Meteorological disaster prevention and reduction process monitoring system and method

Abstract

The invention discloses a meteorological disaster prevention and reduction process monitoring system and method, and the system comprises a data collection module which collects meteorological data in real time and obtains local geographical environment data, and is used for providing a meteorological and environment data basis; the data processing module is used for preprocessing, storing and preliminarily analyzing the acquired data; the weight analysis module is used for setting disaster analysis weights according to local climate characteristics; the intelligent analysis module is used for carrying out disaster prediction analysis based on the weight and the meteorological data; and the interface display module provides a visual monitoring interface and displays meteorological data, disaster risks and prevention measures. According to the invention, through cooperative work of the weight analysis module and the intelligent analysis module, accurate identification and customized early warning of disaster risks in different regions are realized, the efficiency and effect of disaster prevention and reduction are improved, and the limitation of a traditional unified monitoring mode can be avoided.

Description

Technical Field

[0001] This invention relates to the field of meteorological disaster monitoring technology, and more specifically, to a meteorological disaster prevention and mitigation process monitoring system and method. Background Technology

[0002] With the intensification of global climate change, the frequent occurrence of extreme weather events has become a serious reality that cannot be ignored, and the impact of meteorological disasters on human society is becoming increasingly severe. In recent years, global temperatures have continued to rise, and the frequency and intensity of extreme weather events have been increasing. According to data released by authoritative international organizations, the global average temperature has risen by about 1.1 degrees Celsius compared to pre-industrial levels, and in 2024, the world experienced the warmest year on record. Although this temperature change may seem small, it acts as a fuse that ignites a chain reaction, continuously exacerbating the intensity of extreme weather events.

[0003] Due to significant differences in geographical environment, climate characteristics, and disaster types across regions (e.g., coastal areas are prone to typhoons, while inland areas are prone to drought), traditional meteorological disaster prevention and mitigation systems often employ a uniform monitoring and analysis model. This makes it difficult to accurately reflect the actual disaster risks in different regions, leading to inaccurate early warning information, unreasonable resource allocation, and even delays in disaster prevention. This forecasting approach not only reduces the system's practicality but may also cause unnecessary economic losses and casualties. Therefore, it is necessary to analyze the actual factors in different regions, accurately identify the main disaster risks in each area, and provide customized early warning and prevention measures to improve disaster prevention and mitigation capabilities and reduce disaster losses. Therefore, we propose a meteorological disaster prevention and mitigation process monitoring system and method. Summary of the Invention

[0004] One objective of this invention is to provide a new technology for a meteorological disaster prevention and mitigation process monitoring system and method. According to a first aspect of the present invention, a meteorological disaster prevention and mitigation process monitoring system and method are provided, including a data acquisition module for real-time acquisition of meteorological data and local geographic environment data, for providing a meteorological and environmental data foundation; The data processing module preprocesses, stores, and performs preliminary analysis on the acquired data. The weighting analysis module sets disaster analysis weights based on local climate characteristics; The intelligent analysis module performs disaster prediction analysis based on weights and meteorological data; The interface display module provides a visual monitoring interface that displays meteorological data, disaster risks, and preventive measures; The auxiliary modules include a database, an early warning release submodule, a resource scheduling submodule, and a system management submodule.

[0005] Optionally, the data acquisition module collects meteorological data and geographical environment data; The meteorological data collection methods include sensor networks, drone monitoring, satellite remote sensing, and crowdsourced data. The sensor network specifically comprises: deploying high-precision meteorological sensors in key areas, with the meteorological sensors powered by natural energy sources based on the geographical environment; The drone monitoring specifically involves: regularly monitoring remote or high-risk areas to obtain terrain and land use data, and monitoring local weather conditions by carrying sensors. The satellite remote sensing is used for large-scale monitoring of meteorological and geographical environments, including cloud images, precipitation distribution, and wind speed and direction; The aforementioned public crowdsourced data specifically refers to setting up a mobile application or website that allows the public to upload local meteorological observation data.

