An intelligent early warning system for dangerous weather based on data analysis

Abstract

The present application relates to the technical field of meteorology, specifically to a dangerous weather intelligent early warning system based on data analysis, comprising: a multi-source weather data acquisition module acquires dangerous weather data such as meteorology, geology and hydrology; a multi-source weather data transmission module transmits data to the cloud through a communication interruption response mechanism and sets access permissions; a multi-source weather data processing module cleans, corrects and extracts key weather features; a snow avalanche determination model establishment module uses GAN to enhance feature data and establishes a snow avalanche determination model based on snow avalanche occurrence probability and confidence interval; an early warning generation module simulates the snow avalanche path and the affected area through the snow avalanche physics model and the shallow water model, evaluates the danger level and issues an early warning; and a model updating module dynamically optimizes the snow avalanche determination model based on the latest data, improving the accuracy and timeliness of the early warning capability.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorology, and in particular to an intelligent early warning system for dangerous weather based on data analysis. Background Art

[0002] The high altitude and complex terrain of the plateau region make transportation relatively difficult, resulting in a low density of automatic weather stations and radar sites. Remote sensing observations are also often limited by factors such as terrain obstruction. Heavy snowfall in the plateau is often accompanied by severe weather conditions such as low temperatures, strong winds, and blowing snow, sometimes even triggering avalanches, posing a serious threat to transportation, electricity, agriculture, animal husbandry, and personal safety. Therefore, timely and accurate avalanche prediction is crucial to effectively reducing accidents and economic losses.

[0003] Some existing solutions enable the deployment of automatic weather stations and ground-based radars in plateau regions, and the initial transmission of observation data via low-power wide-area networks or satellite communications. Combining weather forecasts with satellite data, these solutions can provide a macroscopic assessment of large-scale avalanches. However, these warning systems often lack sophisticated analytical tools to determine the affected area, failing to accurately identify the specific location, propagation path, and impact range of the avalanche. This results in poorly targeted warning information and makes it difficult to more accurately predict the impact of plateau snowstorms. Furthermore, given the limited communication conditions in plateau regions, these warning systems often lack effective emergency communication and information transmission mechanisms, resulting in inefficient warning issuance and emergency response, making them unable to meet the needs of emergency response.

[0004] In order to improve the accuracy and timeliness of early warning capabilities, a dangerous weather intelligent early warning system based on data analysis is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent early warning system for dangerous weather based on data analysis, which obtains meteorological, geological, hydrological and other dangerous weather data through a multi-source weather data acquisition module; a multi-source weather data transmission module transmits data to the cloud through a communication interruption response mechanism and sets access rights; a multi-source weather data processing module cleans and proofreads the data and extracts key weather features; an avalanche determination model establishment module uses GAN to enhance feature data and establish an avalanche determination model based on avalanche occurrence probability and confidence interval; an early warning generation module simulates avalanche paths and impact areas through an avalanche physics model and a shallow water model, evaluates the hazard level and issues early warnings; a model update module dynamically optimizes the avalanche determination model based on the latest data, thereby improving the accuracy and timeliness of the early warning capability. To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A dangerous weather intelligent early warning system based on data analysis, comprising:

[0007] Multi-source weather data acquisition module, used to collect hazardous weather data including meteorological data, geological data and hydrological data;

[0008] A multi-source weather data transmission module is used to transmit the dangerous weather data to the cloud server using a communication interruption response mechanism, and to set access permissions for the dangerous weather data, so as to perform hierarchical permission management on the dangerous weather data according to role identity;

[0009] a multi-source weather data processing module, configured to clean and quality-check the hazardous weather data to obtain a first data set; and filter the first data set using a Pearson correlation coefficient to obtain weather characteristic data;

[0010] an avalanche determination model establishment module, configured to perform data enhancement on the weather characteristic data using a GAN model to obtain a second data set; establish an avalanche determination model, identify the second data set, and output an avalanche occurrence probability and an avalanche confidence interval;

[0011] an early warning generation module, which calculates an initial flow velocity using an avalanche physics model based on the dangerous weather data, performs path simulation using a shallow water model based on the initial flow velocity, and generates an avalanche impact area if the avalanche occurrence probability and the avalanche confidence interval meet a first condition; generates an avalanche hazard level based on the avalanche impact area and issues early warning information;

[0012] The dangerous weather prediction model updating module is used to obtain the latest dangerous weather data, and automatically perform data analysis and update the avalanche determination model.

