Meteorological disaster risk assessment method and system based on disaster risk grading

Abstract

The invention discloses a meteorological disaster risk assessment method and system based on disaster risk grading, and belongs to the technical field of meteorological disaster assessment, and the method specifically comprises the steps: collecting the meteorological and disaster-bearing body data and geographic information of a disaster area, and carrying out the preprocessing through a spatial interpolation method; setting meteorological disaster-inducing factors, disaster-pregnant environments and disaster-bearing body vulnerability indexes, and constructing a judgment matrix and distributing index weights by using an analytic hierarchy process; constructing a disaster risk grading model according to the risk indexes and the corresponding weights, inputting data of the to-be-evaluated region, calculating a risk value, judging a risk grade, and generating a report; establishing a real-time monitoring system, updating a risk assessment result, and issuing early warning information when a risk value reaches an early warning threshold value; according to the invention, through comprehensive analysis and real-time monitoring, the accuracy and timeliness of meteorological disaster risk assessment are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of meteorological disaster assessment, and specifically relates to a meteorological disaster risk assessment method and system based on disaster risk grading. Background Art

[0002] For meteorological disasters such as rainstorms, floods, droughts, typhoons, cold snaps, etc., accurately assessing meteorological disaster risks can help formulate disaster prevention and mitigation measures in advance and allocate resources reasonably. However, existing meteorological disaster risk assessment methods often have problems such as a single assessment index, insufficient consideration of vulnerability differences in different regions, and lack of a dynamic update mechanism, resulting in inaccurate and impractical assessment results and being difficult to meet the actual disaster prevention and mitigation needs.

[0003] For example, the Chinese patent application with the publication number CN118350630A applied a meteorological disaster risk assessment and prevention method based on artificial intelligence, including: data collection and processing, which collects multi-source data of historical meteorological data, topographic and geomorphic data, and social and economic data, and performs data cleaning and standardization processing on it; feature extraction, using deep learning algorithms to extract key features related to meteorological disaster risks from the processed data; model construction, constructing a meteorological disaster risk assessment model based on the extracted key features; risk assessment, inputting real-time meteorological data into the constructed model. By using deep learning algorithms to process and analyze multi-source data, it can extract key features related to meteorological disaster risks, achieve refined risk assessment, and accurately reflect the true risks of disasters.

[0004] For example, the Chinese patent application with the publication number CN116911606A disclosed a comprehensive risk assessment method for transmission lines under multiple meteorological disasters, including: obtaining the basic information of the target transmission line, establishing data statistics and fault prediction models, risk probability valuation, determination of risk weights, determination of risk consequences, determination of comprehensive risk values, and division of risk levels; this technical solution can assess the fault risks of transmission lines affected by multiple meteorological factors and improve the operation reliability of transmission lines.

[0005] The above existing technologies all have the following problems: poor model generalization ability; poor adaptability of risk assessment results; high cost. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention proposes a meteorological disaster risk assessment method and system based on disaster risk grading, which collects meteorological data, disaster-bearing body data and geographical information of the disaster area and preprocesses them using spatial interpolation method; sets meteorological disaster-causing factor, disaster-forming environment and disaster-bearing body vulnerability indicators, constructs a judgment matrix using the analytic hierarchy process and assigns weights to the indicators; constructs a disaster risk grading model based on the risk indicators and corresponding weights, inputs the data of the area to be evaluated, calculates the risk value and determines the risk level, and generates a report; establishes a real-time monitoring system to update the risk assessment results, and issues a warning message when the risk value reaches the warning threshold; through comprehensive analysis and real-time monitoring, the present application improves the accuracy and timeliness of meteorological disaster risk assessment.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A meteorological disaster risk assessment method based on disaster risk grading, comprising:

[0009] Step S1: Collect meteorological data, disaster-bearing body data and geographical information of the disaster area, and preprocess them using spatial interpolation method;

[0010] Step S2: Set meteorological disaster-causing factor indicators, disaster-forming environment indicators and disaster-bearing body vulnerability indicators, and construct a judgment matrix according to the comparison results of pairwise indicators using the analytic hierarchy process, and assign weights to different indicators by solving the judgment matrix;

[0011] Step S3: Construct a disaster risk grading model based on the indicators and corresponding weights, input the meteorological data, disaster-bearing body data and geographical information of the area to be evaluated into the disaster risk grading model, obtain the meteorological disaster risk value of the area to be evaluated, and automatically judge the risk level to which the area to be evaluated belongs according to the calculated meteorological disaster risk value in combination with the preset risk warning threshold, and generate a risk assessment report;

[0012] Step S4: Establish a real-time meteorological data monitoring system, monitor meteorological data in real time, regularly update the disaster risk assessment results, and issue a meteorological disaster warning message when the meteorological disaster risk value is greater than or equal to the preset risk warning threshold.