[0006] Optionally, the workflow of the data processing module is as follows: 1) Acquire raw meteorological, geographical environment, and historical data collected by the data acquisition module; 2) Perform data cleaning on the acquired data; 3) Using blockchain technology, the cleaned data is stored in a database and access is controlled in real time; 4) Perform preliminary statistical analysis on the cleaned data and extract key features; 5) Transfer the cleaned and preliminarily analyzed data to the weight analysis module and the intelligent analysis module; The preliminary statistical analysis of the cleaned data includes: statistical analysis, trend analysis, and spatial analysis.

[0007] Optionally, the workflow of the weight analysis module is as follows: 1) Input data, including historical meteorological data, historical disaster data, and geographical environment data; 2) Analyze climate characteristics and identify major disaster types; 3) Analyze geographical environmental data to assess disaster risks; 4) Dynamically calculate weights by combining meteorological and geographical environmental data; 5) Provides a weight adjustment interface, allowing administrators to manually adjust weight parameters; 6) Generate a weight matrix and transmit it to the intelligent analysis module.

[0008] Optionally, the workflow of the intelligent analysis module is as follows: Data input: Obtain the various data output by the data processing module and the weight matrix output by the weight analysis module; Weight coefficient determination: Based on historical disaster data, the weight coefficients are determined and fed back to the weight analysis module; Disaster prediction and analysis: Disaster risk prediction is performed based on a weight matrix and real-time meteorological data; Output results: The prediction results are passed to the interface display module and the early warning release submodule.

[0009] Optionally, the determination of the weighting coefficients specifically involves, Input historical disaster data: including disaster type, frequency of occurrence, degree of impact, geographical environmental risk score, and actual disaster occurrence; Eigenvectors: meteorological factors and geographical environmental factors; Target variable: Disaster occurrence; Using machine learning models for disaster risk prediction; A method for monitoring meteorological disaster prevention and mitigation processes, based on the aforementioned system, includes the following steps: S1, by deploying a data acquisition module, acquires meteorological and geographical environmental data in real time, and obtains historical disaster data; S2 preprocesses and performs preliminary analysis on the acquired data, and then transmits the processed data to the weight analysis module and the intelligent analysis module respectively. S3: Based on historical disaster data, determine the weighting coefficients, and then combine historical meteorological data, historical disaster data, geographical environment data, and weighting coefficients to dynamically analyze and output the weight matrix; S4, based on a weight matrix and real-time data, predicts the probability, type, and scope of a disaster. S5 will publish the prediction results through the interface display module and the early warning release sub-module.

[0010] Optionally, the specific process for outputting the weight matrix in step S3 is as follows: S31. The intelligent analysis module determines the weight coefficients through an optimization algorithm and transmits them to the weight analysis module. S32. The weighting analysis module identifies the main local disaster types and assesses the impact of the geographical environment on disaster risk. S33. Using a comprehensive weighting algorithm, calculate the disaster frequency weight, impact weight, and geographical environment weight to generate a weight matrix. S34. Provides an interface to support administrators in manually adjusting weight parameters. S35. Transmit the weight matrix to the intelligent analysis module for disaster prediction and analysis.

[0011] According to one embodiment of this disclosure, the meteorological disaster prevention and mitigation process monitoring system, through a weight analysis module and an intelligent analysis module, achieves accurate prediction and customized early warning of disaster risks in different regions, thereby improving disaster prevention and mitigation capabilities. First, by analyzing historical data and geographical environment of different regions, the system calculates the weights of disaster analysis and generates a weight matrix, thus accurately reflecting local disaster risks. Furthermore, it supports administrators manually adjusting weight parameters, further enhancing the system's flexibility and adaptability. Secondly, the intelligent analysis module predicts disaster risks based on the weight matrix and real-time meteorological data, outputting the probability, type, and scope of disaster occurrence. By combining weight analysis and real-time data, it provides customized disaster early warning information, offering accurate warnings to different regions and helping relevant departments and the public to take preventive measures in advance. In addition, the intelligent analysis module dynamically adjusts the weight coefficients through algorithm optimization to ensure the scientific validity and reliability of the prediction results.