[0013] Furthermore, the dangerous weather data includes:

[0014] The meteorological data include temperature, humidity, air pressure, wind speed and direction, and precipitation;

[0015] The geological data include snow depth, terrain slope, rock and soil layer distribution, and historical events of avalanche disasters;

[0016] The hydrological data includes snow melt rates, river flows, and soil moisture.

[0017] Furthermore, the communication interruption response mechanism includes:

[0018] If the network is interrupted, the hazardous weather data is stored in a local storage device;

[0019] If the network is restored, the local storage device synchronizes the hazardous weather data using an incremental upload method.

[0020] Furthermore, the access permission setting process includes:

[0021] Encrypting the hazardous weather data during transmission using an encryption protocol to generate encrypted weather data;

[0022] The role identities include meteorologist, emergency personnel and administrator, and setting the access rights to the weather encrypted data according to different role identities includes:

[0023] The meteorologist has the authority to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, and the multi-source weather data processing module;

[0024] The emergency personnel have the authority to view the multi-source weather data acquisition module and the warning generation module;

[0025] The administrator has the authority to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, the multi-source weather data processing module, the avalanche determination model establishment module, the warning generation module and the dangerous weather prediction model update module.

[0026] Furthermore, the data cleaning and the quality proofreading specifically include: using a time series interpolation method and a spatial interpolation method to complete the hazardous weather data, and cross-validating the hazardous weather data from different data sources to obtain the first data set.

[0027] Furthermore, the implementation process of the Pearson correlation coefficient includes:

[0028] Calculating the Pearson correlation coefficient between each of the dangerous weather data and the avalanche occurrence event;

[0029] A characteristic absolute value threshold is set, and if the Pearson correlation coefficient is greater than the characteristic absolute value threshold, the dangerous weather data corresponding to the Pearson correlation coefficient is filtered as the weather characteristic data.

[0030] Furthermore, the implementation process of the avalanche determination model includes:

[0031] Constructing the avalanche determination model, comprising an input layer, a hidden layer, an output layer, and a Bayesian layer; the input layer is used to receive the second data set; the hidden layer is used to extract data features of the second data set; the output layer is used to predict the avalanche occurrence probability and the avalanche confidence interval; the Bayesian layer introduces uncertainty analysis to obtain the confidence level of the prediction result;

[0032] Setting the loss function to a weighted combination of negative log-likelihood and KL divergence; the negative log-likelihood is used to evaluate the loss value of the avalanche probability, and the KL divergence is used to evaluate the loss value of the avalanche confidence interval;

[0033] Splitting the second data set into a training set and a test set, and inputting the sets into the avalanche determination model; the training set is used to train the avalanche determination model, and the test set is used to evaluate the avalanche determination model;

[0034] The avalanche determination model after the test is saved.

[0035] Furthermore, the first condition includes: the minimum value of the avalanche confidence interval is greater than a preset confidence threshold, the width of the avalanche confidence interval is less than a preset interval width, and the avalanche occurrence probability is greater than a preset probability threshold.

[0036] Furthermore, the process of generating the avalanche hazard level includes:

[0037] Obtain each geographic grid, and if the avalanche flow velocity corresponding to the geographic grid exceeds a flow velocity threshold, or the avalanche depth exceeds a depth threshold, then the geographic grid is the avalanche affected area;

[0038] For the avalanche affected area, setting the avalanche hazard level according to a range in which the avalanche flow velocity exceeds the flow velocity threshold and a range in which the avalanche depth exceeds the depth threshold;

[0039] The avalanche risk levels include low risk level, medium risk level and high risk level.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. This invention utilizes a communication interruption response mechanism. In the event of a network outage, critical hazardous weather data can be securely stored in a local storage device. Upon network recovery, the data is synchronized using an incremental upload method, enhancing the reliability and security of data transmission and avoiding data loss or delays caused by communication interruptions. Furthermore, hazardous weather data during transmission is encrypted using an encryption protocol, and role-based hierarchical permission management is implemented. This not only ensures that different roles can accurately access the required modules, but also improves the accuracy and timeliness of avalanche risk warnings.

[0042] 2. This paper uses a GAN model to enhance weather feature data, improving the robustness of the model and effectively addressing the problem of insufficient historical avalanche data. On this basis, an avalanche determination model is constructed, comprising an input layer, a hidden layer, an output layer, and a Bayesian layer. The model is finely optimized using a loss function that combines negative log-likelihood and KL divergence weighted combinations. This improves the prediction accuracy of avalanche probability and the reliability of confidence interval calculations, providing an accurate basis for risk assessment and thus enhancing the accuracy and timeliness of avalanche risk warnings.