[0013] Specifically, the specific steps of the step S1 include:

[0014] S1.1: Collect meteorological data, disaster-bearing body data and geographical information of the disaster area, and form disaster risk assessment data Z = {z 1 ,..., z n} through integration, and the coordinates corresponding to each disaster risk assessment data z i are (x i , y i ), i = 1, 2,..., n, where z iDenote the i-th disaster risk assessment data, and n represents the quantity of disaster risk assessment data;

[0015] S1.2: Use to interpolate and supplement Z to generate the processed disaster risk assessment data. Among them, G(x, y) represents the estimated value of the unknown point (x, y), (x, y) represents the coordinates of the point to be interpolated, and β i represents the weight adjustment factor of the i-th disaster risk assessment data point, and f(θ i ) represents the direction sensitivity function, and θ i represents the angle between the line connecting the unknown point (x, y) and the known disaster risk assessment data point i and the reference direction, and d i represents the Euclidean distance between the unknown point (x, y) and the known disaster risk assessment data point i, and σ i represents the local coefficient of variation, and G i represents the value of the known disaster risk assessment data point i, and p represents the distance decay parameter.

[0016] Specifically, the specific steps of step S2 include:

[0017] S2.1: Determine the overall goal of meteorological disaster risk assessment, divide the meteorological disaster risk assessment problem into an objective layer, a criterion layer, and an index layer, and refine the indicators in the criterion layer. The objective layer is meteorological disaster risk assessment, the criterion layer is meteorological hazard factor indicators, disaster-bearing environment indicators, and vulnerability indicators of disaster-bearing bodies, and the index layer is preventive measures;

[0018] S2.2: Arrange the objective layer, criterion layer, and index layer in sequence from top to bottom, use lines to indicate the hierarchical subordination relationship, and construct a hierarchical structure model;

[0019] S2.3: Make pairwise comparisons of the indicators within the criterion layer, and use the 1-9 scale method to quantify the relative importance between the indicators. Based on the quantification results, construct a judgment matrix A = (a jk ), where a jk represents the importance degree of indicator j relative to indicator k.

[0020] Specifically, the specific steps of step S2 also include:

[0021] S2.4: According to the judgment matrix A = (a jk ), calculate the maximum eigenvalue λ max of A and its corresponding eigenvector W = (w 1 ,..., w m ), where w m represents the preliminary weight allocation of the m-th indicator, and m represents the number of indicators;

[0022] S2.5: Calculate the consistency ratio CR;

[0023] If CR < h 1 , it indicates that the judgment matrix A = (a jk ) has consistency, and the elements w 1 ,..., w m in the eigenvector W = (w m ) are used as the weights of each index;

[0024] If CR ≥ h 1 , the judgment matrix is readjusted, where h 1 represents the consistency threshold.

[0025] Specifically, the specific steps of step S3 include:

[0026] S3.1: Obtain meteorological disaster-causing factor indicators, disaster-bearing environment indicators, vulnerability indicators of disaster-affected bodies, and their corresponding weights;

[0027] S3.2: Load the pre-constructed weighted comprehensive scoring model, configure the parameters of the weighted comprehensive scoring model according to the meteorological disaster-causing factor indicators, disaster-bearing environment indicators, vulnerability indicators of disaster-affected bodies, and their corresponding weights, and use the pre-collected historical disaster data to train the configured weighted comprehensive scoring model to obtain a disaster risk grading model;

[0028] S3.3: Collect disaster risk assessment data of the area to be evaluated and perform preprocessing;

[0029] S3.4: Input the preprocessed disaster risk assessment data into the disaster risk grading model, and run the disaster risk grading model to calculate the meteorological disaster risk value of the area to be evaluated;

[0030] S3.5: Based on the statistics of historical disaster data and the disaster prevention and mitigation capabilities of the area, divide different risk level ranges and set corresponding thresholds;

[0031] S3.6: Compare the calculated meteorological disaster risk value with the preset risk warning threshold to determine the risk level to which the area to be evaluated belongs;

[0032] S3.7: Generate a risk assessment report using text templates and data visualization techniques. The content of the risk assessment report includes basic information of the area to be evaluated, input meteorological data and geographical information, numerical values and weights of each index, risk calculation process and results, basis for risk level determination, potential disaster consequences, and disaster prevention and mitigation suggestions.