[0012] By working together with the weighting analysis module and the intelligent analysis module, accurate identification and customized early warning of disaster risks in different regions can be achieved, which not only improves the efficiency and effectiveness of disaster prevention and mitigation, but also avoids the limitations of the traditional unified monitoring model.

[0013] Other features and advantages of the invention will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with their description, serve to explain the principles of the invention.

[0015] Figure 1 This is a schematic diagram of the system framework of a meteorological disaster prevention and mitigation process monitoring system in one embodiment; Figure 2 This is a schematic diagram of a meteorological disaster prevention and mitigation process monitoring method in an embodiment. Detailed Implementation

[0016] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0017] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0018] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0019] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0020] like Figure 1-2 As shown, a meteorological disaster prevention and mitigation process monitoring system and method includes a data acquisition module, which collects meteorological data and acquires local geographic environment data in real time to provide a meteorological and environmental data foundation. The data processing module preprocesses, stores, and performs preliminary analysis on the acquired data. The weighting analysis module sets disaster analysis weights based on local climate characteristics; The intelligent analysis module performs disaster prediction analysis based on weights and meteorological data; The interface display module provides a visual monitoring interface that displays meteorological data, disaster risks, and preventive measures; The auxiliary modules include a database, an early warning release submodule, a resource scheduling submodule, and a system management submodule.

[0021] Furthermore, by employing multi-module collaborative work, the accuracy and efficiency of disaster prediction and response are improved. First, the data acquisition module acquires multi-source meteorological and geographical environmental data in real time, ensuring the comprehensiveness and timeliness of the data and providing a solid foundation for disaster analysis. The data processing module cleans, stores, and performs preliminary analysis on the data, extracting key features to ensure data quality and reliability. The weight analysis module dynamically calculates disaster weights based on local climate characteristics and historical disaster data, accurately reflecting regional disaster risks and avoiding the limitations of traditional unified monitoring models. The intelligent analysis module conducts disaster prediction analysis based on weights and real-time meteorological data, providing customized early warning information to help relevant departments and the public take preventive measures in advance. The interface display module visually presents meteorological data and disaster risks, improving decision-making efficiency. The auxiliary module ensures the efficient operation of the system and the optimized allocation of emergency resources through databases, early warning issuance, resource scheduling, and system management. This system, through its accuracy, flexibility, and real-time performance, enhances disaster prevention and mitigation capabilities, reducing economic losses and casualties caused by disasters.

[0022] Specifically, the data acquisition module collects meteorological data and geographical environment data; The meteorological data collection methods include sensor networks, drone monitoring, satellite remote sensing, and crowdsourced data. The sensor network specifically comprises: deploying high-precision meteorological sensors in key areas, with the meteorological sensors powered by natural energy sources based on the geographical environment; The drone monitoring specifically involves: regularly monitoring remote or high-risk areas to obtain terrain and land use data, and monitoring local weather conditions by carrying sensors. The satellite remote sensing is used for large-scale monitoring of meteorological and geographical environments, including cloud images, precipitation distribution, and wind speed and direction; The aforementioned public crowdsourced data specifically refers to setting up a mobile application or website that allows the public to upload local meteorological observation data.