[0043] 3. This invention calculates the initial flow velocity using an avalanche physics model and simulates the path using a shallow water model, generating a detailed map of the avalanche impact area. This allows for precise demarcation of avalanche impact areas and risk level assessment, making early warning information more targeted and timely. Furthermore, based on gridded areas and set avalanche flow velocity and depth thresholds, three risk levels (low, medium, and high) are defined, and corresponding warning information is issued. This allows for early identification of high-risk areas, effectively improving the accuracy and timeliness of avalanche risk warnings and paving the way for effective preventive measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a schematic structural diagram of a dangerous weather intelligent early warning system based on data analysis according to the present invention;

[0045] Figure 2 Schematic diagram of the communication interruption response mechanism of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0047] See also Figures 1 to 2 The present invention provides a dangerous weather intelligent early warning system based on data analysis, and the technical solution is as follows:

[0048] Area A is located in a high-altitude mountainous area with complex terrain and is one of the areas prone to avalanches. The climate conditions in the area are changeable, with heavy snow accumulation in winter and snowmelt easily occurring after the temperature rises in spring, triggering avalanches. In addition, the population density in Area A is low, but major transportation arteries and some villages may be located in areas potentially affected by avalanches. Once an avalanche occurs, it will have a significant impact on transportation and residents' lives. In response to the avalanche monitoring and early warning needs in Area A, Example 1 is as follows:

[0049] like Figure 1 As shown, a dangerous weather intelligent early warning system based on data analysis includes:

[0050] refer to Figure 1 The multi-source weather data acquisition module in is used to collect hazardous weather data including meteorological data, geological data and hydrological data.

[0051] Furthermore, the dangerous weather data includes:

[0052] The meteorological data include temperature, humidity, air pressure, wind speed and direction, and precipitation;

[0053] The geological data include snow depth, terrain slope, rock and soil layer distribution, and historical events of avalanche disasters;

[0054] The hydrological data includes snow melt rates, river flows, and soil moisture.

[0055] Specifically, automatic weather stations already in place in the plateau region, or those deployed in areas prone to avalanches, are equipped with temperature, humidity, air pressure, wind speed and direction, and precipitation sensors, which automatically record data every 10 minutes. Next, meteorological satellite images and weather radar data are integrated to obtain geologically relevant information. Snow depth is determined by satellite imaging technology to identify snow accumulation areas and depths. Terrain slope is calculated using a digital elevation model (DEM). Rock and soil layer distribution is obtained through geological radar scanning and analysis. Historical avalanche disaster events are integrated based on the time, location, and impact range of past avalanche events. NDSI changes are calculated using satellite imagery and remote sensing technology to identify snow melt rates. River flow and soil moisture data are integrated using ground hydrological monitoring stations, remote sensing technology, and hydrological numerical models.

[0056] Through the multi-source weather data acquisition module, the system can integrate dangerous weather data sets from different sources to provide comprehensive data support for subsequent modules, thereby effectively improving the accuracy and timeliness of avalanche risk warnings.

[0057] refer to Figure 1 The multi-source weather data transmission module is used to transmit the dangerous weather data to the cloud server using the communication interruption response mechanism, and set access rights for the dangerous weather data, so as to perform hierarchical permission management on the dangerous weather data according to role identity.

[0058] Furthermore, the communication interruption response mechanism includes:

[0059] If the network is interrupted, the hazardous weather data is stored in a local storage device;

[0060] If the network is restored, the local storage device synchronizes the hazardous weather data using an incremental upload method.

[0061] Specifically, in this embodiment, Figure 2 This is a flow chart of the communication interruption response mechanism of the present invention. Figure 2As shown, the local storage device uses the storage device of the automatic weather station. First, the network state is checked to determine whether the network is normal. If normal, the normal data transmission mode is used, and transmission to the cloud server is performed. If network interruption or instability is detected, the system automatically switches to the local storage mode, and the real-time collected dangerous weather data (such as temperature, humidity, snow depth, and soil moisture) is stored in time sequence, ensuring the integrity and continuity of the data. Among them, the cyclic coverage storage strategy is used to ensure that the latest data is saved first, avoid data loss due to insufficient storage space, and improve the utilization rate of the local storage space. When the network connection of the monitoring point is restored to stability, the system will start the incremental upload mechanism to synchronize the newly stored data during the interruption to the cloud server, reducing the amount of repeated transmission data and improving the transmission efficiency, thereby ensuring the stable operation of the system in harsh environments and improving the accuracy and timeliness of the snow avalanche risk warning.