[0033] Specifically, the meteorological disaster-causing factor indicators include the maximum wind force of a typhoon, the lowest central air pressure of a typhoon, and the process rainfall; the disaster-bearing environment indicators include the terrain slope and the distance from the coastline; the vulnerability indicators of the disaster-affected bodies include the population density, the wind resistance level of buildings, and the intact rate of infrastructure.

[0034] A meteorological disaster risk assessment system based on disaster risk classification includes: a data processing module, an indicator construction module, a model construction module, and an early warning module;

[0035] The data processing module is used to collect various types of basic data and preprocess the collected data;

[0036] The indicator construction module is used to evaluate various indicators of meteorological disaster risks and assign the weights of each indicator in the evaluation;

[0037] The model construction module is used to construct a disaster risk classification model according to the determined indicators and weights, and use the disaster risk classification model to conduct a risk assessment on the area to be evaluated, generate a meteorological disaster risk value and the corresponding risk level, and generate a risk assessment report at the same time;

[0038] The early warning module is used to establish a real-time meteorological data monitoring mechanism, detect meteorological data, regularly update the disaster risk assessment results, and issue a warning message when the meteorological disaster risk value exceeds the risk warning threshold.

[0039] Specifically, the indicator construction module includes: an indicator construction unit and an analytic hierarchy process unit;

[0040] The indicator construction unit is used to construct a disaster risk assessment indicator system for different types of meteorological disasters;

[0041] The analytic hierarchy process unit is used to adopt the analytic hierarchy process method, construct a judgment matrix through the comparison results of pairwise indicators, solve the judgment matrix to obtain the weights of each indicator, and conduct a consistency test.

[0042] Specifically, the model construction module includes: a model construction unit and a risk assessment unit;

[0043] The model construction unit is used to construct a disaster risk classification model according to the indicators and the corresponding weights;

[0044] The risk assessment unit is used to input the data of the area to be evaluated into the disaster risk classification model, calculate the meteorological disaster risk value, and combine it with the preset risk warning threshold to judge the risk level to which the area to be evaluated belongs.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] 1. The present invention proposes a meteorological disaster risk assessment system based on disaster risk classification, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0047] 2. The present invention proposes a meteorological disaster risk assessment method based on disaster risk classification. By systematically collecting and processing meteorological data, disaster-prone body data and geographic information in the disaster-stricken area, and introducing the hierarchical analysis method to determine the importance weight of each risk indicator, a scientific and comprehensive disaster risk classification model is constructed. The model can accurately assess the meteorological disaster risk value of the area to be assessed and automatically determine the risk level to which it belongs, which helps to improve the efficiency and accuracy of disaster prevention and emergency response.

[0048] 3. The present invention proposes a meteorological disaster risk assessment method based on disaster risk classification, and also establishes a real-time meteorological data monitoring system that can monitor meteorological data in real time and regularly update the disaster risk assessment results; when the risk value reaches or exceeds the preset warning threshold, the system will promptly issue meteorological disaster warning information, thereby effectively warning and preventing meteorological disasters, and improving the prevention and response capabilities of meteorological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of a meteorological disaster risk assessment method based on disaster risk classification of the present invention;

[0050] Figure 2 This is a principle flow chart of a meteorological disaster risk assessment method based on disaster risk classification according to the present invention;

[0051] Figure 3 This is an architecture diagram of the meteorological disaster risk assessment system based on disaster risk classification of the present invention. DETAILED DESCRIPTION

[0052] Example 1

[0053] See also Figure 1 and Figure 2 The present invention provides an embodiment: a meteorological disaster risk assessment method based on disaster risk classification, comprising the following steps:

[0054] Step S1: Collect meteorological data, disaster-affected body data and geographic information of the disaster-affected area, and use spatial interpolation method for preprocessing;

[0055] Among them, the meteorological data of the disaster-stricken areas include time series data of various meteorological elements such as temperature, humidity, wind speed, precipitation, etc.; the geographical information includes topography, altitude, river system distribution, and land use type; the disaster-prone body data includes population density distribution, building types and distribution, infrastructure conditions, and crop planting areas and types.