[0023] Furthermore, sensor networks deploy high-precision meteorological sensors in key areas, powered by natural energy sources, to monitor key meteorological parameters such as temperature, humidity, and wind speed in real time, ensuring data continuity and reliability. Unmanned aerial vehicles (UAVs) regularly monitor remote or high-risk areas, acquiring topographic, land use data, and local meteorological conditions to compensate for the shortcomings of traditional monitoring methods. Satellite remote sensing provides large-scale monitoring of cloud images, precipitation distribution, and wind speed and direction, offering macro-meteorological information and enhancing early warning capabilities for regional disasters. Crowdsourced data is collected from local meteorological observations uploaded by the public through mobile applications or websites, expanding data sources and improving data diversity and real-time performance. Utilizing multi-source data acquisition methods enhances the comprehensiveness and accuracy of the data. Simultaneously, it strengthens the system's adaptability to different geographical environments and climatic conditions, providing more scientific and timely data support for disaster prediction and prevention decisions, thereby improving the efficiency and effectiveness of disaster prevention and mitigation.

[0024] Specifically, the workflow of the data processing module is as follows: 1) Acquire raw meteorological, geographical environment, and historical data collected by the data acquisition module; 2) Perform data cleaning on the acquired data; 3) Using blockchain technology, the cleaned data is stored in a database and access is controlled in real time; 4) Perform preliminary statistical analysis on the cleaned data and extract key features; 5) Transfer the cleaned and preliminarily analyzed data to the weight analysis module and the intelligent analysis module; The preliminary statistical analysis of the cleaned data includes: statistical analysis, trend analysis, and spatial analysis.

[0025] Furthermore, firstly, data cleaning removes noise and outliers, improving data accuracy and consistency. Next, blockchain technology is used to store the cleaned data in a database, ensuring data security, traceability, and real-time access control to prevent data tampering and loss. Then, preliminary statistical analysis is performed on the cleaned data, including statistical analysis, trend analysis, and spatial analysis, extracting key features such as meteorological trends and geographical environmental risks to provide a scientific basis for subsequent analysis. Finally, the cleaned and preliminarily analyzed data is transmitted to the weighted analysis module and the intelligent analysis module to support accurate disaster prediction and decision-making. This process not only improves the efficiency and scientific rigor of data processing but also ensures high data quality and security, providing data support for disaster prevention and mitigation. Specifically, the workflow of the weight analysis module is as follows: 1) Input data, including historical meteorological data, historical disaster data, and geographical environment data; 2) Analyze climate characteristics and identify major disaster types; 3) Analyze geographical environmental data to assess disaster risks; 4) Dynamically calculate weights by combining meteorological and geographical environmental data; 5) Provides a weight adjustment interface, allowing administrators to manually adjust weight parameters; 6) Generate a weight matrix and transmit it to the intelligent analysis module.

[0026] Furthermore, firstly, the module inputs historical meteorological data, historical disaster data, and geographical environmental data to ensure the comprehensiveness and reliability of the basic data for analysis. Secondly, by analyzing climate characteristics, it identifies major disaster types, such as typhoons, droughts, or floods, clarifying the regional disaster characteristics. Next, combining geographical environmental data, it assesses disaster risks, such as the impact of topography on floods or the sensitivity of soil to drought. Then, it dynamically calculates weights, comprehensively considering meteorological and geographical environmental factors to generate a weight matrix reflecting regional disaster risks. In addition, the module provides a weight adjustment interface, allowing administrators to manually adjust weight parameters according to actual conditions, enhancing the system's flexibility and adaptability. Finally, the generated weight matrix is ​​transmitted to the intelligent analysis module, which not only improves the targeting and accuracy of disaster prediction but also enables the system to flexibly respond to the disaster characteristics of different regions, thereby significantly improving the efficiency and effectiveness of disaster prevention and mitigation and reducing the losses caused by disasters.

[0027] Specifically, the dynamic calculation of weights is as follows: The formula for the comprehensive weighting algorithm is:

[0028] in: These are the frequency, impact, and geographical environment weighting coefficients, respectively. And satisfy ; Disaster frequency weighting:

[0029] For the first The frequency of such disasters The total number of disaster types; Disaster impact weight:

[0030] For the first The impact of disasters, The total number of disaster types; Geographical environment weight:

[0031] For the first Geographical environmental risk scoring for disasters of this type The total number of disaster types; The The value is determined by the intelligent analysis module based on the optimization algorithm.