[0062] Further, the setting process of the access permission includes:

[0063] The dangerous weather data in the transmission process is encrypted using an encryption protocol to generate weather encrypted data;

[0064] The role identity includes meteorologists, emergency personnel, and administrators, and the access permission to the weather encrypted data is set according to different role identities, including:

[0065] The meteorologist has the permission to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, and the multi-source weather data processing module;

[0066] The emergency personnel have the permission to view the multi-source weather data acquisition module and the warning generation module;

[0067] The administrator has the permission to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, the multi-source weather data processing module, the avalanche determination model establishment module, the warning generation module, and the dangerous weather prediction model update module.

[0068] Specifically, in this embodiment, the encryption protocol uses the TLS protocol to ensure that the data is not tampered with during transmission. Among the three types of user roles set by the system, meteorologists are mainly responsible for weather data analysis and processing, emergency personnel mainly focus on monitoring and warning information for disaster occurrence to quickly respond to disasters, and administrators comprehensively manage the system. The corresponding subdivided permission allocation table is shown in Table 1, which gives the use permissions of the three types of users to the system.

[0069] Table 1: Permission allocation table

[0070] Module Name Meteorologist's authority Emergency personnel authority Administrator privileges Multi-source weather data acquisition module View, modify Check View, modify Multi-source weather data transmission module View, modify none View, modify Multi-source weather data processing module View, modify none View, modify Avalanche determination model building module none none View, modify Warning generation module none Check View, modify Hazardous weather forecast model update module none none View, modify

[0071] Through permission settings and data encryption, the system not only ensures data security but also clarifies the division of responsibilities, improves management efficiency, and enables rapid emergency response to warning information when avalanches are predicted. This not only ensures the efficient operation of the system but also provides reliable technical support to relevant departments, improving the accuracy and timeliness of avalanche risk warnings.

[0072] refer to Figure 1 The multi-source weather data processing module is used to clean and quality check the dangerous weather data to obtain a first data set; the first data set is filtered by the Pearson correlation coefficient to obtain weather characteristic data.

[0073] Furthermore, the data cleaning and the quality proofreading specifically include: using a time series interpolation method and a spatial interpolation method to complete the hazardous weather data, and cross-validating the hazardous weather data from different data sources to obtain the first data set.

[0074] Specifically, in this embodiment, since meteorological data (such as temperature and humidity) and hydrological data (such as snow melt rate) may have missing data, linear interpolation is used to fill in the missing time point data. For the spatial distribution of geological data (such as terrain slope and rock and soil layer distribution) and the spatial distribution of hydrological data (such as river flow and soil moisture), the inverse distance weighted method is used to fill in the missing data.

[0075] In order to ensure the consistency and accuracy of data between different data sources, cross-validation of hazardous weather data from different data sources is required. For example, compare whether the precipitation of automatic weather stations and meteorological satellites in overlapping areas and time periods is consistent. After aligning the time index, use the Spearman rank correlation coefficient method or the Pearson correlation coefficient method to calculate the correlation coefficient of the two data. If the correlation coefficient is high (such as greater than 0.8), it means that the data consistency of the two data sources is good. Otherwise, it is necessary to further check the data source and processing process, and data cleaning may be required again. After time series interpolation, spatial interpolation and cross-data source cross-validation, all data are integrated to generate the first data set for subsequent model training. Through the above data cleaning and quality proofreading, the data from different data sources are synchronized, which effectively improves the reliability of the data and provides a reliable data foundation for subsequent modules, thereby improving the accuracy of avalanche risk warnings.

[0076] Furthermore, the implementation process of the Pearson correlation coefficient includes:

[0077] Calculating the Pearson correlation coefficient between each of the dangerous weather data and the avalanche occurrence event;

[0078] A characteristic absolute value threshold is set, and if the Pearson correlation coefficient is greater than the characteristic absolute value threshold, the dangerous weather data corresponding to the Pearson correlation coefficient is filtered as the weather characteristic data.

[0079] Specifically, in this embodiment, the feature absolute value threshold is set to 0.7. For each type of data (such as temperature, precipitation, etc.), it is aligned with the sequence of avalanche events, and the Pearson correlation coefficient between them and the avalanche events is calculated. If the Pearson correlation coefficient is greater than 0.7, this data is selected into the weather feature data. As shown in Table 2, the correlation coefficient of each data type and whether it is screened as weather feature data are shown. By selecting feature data that is highly correlated with avalanche risk (such as temperature, wind speed, precipitation, snow depth, etc.), irrelevant or redundant data can be effectively eliminated, reducing the computational burden of the avalanche determination model. This not only improves the training efficiency of the model, but also enhances its prediction accuracy, thereby enabling more accurate avalanche risk warnings.