[0056] Step S2: Set meteorological disaster-causing factor indicators, disaster-bearing environment indicators, and disaster-affected body vulnerability indicators, and use the analytic hierarchy process to construct a judgment matrix based on the comparison results of pairwise indicators, and allocate weights to different indicators by solving the judgment matrix;

[0057] The meteorological disaster-causing factor indicators include the maximum wind force of typhoons, the lowest central pressure of typhoons, and the process rainfall; the disaster-bearing environment indicators include the terrain slope and the distance from the coastline; the disaster-affected body vulnerability indicators include the population density, the wind resistance capacity level of buildings, and the intact rate of infrastructure.

[0058] Step S3: Construct a disaster risk grading model based on the indicators and their corresponding weights, input the meteorological data, disaster-affected body data, and geographical information of the area to be evaluated into the disaster risk grading model, obtain the meteorological disaster risk value of the area to be evaluated, and automatically judge the risk level to which the area to be evaluated belongs according to the calculated meteorological disaster risk value, and generate a risk assessment report in combination with the preset risk warning threshold;

[0059] Step S4: Establish a real-time meteorological data monitoring system to monitor meteorological data in real time, regularly update the disaster risk assessment results, and issue meteorological disaster warning information when the meteorological disaster risk value is greater than or equal to the preset risk warning threshold.

[0060] Among them, when the meteorological disaster risk value is greater than or equal to the risk warning threshold, trigger the warning mechanism and issue meteorological disaster warning information in a timely manner through means such as text messages, emails, and application notifications.

[0061] Exemplarily, collect the typhoon meteorological data of a city in the past 50 years, including typhoon paths, wind forces, wind speeds, rainfall, etc.; obtain the geographical information data of the city, such as terrain elevation, coastline length, river distribution, etc.; count the data of disaster-bearing bodies, and clean and preprocess these data to remove outliers and incorrect data; for typhoon disasters, select the following risk indicators: disaster-causing factor indicators: maximum typhoon wind force, minimum central pressure of the typhoon, process rainfall; disaster-forming environment indicators: terrain slope, distance from the coastline; vulnerability indicators of disaster-bearing bodies: population density, wind resistance level of buildings, integrity rate of infrastructure; use the analytic hierarchy process to determine the weights of each indicator, compare and score the relative importance of each indicator pairwise, and construct a judgment matrix; by calculating the maximum eigenvalue of the judgment matrix and its corresponding eigenvector, and conducting a consistency test, obtain the weight values of each indicator, and then formulate a typhoon disaster risk grading standard according to the historical typhoon disaster loss situation of the city, as shown in Table 1; construct a typhoon disaster risk grading model, and then substitute the actual data of each region of the city into the typhoon disaster risk grading model to calculate the typhoon disaster risk value of each region; display the evaluation results in the form of a map, mark different risk level regions with different colors, and at the same time generate a detailed risk assessment report, including the risk indicator values, disaster risk values, risk levels of each region, and corresponding disaster prevention and mitigation suggestions.

[0062] Table 1 Typhoon Disaster Risk Grading Standard

[0063]

[0064] The specific steps of step S1 include:

[0065] S1.1: Collect meteorological data, disaster-bearing body data and geographical information of the disaster area, and integrate them to form disaster risk assessment data Z = {z 1 ,..., z n}, and the coordinates corresponding to each disaster risk assessment data z i are (x i , y i ), i = 1, 2,..., n, where z i represents the i-th disaster risk assessment data, and n represents the number of disaster risk assessment data;

[0066] S1.2: Use to interpolate and supplement Z to generate processed disaster risk assessment data, where G(x, y) represents the estimated value of the unknown point (x, y), (x, y) represents the coordinates of the point to be interpolated, β i represents the weight adjustment factor of the i-th disaster risk assessment data point, f(θ i ) represents the direction sensitivity function, and θ iDenote the angle between the line connecting the unknown point (x, y) and the known disaster risk assessment data point i and the reference direction, d i Denote the Euclidean distance between the unknown point (x, y) and the known disaster risk assessment data point i, σ i Denote the local coefficient of variation, G i Denote the value of the known disaster risk assessment data point i, and p represents the distance attenuation parameter.