[0032] Furthermore, Specifically, the workflow of the intelligent analysis module is as follows: Data input: Obtain the various data output by the data processing module and the weight matrix output by the weight analysis module; Weight coefficient determination: Based on historical disaster data, the weight coefficients are determined and fed back to the weight analysis module; Disaster prediction and analysis: Disaster risk prediction is performed based on a weight matrix and real-time meteorological data; Output results: The prediction results are passed to the interface display module and the early warning release submodule.

[0033] Furthermore, firstly, weighting coefficients are determined using historical disaster data and fed back to the weighting analysis module to dynamically optimize weight calculations and improve prediction accuracy. Next, based on the weighting matrix and real-time meteorological data, disaster risk prediction is performed, outputting disaster type, probability of occurrence, and impact range, providing customized early warning information for different regions. Finally, the prediction results are transmitted to the interface display module and the early warning release submodule to visualize disaster risks and promptly release early warning information, helping relevant departments and the public to take preventative measures in advance. This prediction method based on weights and real-time data not only improves the accuracy and targeting of disaster early warnings but also optimizes the allocation and scheduling of emergency resources, significantly reducing economic losses and casualties caused by disasters.

[0034] Specifically, the determination of the weighting coefficients is as follows: Input historical disaster data: including disaster type, frequency of occurrence, degree of impact, geographical environmental risk score, and actual disaster occurrence; Eigenvectors: meteorological factors and geographical environmental factors; Target variable: Disaster occurrence; Using machine learning models for disaster risk prediction; Define the objective function: 1) Prediction results:

[0035] in, For the input feature vector, For machine learning models; 2) Objective function:

[0036] in: This refers to the actual occurrence of the disaster; For the predicted results; The number of samples; The regularization coefficient is used. 3) Cross-validation:

[0037] in, For the first Folding error; After optimizing the weight coefficients using the gradient descent algorithm, the optimal weight coefficients are output.

[0038] Furthermore, Specifically, the optimization of the weighting coefficients involves: Calculate the gradient of the objective function:

[0039] renew Value:

[0040]

[0041]

[0042] in: The learning rate; Constraints: ; Repeat the iteration until convergence.

[0043] Furthermore, the weight coefficient optimization algorithm, based on historical data analysis and machine learning optimization principles, enhances the accuracy and applicability of disaster risk prediction through multi-level improvements and optimizations. First, the algorithm utilizes historical disaster data to analyze the relative importance of disaster frequency, impact severity, and geographical environmental risks. Second, by introducing machine learning models and gradient descent, the weight coefficients are dynamically adjusted to adapt to the characteristics of disasters in different regions and time periods, avoiding the limitations of fixed weight coefficients in traditional methods. In addition, the algorithm incorporates regularization techniques to effectively prevent model overfitting by controlling the magnitude of the weight coefficients, improving the model's generalization ability, and ensuring stable performance on unknown data.

[0044] Meanwhile, cross-validation is employed to evaluate the model's average performance by repeatedly splitting the dataset, further enhancing the reliability and robustness of the results. This improves the algorithm's prediction accuracy, generalization ability, adaptability, scientific rigor, objectivity, and efficiency. A method for monitoring meteorological disaster prevention and mitigation processes, based on the aforementioned system, includes the following steps: S1, by deploying a data acquisition module, acquires meteorological and geographical environmental data in real time, and obtains historical disaster data; S2 preprocesses and performs preliminary analysis on the acquired data, and then transmits the processed data to the weight analysis module and the intelligent analysis module respectively. S3: Based on historical disaster data, determine the weighting coefficients, and then combine historical meteorological data, historical disaster data, geographical environment data, and weighting coefficients to dynamically analyze and output the weight matrix; S4, based on a weight matrix and real-time data, predicts the probability, type, and scope of a disaster. S5 will publish the prediction results through the interface display module and the early warning release sub-module.