[0080] Table 2 Screening results

[0081] Data Type Pearson correlation coefficient Feature absolute value threshold (0.7) Filter results temperature 0.82 Greater than 0.7 Filter to weather characteristic data precipitation 0.76 Greater than 0.7 Filter to weather characteristic data wind speed 0.65 Less than 0.7 No screening humidity 0.73 Greater than 0.7 Filter to weather characteristic data Snow depth 0.88 Greater than 0.7 Filter to weather characteristic data Terrain slope 0.72 Greater than 0.7 Filter to weather characteristic data Soil moisture 0.78 Greater than 0.7 Filter to weather characteristic data Snow melt rate 0.75 Greater than 0.7 Filter to weather characteristic data River flow 0.55 Less than 0.7 No screening Rock and soil layer distribution 0.68 Less than 0.7 No screening

[0082] refer to Figure 1 The avalanche determination model establishment module in the invention is used to perform data enhancement on the weather feature data using the GAN model to obtain a second data set; establish an avalanche determination model, identify the second data set, and output the avalanche occurrence probability and avalanche confidence interval.

[0083] In the data collection process for avalanche risk warnings, obtaining large amounts of accurately labeled avalanche event data is challenging, as avalanches are extremely low-probability events. However, GANs can leverage existing weather data for training, generating synthetic data that closely resembles the distribution of real data. This provides the model with more training resources, effectively improving the generalization capabilities of the avalanche prediction model and enabling more accurate judgment and prediction of actual avalanche events.

[0084] Furthermore, the implementation process of the avalanche determination model includes:

[0085] Constructing the avalanche determination model, comprising an input layer, a hidden layer, an output layer, and a Bayesian layer; the input layer is used to receive the second data set; the hidden layer is used to extract data features of the second data set; the output layer is used to predict the avalanche occurrence probability and the avalanche confidence interval; the Bayesian layer introduces uncertainty analysis to obtain the confidence level of the prediction result;

[0086] Setting the loss function to a weighted combination of negative log-likelihood and KL divergence; the negative log-likelihood is used to evaluate the loss value of the avalanche probability, and the KL divergence is used to evaluate the loss value of the avalanche confidence interval;

[0087] Splitting the second data set into a training set and a test set, and inputting the sets into the avalanche determination model; the training set is used to train the avalanche determination model, and the test set is used to evaluate the avalanche determination model;

[0088] The avalanche determination model after the test is saved.

[0089] In this embodiment, the avalanche determination model is constructed based on a Bayesian neural network (BNN), including an input layer, a hidden layer, an output layer, and a Bayesian layer. In order to optimize the model performance, the loss function is expressed as:

[0090] L = NLL + α × KL;

[0091] Among them, L is the loss value, NLL is the negative log-likelihood value, KL is the KL divergence value, and α is the weight parameter, which can be set to 0.8.

[0092] Next, the second dataset was split into a training set and a test set in a ratio of 8 to 2. The training set was fed into the avalanche detection model, and multiple iterations of training were performed using the Adam optimizer and a learning rate decay strategy until the loss function converged. The test set was then used to evaluate the avalanche detection model, using mean squared error (MSE) and prediction interval coverage (PICP) as evaluation metrics. The BNN achieved an MSE of 7.4% and a PICP of 91%. This test not only predicts the probability of avalanche occurrence but also assesses the uncertainty of the prediction results, outputting a confidence level. This allows for more accurate avalanche risk warnings, providing valuable information for evacuation decisions in the event of avalanches.

[0093] Table 3 Judgment results

[0094]

[0095] refer to Figure 1 In the warning generation module, if the avalanche occurrence probability and the avalanche confidence interval meet the first condition, the initial flow velocity is calculated using the avalanche physics model according to the dangerous weather data, and the path simulation is performed using the shallow water model according to the initial flow velocity to generate the avalanche impact area; the avalanche hazard level is generated according to the avalanche impact area and warning information is issued.

[0096] Furthermore, the first condition includes: the minimum value of the avalanche confidence interval is greater than a preset confidence threshold, the width of the avalanche confidence interval is less than a preset interval width, and the avalanche occurrence probability is greater than a preset probability threshold.