[0067] It should be understood that in the present invention, the modified formula G(x, y) by introducing the weight adjustment factor β i , the direction sensitivity function f(θ i ) and the local coefficient of variation σ i , significantly enhances the flexibility and accuracy of spatial interpolation, and can more finely consider the contribution degree of different known points to the interpolation result of the unknown point, the influence of direction on interpolation, and the variation characteristics of local data, so as to generate a more reliable and practical interpolation result.

[0068] The specific steps of step S2 include:

[0069] S2.1: Determine the overall goal of meteorological disaster risk assessment, divide the meteorological disaster risk assessment problem into an objective layer, a criterion layer, and an index layer, and refine the indicators in the criterion layer. The objective layer is meteorological disaster risk assessment, the criterion layer is meteorological disaster-causing factor indicators, disaster-bearing environment indicators, and vulnerability indicators of disaster-affected bodies, and the index layer is preventive measures;

[0070] Furthermore, the specific steps of S2.1 include:

[0071] (1) Clearly define the overall goal of meteorological disaster risk assessment, such as reducing the impact of meteorological disasters on social economy and people's lives, and improving the prevention and response capabilities of meteorological disasters;

[0072] (2) Divide the meteorological disaster risk assessment problem into an objective layer, a criterion layer, and an index layer;

[0073] (3) Refine the criterion layer indicators: conduct in-depth research and analysis on each indicator in the criterion layer, determine its specific content and elements, and select corresponding indicators according to the characteristics of meteorological disasters and assessment requirements to reflect the specific situation of each criterion layer;

[0074] (4) Organize the refined indicators according to the hierarchical structure to form a complete meteorological disaster risk assessment system, and determine the weight and scoring criteria of each indicator for subsequent quantitative assessment.

[0075] S2.2: Arrange the objective layer, criterion layer, and index layer in sequence from top to bottom, use lines to indicate the hierarchical subordination relationship, and construct a hierarchical structure model;

[0076] S2.3: Pairwise comparison of the indicators within the criterion layer, and use the 1-9 scale method to quantify the relative importance between the indicators. Based on the quantification results, construct a judgment matrix A = (a jk ) according to the number of indicators in the criterion layer, where a jk represents the degree of importance of indicator j relative to indicator k, and the specific scaling process is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0077] Among them, the 1-9 scale method is a commonly used quantification method, where 1 means that two indicators are equally important, 3 means that one indicator is slightly more important than the other, 5 means that one indicator is significantly more important than the other, 7 means that one indicator is strongly more important than the other, 9 means that one indicator is extremely more important than the other, and 2, 4, 6, and 8 respectively represent the intermediate values between adjacent levels. Exemplarily, if the degree of importance of indicator A relative to indicator B is u, (1 ≤ u ≤ 9), then a AB = u,

[0078] S2.4: According to the judgment matrix A = (a jk ), calculate the maximum eigenvalue λ max of A and its corresponding eigenvector W = (w 1 ,..., w m ), where w m represents the preliminary weight allocation of the m-th indicator, and m represents the number of indicators. Among them, the solution of the matrix is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0079] S2.5: Calculate the consistency ratio

[0080] If CR < h 1 , it means that the judgment matrix A = (a jk ) has consistency, and the elements w 1 ,..., w m in the eigenvector W = (w m ) are used as the weights of each indicator;

[0081] Among them, the meaning that the judgment matrix has consistency is that: in the judgment matrix, the relationship between each element a jk is coordinated and consistent, and there is no logical contradiction; by calculating the consistency ratio, it can be determined whether the judgment matrix meets certain accuracy requirements. If the judgment matrix has consistency, then the weight allocation result calculated based on this matrix reflects the true importance relationship between the indicators.

[0082] If CR ≥ h 1, it indicates that the judgment matrix needs to be readjusted. Among them, RI represents the average random consistency index, which is found from a pre-determined table according to the order of the judgment matrix, and h 1 represents the consistency threshold, and h 1 = 0.1.