[0045] Specifically, the process of outputting the weight matrix in step S3 is as follows: S31. The intelligent analysis module determines the weight coefficients through an optimization algorithm and transmits them to the weight analysis module. S32. The weighting analysis module identifies the main local disaster types and assesses the impact of the geographical environment on disaster risk. S33. Using a comprehensive weighting algorithm, calculate the disaster frequency weight, impact weight, and geographical environment weight to generate a weight matrix. S34. Provides an interface to support administrators in manually adjusting weight parameters. S35. Transmit the weight matrix to the intelligent analysis module for disaster prediction and analysis.

[0046] Furthermore, this method integrates multiple modules including data acquisition, preprocessing, weight analysis, intelligent prediction, and result display. First, by acquiring real-time meteorological and geographical environmental data, combined with historical disaster data, it provides a comprehensive and dynamic data foundation for the intelligent analysis module, ensuring the timeliness and accuracy of predictions. In the data preprocessing stage, the system cleans and performs preliminary analysis on the raw data to improve data quality and reduce the interference of noise and outliers, providing reliable input for subsequent weight analysis and intelligent prediction. In the weight analysis module, the system dynamically determines weight coefficients through optimization algorithms and, combined with historical data and geographical environmental factors, generates a weight matrix adapted to the disaster characteristics of different regions and time periods. This avoids the limitations of fixed weight coefficients in traditional methods. Simultaneously, it provides an interface for administrators to manually adjust weight parameters, increasing flexibility and practicality, allowing administrators to fine-tune according to actual conditions and further improve prediction accuracy.

[0047] Based on a weighted matrix and real-time data, the system can predict the probability, type, and scope of disasters, providing a scientific basis for disaster early warning, enabling the formulation of response strategies in advance, and effectively reducing disaster losses. Finally, the system publishes the prediction results intuitively and efficiently through an interface display module and an early warning release sub-module, improving information transparency and dissemination efficiency, and enhancing public awareness and participation in disaster prevention.

[0048] In summary, the weighted analysis module and intelligent analysis module enable accurate prediction and customized early warning of disaster risks in different regions, thereby improving disaster prevention and mitigation capabilities. Firstly, by analyzing historical data and geographical environment of different regions, the system calculates the weights for disaster analysis and generates a weight matrix, thus accurately reflecting local disaster risks. Furthermore, the system allows administrators to manually adjust weight parameters, further enhancing its flexibility and adaptability. Secondly, the intelligent analysis module predicts disaster risks based on the weight matrix and real-time meteorological data, outputting the probability, type, and scope of disaster occurrence. By combining weight analysis and real-time data, it provides customized disaster early warning information, offering accurate warnings to different regions and helping relevant departments and the public to take preventive measures in advance. In addition, the intelligent analysis module dynamically adjusts the weight coefficients through algorithm optimization to ensure the scientific validity and reliability of the prediction results.

[0049] By working together with the weighting analysis module and the intelligent analysis module, accurate identification and customized early warning of disaster risks in different regions can be achieved, which not only improves the efficiency and effectiveness of disaster prevention and mitigation, but also avoids the limitations of the traditional unified monitoring model.

[0050] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A meteorological disaster prevention and mitigation process monitoring system, characterized in that: The system comprises a data acquisition module, a real-time meteorological data acquisition and local geographical environment data acquisition module, a data processing module, a weight analysis module, an intelligent analysis module, an interface display module, and an auxiliary module. The data acquisition module acquires meteorological data and geographical environment data. The meteorological data acquisition method comprises a sensor network, unmanned aerial vehicle monitoring, satellite remote sensing, and public crowdsourcing data. The sensor network comprises high-precision meteorological sensors deployed in key areas, which are powered by natural energy according to the geographical environment. The unmanned aerial vehicle monitoring comprises regular monitoring of remote areas or high-risk areas to obtain terrain and land use data and monitoring local meteorological conditions by carrying sensors. The satellite remote sensing is used for large-scale monitoring of meteorological and geographical environment, including cloud images, precipitation distribution, and wind speed and direction.