[0097] Specifically, in the present embodiment, the confidence threshold is set to 50%, the interval width is set to 10%, and the occurrence probability threshold is set to 50%. The judgment result is shown in Table 3. If the above three conditions are met at the same time, it is judged as "yes", indicating that the next step of generating early warning can be performed; otherwise, it is judged as "no". Through the setting of the first condition, the snow avalanche events that meet the early warning conditions can be effectively screened out, avoiding false positives and false negatives. In addition, combined with the comprehensive judgment of the snow avalanche occurrence probability and the confidence interval, the reliability and decision-making scientificity of the model prediction can be improved, thereby improving the accuracy of the snow avalanche risk early warning.

[0098] Further, the initial flow rate is calculated according to the physical characteristics of the snow avalanche, which is used to simulate the initial motion state of the snow avalanche, and is represented as:

[0099]

[0100] where v0 is the initial flow rate, g is the acceleration of gravity, H is the vertical drop of the snow avalanche starting point, and μ is the friction coefficient.

[0101] where the process of obtaining H is as follows: according to the terrain slope, the steep region (such as the slope greater than 30°) is selected as the possible snow avalanche starting point, then the height of the lowest point under the snow avalanche path is obtained, and the two values are subtracted to obtain H. The friction coefficient is 0.1 to 0.5, which can be calculated according to the snow avalanche path and sliding speed in the historical snow avalanche data.

[0102] Specifically, the A region is divided into regular geographic grids, each geographic grid contains key parameters related to snow avalanche propagation, such as terrain slope, geological roughness and snow depth, etc., which can finely depict the local terrain features. At the snow avalanche starting point, the initial flow rate and initial snow depth are assigned according to the model calculation and monitoring data as the initial conditions for simulation. The snow avalanche propagation process gradually expands downstream of the grid according to the physical law, and the explicit Euler method is used to numerically solve the shallow water equation. The shallow water equation describes the mass and momentum conservation in the snow avalanche flow, and through step-by-step iterative calculation, the depth change and flow rate distribution in the snow avalanche flow process are dynamically simulated. After the simulation is completed, the system outputs the snow avalanche depth and flow rate distribution corresponding to each geographic grid, showing the propagation characteristics of the snow avalanche in the A region, which can clearly identify the potential high-risk areas, thereby providing data support for disaster early warning and emergency response.

[0103] Further, the generation process of the snow avalanche risk level comprises:

[0104] For each geographic grid, if the snow avalanche flow rate corresponding to the geographic grid exceeds the flow rate threshold, and the snow avalanche depth exceeds the depth threshold in any one of the two, the geographic grid is the snow avalanche affected area.

[0105] Among them, the geographic grid is a grid structure used to divide alpine geographical areas. The characteristics of each area (avalanche flow velocity, avalanche depth) can be analyzed separately, thereby accurately capturing regional changes.

[0106] For the avalanche affected area, setting the avalanche hazard level according to a range in which the avalanche flow velocity exceeds the flow velocity threshold and a range in which the avalanche depth exceeds the depth threshold;

[0107] The avalanche risk levels include low risk level, medium risk level and high risk level.

[0108] Among them, in this embodiment, the flow velocity threshold is set to 1.5m / s, and the depth threshold is set to 0.5m. The low risk level is a yellow warning, indicating that the possibility of avalanche impact is low, the flow velocity does not exceed the flow velocity threshold, and the depth does not exceed the depth threshold; the medium risk level is an orange warning, indicating that the possibility of impact is medium, the flow velocity exceeds the flow velocity threshold by less than 1.5m / s, and the depth does not exceed the depth threshold by less than 0.5m; the high risk level is a red warning, indicating that the possibility of impact is large, the flow velocity exceeds the flow velocity threshold by more than 1.5m / s, and the depth exceeds the depth threshold by more than 0.5m, and emergency measures must be initiated. As shown in Table 4, the risk levels corresponding to different geographical grids are given. By setting flow velocity and depth thresholds and dividing them according to gridded areas, resource allocation can be effectively optimized, thereby achieving accurate assessment of the avalanche impact area. In this mode, the specific location of each grid can quickly determine its risk level, thereby improving the accuracy of disaster warning. At the same time, combined with dynamic monitoring of flow velocity and depth, and real-time capture of changes, the system can flexibly adapt to real-time changes in avalanche conditions, improve the real-time and accuracy of early warnings, and provide stronger protection for responding to avalanche disasters.

[0109] Table 4 Avalanche hazard level results

[0110] Geographic Grid Exceeding flow rate threshold (m / s) Exceeding the depth threshold (m) Risk Level Risk Color (0，0) 0 0 Low risk Yellow Warning (0，1) 0.8 0.2 Medium risk Orange alert (0，2) 1.8 0.8 High risk Red Alert (1，0) 1.2 0.2 High risk Red Alert

[0111] refer to Figure 1 The dangerous weather prediction model update module in the system is used to obtain the latest dangerous weather data, automatically analyze the data, and update the avalanche determination model. This continuously updated and optimized model not only gradually optimizes and adapts to the current avalanche situation in real time, but also provides a reference and reference for other weather-related disaster predictions.