[0083] The specific steps of step S3 include:

[0084] S3.1: Obtain meteorological disaster-causing factor indicators, disaster-bearing environment indicators, vulnerability indicators of disaster-affected bodies, and their corresponding weights;

[0085] S3.2: Load the pre-constructed weighted comprehensive scoring model, configure the parameters of the weighted comprehensive scoring model according to the meteorological disaster-causing factor indicators, disaster-bearing environment indicators, vulnerability indicators of disaster-affected bodies, and their corresponding weights, and use the pre-collected historical disaster data to train the configured weighted comprehensive scoring model to obtain a disaster risk grading model. Among them, the weighted comprehensive scoring model is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0086] S3.3: Collect disaster risk assessment data of the area to be evaluated and perform preprocessing;

[0087] S3.4: Input the preprocessed disaster risk assessment data in the format required by the disaster risk grading model, and run the disaster risk grading model to calculate the meteorological disaster risk value of the area to be evaluated;

[0088] S3.5: Based on the statistics of historical disaster data and the disaster prevention and mitigation capabilities of the area, divide different risk level ranges and set corresponding thresholds;

[0089] Among them, the disaster prevention and mitigation capabilities of the area need to consider the existing emergency rescue material reserves, the perfection degree of the personnel evacuation plan, and the anti-disaster reinforcement of infrastructure; dividing different risk level ranges includes: for example, low risk 0-20, relatively low risk 21-40, medium risk 41-60, relatively high risk 61-80, high risk 81-100.

[0090] S3.6: Compare the calculated meteorological disaster risk value with the preset risk warning threshold to determine the risk level to which the area to be evaluated belongs;

[0091] S3.7: Generate a risk assessment report using text templates and data visualization techniques. The content of the risk assessment report includes the basic information of the area to be evaluated, the input meteorological data and geographical information, the values and weights of each indicator, the risk calculation process and results, the basis for risk level determination, the possible disaster consequences, and disaster prevention and mitigation suggestions. Among them, the text templates and data visualization techniques are the prior art content in this field and are not the creative solution of this application, so it will not be elaborated here.

[0092] Example 2

[0093] See also Figure 3 Another embodiment provided by the present invention is a meteorological disaster risk assessment system based on disaster risk classification, comprising:

[0094] Data processing module, indicator building module, model building module, and early warning module;

[0095] The data processing module is used to collect various basic data and pre-process the collected data to provide a high-quality data source for subsequent assessment work. The various basic data include meteorological data of the disaster-affected area, disaster-bearing body data and geographic information;

[0096] Among them, meteorological data collection is to collect real-time and historical data of meteorological elements such as temperature, precipitation, wind speed, wind direction, humidity, etc. through various channels such as meteorological observation stations distributed in the disaster-stricken areas, satellite remote sensing, meteorological radar, etc. These data reflect the meteorological conditions when the disaster occurred; disaster-prone body data collection is to collect population density, building types, infrastructure conditions, crop planting areas and varieties, etc. through channels such as urban planning archives and field surveys, which are used to measure the characteristics of objects that may suffer losses when disasters occur; geographic information collection is to obtain geographical data such as topography, river system distribution, soil type, and land use status from surveying and mapping departments and satellite image data with the help of geographic information system technology. These geographical factors will affect the formation, development, and degree of harm of meteorological disasters.

[0097] The indicator construction module is used to evaluate various indicators of meteorological disaster risks and allocate weights to each indicator in the overall assessment to ensure that the assessment results can accurately reflect the actual risk situation;

[0098] The model building module is used to build a disaster risk classification model based on the determined indicators and weights, and use the disaster risk classification model to conduct risk assessment on the area to be assessed, generate specific meteorological disaster risk values ​​and corresponding risk levels, and generate an intuitive risk assessment report;

[0099] The early warning module is used to establish a continuous real-time meteorological data monitoring mechanism, detect meteorological data, and regularly update disaster risk assessment results. When the meteorological disaster risk value exceeds the risk warning threshold, early warning information is quickly issued to relevant personnel and institutions to buy time for disaster prevention and mitigation.

[0100] The data processing module includes: a data collection unit and a spatial interpolation unit;

[0101] Data collection unit, used to collect meteorological data, disaster-bearing body data and geographic information of the disaster-affected area from meteorological stations, satellites and geographic information systems;

[0102] A spatial interpolation unit, which is used to preprocess the collected data by using the spatial interpolation method to fill data gaps or improve data resolution.

[0103] The index construction module includes: an index construction unit and an analytic hierarchy process unit;

[0104] The index construction unit is used to construct a disaster risk assessment index system for different types of meteorological disasters;

[0105] The analytic hierarchy process unit is used to adopt the analytic hierarchy process method, construct a judgment matrix through the comparison results of pairwise indexes, solve the judgment matrix to obtain the weights of each index, and conduct a consistency test to ensure the rationality of weight distribution, avoid subjective randomness, and enable the index weights to accurately reflect the contribution degree of each factor to the disaster risk.

