrain type. The meteorological data includes wind speed, air pressure, and temperature.

[0121] a calculation module, which classifies the geographical location and the disaster data to obtain a risk area, obtains first data based on the risk area, obtains second data based on a correlation between the environmental data and the disaster data, and establishes a risk prediction model based on the risk score, the meteorological data, and the disaster data;

[0122] an optimization module, fusing the first data and the second data to obtain a dynamic risk score;

[0123] The output module inputs the data to be predicted into the risk prediction model to obtain the prediction result.

[0124] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0125] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0126] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0127] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a quantitative model-based high wind meteorological disaster risk prediction device at the logical level. The processor executes the program stored in the memory and is specifically configured to implement any of the aforementioned quantitative model-based high wind meteorological disaster risk prediction methods and systems.

[0128] The above application Figure 1The method and system for predicting the risk of high wind meteorological disasters based on a quantitative model disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0129] The electronic device may also perform Figure 1 A method and system for predicting the risk of high wind meteorological disasters based on quantitative models was developed. Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0130] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, they execute any of the aforementioned quantitative model-based high wind meteorological disaster risk prediction methods and systems.

[0131] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0139] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] 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 method for predicting the risk of high wind meteorological disasters based on a quantitative model, characterized in that: The following steps are involved: Acquiring historical data, including geographic location, environmental data, meteorological data, and disaster data, wherein the geographic location includes latitude, longitude, and altitude, the environmental data includes vegetation index and terrain type, and the meteorological data includes wind speed, air pressure, and temperature; Classifying the geographical location and the disaster data to obtain a risk area, and obtaining first data based on the risk area. The average disaster frequency of the disaster data is extracted, and data points are established using the geographical location and the disaster frequency. Three Gaussian distributions are preset, and the formula of the Gaussian probability density function is: Where x is the data point, μ k is the mean vector of the k-th Gaussian distribution, D is the dimension of the data point, ε is the covariance matrix, |ε| is the determinant of the covariance matrix, a is the weight coefficient, and the formula of the probability density function of the data point is: where p(x) is the probability density function of x, Calculate the posterior probability: where x n represents the nth data point, v is the uniform mixing parameter, and the likelihood function of the mean vector is: Where N is the number of data points and the likelihood function of the covariance matrix is: The likelihood function of the weight coefficients is: The risk area is divided into high-risk area, medium-risk area and low-risk area according to the disaster frequency and the Gaussian distribution, and the first data is the product of the maximum posterior probability of the data point and the average value of the disaster frequency of the corresponding risk area. Obtaining second data based on the correlation between the environmental data and the disaster data, The terrain type is converted into a numerical number, the disaster data is predicted based on the environmental data, and a regression model is established, where the second data is the predicted value: in is the predicted value of the t-th decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th environmental data, I is the sample set i on the t-th decision tree, w i is the weight vector, and the regularized loss function of the regression model is: in represents the loss function of the kth environmental data, which is the cross entropy loss, n is the number of environmental data, T is the total number of decision trees, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and w j is the weight of decision tree j, the split gain of the decision tree: Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative; fusing the first data and the second data to obtain a dynamic risk score, and establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data; The data to be predicted is input into the risk prediction model to obtain the prediction result.

2. The method for predicting the risk of high wind meteorological disasters based on a quantitative model according to claim 1, characterized in that: The method of fusing the first data and the second data to obtain a dynamic risk score includes: The first data and the second data are normalized by range, and scoring weights are preset, the sum of the scoring weights is 1, wherein the scoring weight of the second data is greater than 0.5, and the scoring weights are adjusted by introducing a dynamic weight adjustment mechanism based on data confidence. The reliability of the first data and the second data is evaluated using statistical tests, and the first data and the second data are weighted and fused according to the dynamically adjusted scoring weights to obtain the risk score.

3. The method for predicting the risk of high wind meteorological disasters based on a quantitative model according to claim 1, characterized in that: The method for establishing a risk prediction model based on the risk score, the meteorological data, and the disaster data includes: A data set is established using the risk score, the meteorological data, and the disaster data. The data set is divided into a sample set and a test set. The sample set is used to train the risk prediction model. The objective function is: Where Θ represents all parameters of the risk prediction model, N is the number of samples, is the sequence length of the sample, y i,t is the disaster data of the i-th sample at time step t, is the predicted data of the risk prediction model, α is the coefficient of the L1 regularization term, and ξ is a constant term used to ensure numerical stability, and ξ=1×10 -8 , Forget Gate: Among them, σ is the sigmoid activation function, H is the dimension of the hidden layer, A(h t-1 ,x t ) is the attention weight vector, W g,j is the weight matrix of the forget gate, [h t-1 ,x t ] j Indicates h t-1 and x t The jth dimension, h t-1 is the hidden state of the previous time step, x t is the input of the current time step, b is the bias term, Input gate and candidate states: in For the tanh activation function, the update of the unit state is: Among them, g t,j and r t,j are the j-th dimension outputs of the forget gate and the input gate, S t-1,j and are the j-th dimension of the previous cell state and the current candidate state, respectively, Output Gate: Among them, t,j is the j-th dimension output of the output gate, b S,j is the j-th dimension bias term of the unit state, and the test set is used to verify the accuracy of the risk prediction model.

4. A system for predicting the risk of high wind meteorological disasters based on a quantitative model, for executing the method for predicting the risk of high wind meteorological disasters based on a quantitative model according to any one of claims 1 to 3, characterized in that: include: A collection module acquires historical data, including geographic location, environmental data, meteorological data, and disaster data. The geographic location includes latitude, longitude, and altitude. The environmental data includes vegetation index and terrain type. The meteorological data includes wind speed, air pressure, and temperature. a calculation module, which classifies the geographical location and the disaster data to obtain a risk area, obtains first data based on the risk area, obtains second data based on a correlation between the environmental data and the disaster data, and establishes a risk prediction model based on the risk score, the meteorological data, and the disaster data; an optimization module, fusing the first data and the second data to obtain a dynamic risk score; The output module inputs the data to be predicted into the risk prediction model to obtain the prediction result.

5. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 3.

6. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the method according to any one of claims 1 to 3.

Images