[0112] To further verify the actual application effect of the dangerous weather intelligent early warning system based on data analysis in area A based on Example 1, Example 2 is as follows:

[0113] A dangerous weather intelligent early warning system based on data analysis, comprising:

[0114] Multi-source weather data acquisition module, used to collect hazardous weather data including meteorological data, geological data and hydrological data;

[0115] A multi-source weather data transmission module is used to transmit the dangerous weather data to the cloud server using a communication interruption response mechanism, and to set access permissions for the dangerous weather data, so as to perform hierarchical permission management on the dangerous weather data according to role identity;

[0116] a multi-source weather data processing module, configured to clean and quality-check the hazardous weather data to obtain a first data set; and filter the first data set using a Pearson correlation coefficient to obtain weather characteristic data;

[0117] an avalanche determination model establishment module, configured to perform data enhancement on the weather characteristic data using a GAN model to obtain a second data set; establish an avalanche determination model, identify the second data set, and output an avalanche occurrence probability and an avalanche confidence interval;

[0118] an early warning generation module, which calculates an initial flow velocity using an avalanche physics model based on the dangerous weather data, performs path simulation using a shallow water model based on the initial flow velocity, and generates an avalanche impact area if the avalanche occurrence probability and the avalanche confidence interval meet a first condition; generates an avalanche hazard level based on the avalanche impact area and issues early warning information;

[0119] The dangerous weather prediction model updating module is used to obtain the latest dangerous weather data, and automatically perform data analysis and update the avalanche determination model.

[0120] Specifically, Table 5 shows a comparison of key indicators for Region A using the present invention and the existing system. This demonstrates that the present invention significantly enhances avalanche prediction capabilities, particularly in reducing missed and false alarms, effectively improving system accuracy. Furthermore, the transmission success rate has also been significantly improved. The data transmission mechanism ensures this success rate even in extreme situations, thereby enhancing the timeliness of warning information.

[0121] Table 5 Comparison of key indicators

[0122] Key Metrics Prediction accuracy False negative rate False positive rate Average time from data collection to warning issuance Data transmission success rate Original system 78.5％ 15.6％ 12.3％ 32 minutes 86.0％ The present invention 84.5％ 7.6％ 9.3％ 24 minutes 98.5％

[0123] Furthermore, if the avalanche hazard level of a geographical grid in area A is a high risk level, the improved Dijkstra algorithm can be used to generate a minimum risk path plan for the traffic route.

[0124] Specifically, the nodes in the high-risk area are marked as obstacle nodes to make the Dijkstra algorithm preferentially avoid these nodes for path planning. According to different geographic grids, the traffic information of the corresponding area is extracted, and combined with the snow avalanche occurrence probability, snow avalanche influence area weight and traffic capacity and other factors, the data is quantitatively described and weighted summation is performed to calculate the path weight of different grids. At the same time, through real-time collection of weather, geological and traffic data, the numerical value of the risk factor is dynamically updated to ensure that the path planning can timely adapt to environmental changes to improve the accuracy and safety of the planning.

[0125] In summary, through the multi-source weather data acquisition module and the multi-source weather data transmission module, the system can obtain and integrate dangerous weather data, and with the help of the communication interruption response mechanism and the authority management, the data integrity and real-time are guaranteed to provide a reliable basis for analysis and decision-making. Then, the multi-source weather data processing module eliminates interference factors through data cleaning and proofreading, improves data quality after cleaning and proofreading, and uses Pearson correlation coefficient to screen key features, which improves the model efficiency and accuracy. Then, through the avalanche determination model establishment module, the system introduces the GAN model for data enhancement, which improves the generalization ability of the model to extreme conditions. The avalanche determination model outputs the avalanche occurrence probability and confidence interval, which improves the prediction accuracy of the model. The early warning generation module accurately divides the influence area and risk level, helps resource allocation, and reduces the loss caused by disasters. Finally, the dangerous weather prediction model updating module can continuously collect and analyze the latest data, dynamically optimize the avalanche determination model, so that it adapts to the changing environmental conditions, ensuring the robustness in the long-term operation, and further improving the timeliness and accuracy of the early warning.