[0106] The model construction module includes: a model construction unit, a risk assessment unit, and a report generation unit;

[0107] The model construction unit is used to construct a disaster risk grading model according to the indexes and corresponding weights. The input of the model is the index values corresponding to the preprocessed meteorological, geographical and other data. Through the internal operation logic of the model, it outputs a quantitative score reflecting the meteorological disaster risk degree of the region;

[0108] The risk assessment unit is used to input the data of the region to be evaluated into the disaster risk grading model, calculate the meteorological disaster risk value, and combine the preset risk warning threshold to judge the risk level of the region to be evaluated;

[0109] The report generation unit is used to generate a detailed risk assessment report by using the text template and data visualization technology according to the meteorological disaster risk value, risk level obtained by the risk assessment unit and the basic data input into the model. The content of the risk assessment report covers the basic information of the region, the values of each index, the risk calculation process, the basis for risk level determination, the possible disaster consequences and disaster prevention and mitigation suggestions, etc.

[0110] The early warning module includes: a real-time monitoring unit, a risk assessment update unit, and an early warning information release unit;

[0111] The real-time monitoring unit is used to construct a real-time meteorological data monitoring system by using highly sensitive meteorological monitoring equipment to monitor meteorological data in real time to ensure the timeliness and accuracy of the data;

[0112] The risk assessment update unit is used to regularly update the disaster risk assessment results according to the real-time monitoring data to reflect the latest disaster risk situation;

[0113] The early warning information release unit is responsible for timely releasing meteorological disaster early warning information when the risk value reaches or exceeds the preset risk early warning threshold. It releases meteorological disaster early warning information to the target audience through multiple channels such as the SMS mass sending platform, the emergency broadcast system, the e-government platform, and the official social media accounts. The content of the early warning information includes the type of disaster, the expected affected area, the risk level, and the recommended preventive measures to ensure the timeliness and effectiveness of information transmission and minimize disaster losses.

[0114] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make changes, modifications, substitutions, and variations to the above embodiments without departing from the purpose and scope of the present invention, and these all fall within the protection scope of the present invention.

Claims

1. A meteorological disaster risk assessment method based on disaster risk classification, characterized in that: include: Step S1: Collect meteorological data, disaster-affected body data and geographic information of the disaster-affected area, and use spatial interpolation method for preprocessing; Step S2: Set meteorological disaster factor indicators, disaster-prone environment indicators and disaster-bearing body vulnerability indicators, and use the hierarchical analysis method to construct a judgment matrix based on the comparison results of each indicator, and assign weights to different indicators by solving the judgment matrix; Step S3: construct a disaster risk classification model based on the indicators and corresponding weights, and input the meteorological data, disaster-prone body data and geographic information of the area to be assessed into the disaster risk classification model to obtain the meteorological disaster risk value of the area to be assessed. According to the calculated meteorological disaster risk value and the preset risk warning threshold, automatically determine the risk level of the area to be assessed, and generate a risk assessment report; Step S4: Establish a real-time meteorological data monitoring system, monitor meteorological data in real time, regularly update disaster risk assessment results, and issue meteorological disaster warning information when the meteorological disaster risk value is greater than or equal to the preset risk warning threshold.

2. The meteorological disaster risk assessment method based on disaster risk classification according to claim 1, characterized in that: The specific steps of step S1 include: S1.1: Collect meteorological data, disaster-prone data and geographic information of the disaster-affected area, and integrate them to form disaster risk assessment data Z = {z1,...,z n }, and each disaster risk assessment data z i The corresponding coordinates are (x i ,y i ),i=1,2,...,n, where z i represents the i-th disaster risk assessment data, and n represents the number of disaster risk assessment data; S1.2: Use Interpolate and supplement Z to generate processed disaster risk assessment data, where G(x,y) represents the estimated value of the unknown point (x,y), (x,y) represents the coordinates of the point to be interpolated, and β i represents the weight adjustment factor of the i-th disaster risk assessment data point, f(θ i ) represents the directional sensitivity function, θ i represents the angle between the line connecting the unknown point (x, y) and the known disaster risk assessment data point i and the reference direction, d i represents the Euclidean distance between the unknown point (x, y) and the known disaster risk assessment data point i, σ i represents the local coefficient of variation, G i represents the value of the known disaster risk assessment data point i, and p represents the distance attenuation parameter.