2. The weather disaster prevention and mitigation process monitoring system according to claim 1, characterized in that: The public crowdsourcing data is obtained by setting up a mobile application or website for public uploading of local meteorological observation data. The data processing module comprises the following steps: 1) obtaining raw meteorological, geographical environment data and historical data collected by the data acquisition module; 2) data cleaning; 3) storing the cleaned data in the database through blockchain technology and real-time access control; 4) preliminary statistical analysis of the cleaned data to extract key features; 3. The weather disaster prevention and mitigation process monitoring system according to claim 1, characterized in that: 5) transmitting the cleaned and preliminarily analyzed data to the weight analysis module and the intelligent analysis module. The preliminary statistical analysis of the cleaned data comprises statistical analysis, trend analysis, and spatial analysis. The weight analysis module comprises the following steps: 1) inputting data, including historical meteorological data, historical disaster data, and geographical environment data; 2) analyzing climate characteristics and identifying main disaster types; 3) analyzing geographical environment data and assessing disaster risk; 4) dynamically calculating weights based on meteorological data and geographical environment data; 4. The weather disaster prevention and mitigation process monitoring system according to claim 1, characterized in that: 5) providing a weight adjustment interface to support manual adjustment of weight parameters by administrators; 6) generating a weight matrix and transmitting it to the intelligent analysis module. The intelligent analysis module comprises the following steps: Data input: obtaining various data output by the data processing module and the weight matrix output by the weight analysis module; Weight coefficient determination: determining the weight coefficient based on historical disaster data and feeding it back to the weight analysis module; Disaster prediction analysis: predicting disaster risk based on the weight matrix and real-time meteorological data; Result output: transmitting the prediction results to the interface display module and the warning release submodule.

5. The weather disaster prevention and mitigation process monitoring system according to claim 1, characterized in that: The weight coefficient determination comprises the following steps: Inputting historical disaster data, including disaster type, frequency, impact, geographical environment risk score, and actual disaster occurrence; Feature vector: meteorological factors and geographical environment factors; ​ ​ 6. The weather disaster prevention and mitigation process monitoring system according to claim 5, characterized in that: ​ ​ ​ Target variable: disaster occurrence; Disaster risk prediction using machine learning model; Optimizing the weight coefficient through gradient descent algorithm, and outputting the optimal weight coefficient.

7. The weather disaster prevention and mitigation process monitoring system according to claim 6, characterized in that: The optimization of the weight coefficient is specifically: Calculating the gradient of the objective function; Repeat iteration until convergence.

8. A weather disaster prevention and mitigation process monitoring method, characterized in that: The method based on the system of claims 1-7, comprising the following steps: S1, by deploying a data acquisition module, real-time acquisition of meteorological data and geographical environment data, and acquisition of historical disaster data; S2, pre-processing and preliminary analysis of the obtained data, and transmitting the processed data to the weight analysis module and the intelligent analysis module respectively; S3, according to the historical disaster data, determine the weight coefficient, and combine the historical meteorological data, historical disaster data, geographical environment data and weight coefficient, dynamically analyze and output the weight matrix; S4, based on the weight matrix and real-time data, predict the probability, type and influence range of disaster occurrence; S5, the prediction result is published through the interface display module and the early warning release submodule.

9. The weather disaster prevention and mitigation process monitoring method according to claim 8, characterized in that: The specific process of outputting the weight matrix in step S3 is: S31, the intelligent analysis module determines the weight coefficient through optimization algorithm, and transmits it to the weight analysis module; S32, the weight analysis module identifies the main disaster types and evaluates the influence of geographical environment on disaster risk S33, through the comprehensive weight algorithm, calculate the disaster frequency weight, influence weight and geographical environment weight, generate the weight matrix S34, provide interface support for administrators to manually adjust weight parameters S35, the weight matrix is transmitted to the intelligent analysis module for disaster prediction analysis.

Images