[0126] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An intelligent early warning system for dangerous weather based on data analysis, characterized in that: include: Multi-source weather data acquisition module, used to collect hazardous weather data including meteorological data, geological data and hydrological data; A multi-source weather data transmission module is used to transmit the dangerous weather data to the cloud server using a communication interruption response mechanism, and to set access permissions for the dangerous weather data, so as to perform hierarchical permission management on the dangerous weather data according to role identity; a multi-source weather data processing module, configured to clean and quality-check the hazardous weather data to obtain a first data set; and filter the first data set using a Pearson correlation coefficient to obtain weather characteristic data; an avalanche determination model establishment module, configured to perform data enhancement on the weather characteristic data using a GAN model to obtain a second data set; Establishing an avalanche determination model, identifying the second data set, and outputting an avalanche occurrence probability and an avalanche confidence interval; The implementation process of the avalanche determination model includes: Constructing the avalanche determination model, comprising an input layer, a hidden layer, an output layer, and a Bayesian layer; the input layer is used to receive the second data set; the hidden layer is used to extract data features of the second data set; the output layer is used to predict the avalanche occurrence probability and the avalanche confidence interval; the Bayesian layer introduces uncertainty analysis to obtain the confidence level of the prediction result; Setting the loss function to a weighted combination of negative log-likelihood and KL divergence; the negative log-likelihood is used to evaluate the loss value of the avalanche probability, and the KL divergence is used to evaluate the loss value of the avalanche confidence interval; Splitting the second data set into a training set and a test set, and inputting the sets into the avalanche determination model; the training set is used to train the avalanche determination model, and the test set is used to evaluate the avalanche determination model; Saving the avalanche determination model after testing; an early warning generation module, which calculates an initial flow velocity using an avalanche physics model based on the dangerous weather data, performs path simulation using a shallow water model based on the initial flow velocity, and generates an avalanche impact area if the avalanche occurrence probability and the avalanche confidence interval meet a first condition; generates an avalanche hazard level based on the avalanche impact area and issues early warning information; The dangerous weather prediction model updating module is used to obtain the latest dangerous weather data, and automatically perform data analysis and update the avalanche determination model.

2. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The hazardous weather data includes: The meteorological data include temperature, humidity, air pressure, wind speed and direction, and precipitation; The geological data include snow depth, terrain slope, rock and soil layer distribution, and historical events of avalanche disasters; The hydrological data includes snow melt rates, river flows, and soil moisture.

3. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The communication interruption response mechanism includes: If the network is interrupted, the hazardous weather data is stored in a local storage device; If the network is restored, the local storage device synchronizes the hazardous weather data using an incremental upload method.

4. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The access permission setting process includes: Encrypting the hazardous weather data during transmission using an encryption protocol to generate encrypted weather data; The role identities include meteorologist, emergency personnel and administrator, and setting the access rights to the weather encrypted data according to different role identities includes: The meteorologist has the authority to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, and the multi-source weather data processing module; The emergency personnel have the authority to view the multi-source weather data acquisition module and the warning generation module; The administrator has the authority to view and modify the multi-source weather data acquisition module, the multi-source weather data transmission module, the multi-source weather data processing module, the avalanche determination model establishment module, the warning generation module and the dangerous weather prediction model update module.

5. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The data cleaning and the quality proofreading specifically include: using a time series interpolation method and a spatial interpolation method to complete the hazardous weather data, and cross-validating the hazardous weather data from different data sources to obtain the first data set.

6. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The implementation process of the Pearson correlation coefficient includes: Calculating the Pearson correlation coefficient between each of the dangerous weather data and avalanche occurrence events; A characteristic absolute value threshold is set, and if the Pearson correlation coefficient is greater than the characteristic absolute value threshold, the dangerous weather data corresponding to the Pearson correlation coefficient is filtered as the weather characteristic data.

7. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The first condition includes: the minimum value of the avalanche confidence interval is greater than a preset confidence threshold, the width of the avalanche confidence interval is less than a preset interval width, and the avalanche occurrence probability is greater than a preset probability threshold.

8. The dangerous weather intelligent early warning system based on data analysis according to claim 1 is characterized in that: The process of generating the avalanche hazard level includes: Obtain each geographic grid, and if the avalanche flow velocity corresponding to the geographic grid exceeds a flow velocity threshold, or the avalanche depth exceeds a depth threshold, then the geographic grid is the avalanche affected area; For the avalanche affected area, setting the avalanche hazard level according to a range in which the avalanche flow velocity exceeds the flow velocity threshold and a range in which the avalanche depth exceeds the depth threshold; The avalanche risk levels include low risk level, medium risk level and high risk level.

Images