3. The meteorological disaster risk assessment method based on disaster risk classification according to claim 2, characterized in that: The specific steps of step S2 include: S2.1: Determine the overall goal of meteorological disaster risk assessment, divide the meteorological disaster risk assessment problem into the target layer, the criterion layer and the indicator layer, and refine the indicators in the criterion layer. The target layer is the meteorological disaster risk assessment, the criterion layer is the meteorological disaster factor index, the disaster-prone environment index, and the disaster-bearing body vulnerability index, and the indicator layer is the preventive measures; S2.2: Arrange the target layer, criterion layer, and indicator layer from top to bottom, use connecting lines to indicate the hierarchical affiliation, and construct a hierarchical structure model; S2.3: Compare the indicators in the criterion layer in pairs, and use the 1-9 scale method to quantify the relative importance of the indicators. Based on the quantification results, the judgment matrix A is constructed according to the number of indicators in the criterion layer. jk ), where a jk Indicates the importance of indicator j relative to indicator k.

4. The meteorological disaster risk assessment method based on disaster risk classification according to claim 3, characterized in that: The specific steps of step S2 also include: S2.4: According to the judgment matrix A = (a jk ), calculate the maximum eigenvalue λ of A max and its corresponding eigenvector W=(w1,...,w m ), where w m It indicates the preliminary weight distribution of the mth indicator, where m represents the number of indicators; S2.5: Calculate the consistency ratio CR; If CR jk ) is consistent, and the feature vector W=(w1,...,w m ) m As the weight of each indicator;​ If CR ≥ h1, the judgment matrix is ​​readjusted, where h1 represents the consistency threshold.

5. The meteorological disaster risk assessment method based on disaster risk classification according to claim 4, characterized in that: The specific steps of step S3 include: S3.1: Obtain meteorological disaster factor indicators, disaster-prone environment indicators, disaster-bearing body vulnerability indicators and corresponding weights; S3.2: Load the pre-built weighted comprehensive scoring model, and configure the parameters of the weighted comprehensive scoring model according to the meteorological disaster factor indicators, disaster-prone environment indicators, disaster-bearing body vulnerability indicators and corresponding weights, and use the pre-collected historical disaster data to train the configured weighted comprehensive scoring model to obtain the disaster risk classification model; S3.3: Collect disaster risk assessment data for the area to be assessed and perform pre-processing; S3.4: Input the pre-processed disaster risk assessment data into the disaster risk classification model, and run the disaster risk classification model to calculate the meteorological disaster risk value of the area to be assessed; S3.5: Based on historical disaster data statistics and regional disaster prevention and mitigation capabilities, different risk levels are divided and corresponding thresholds are set; S3.6: Compare the calculated meteorological disaster risk value with the preset risk warning threshold to determine the risk level of the area to be assessed; S3.7: Generate risk assessment reports using text templates and data visualization techniques.

6. The meteorological disaster risk assessment method based on disaster risk classification according to claim 5, characterized in that: The meteorological disaster factor indicators include the maximum wind speed of the typhoon, the lowest air pressure in the center of the typhoon, and the amount of rainfall during the process; the disaster-prone environment indicators include the terrain slope and the distance from the coastline; the disaster-bearing body vulnerability indicators include population density, building wind resistance level, and the integrity rate of infrastructure.

7. A meteorological disaster risk assessment system based on disaster risk classification, which is used to implement the meteorological disaster risk assessment method based on disaster risk classification as described in any one of claims 1 to 6, characterized in that: include: Data processing module, indicator building module, model building module, and early warning module; The data processing module is used to collect various basic data and pre-process the collected data; The indicator construction module is used to evaluate various indicators of meteorological disaster risks and assign weights to each indicator in the evaluation; The model building module is used to build a disaster risk classification model according to the determined indicators and weights, and use the disaster risk classification model to conduct risk assessment on the area to be assessed, generate meteorological disaster risk values ​​and corresponding risk levels, and generate a risk assessment report; The early warning module is used to establish a real-time meteorological data monitoring mechanism, monitor meteorological data, regularly update disaster risk assessment results, and issue early warning information when the meteorological disaster risk value exceeds the risk warning threshold.

8. The meteorological disaster risk assessment system based on disaster risk classification according to claim 7, characterized in that: The indicator construction module includes: an indicator construction unit and a hierarchical analysis unit; The indicator construction unit is used to construct a disaster risk assessment indicator system for different meteorological disaster types; The hierarchical analysis unit is used to adopt the hierarchical analysis method to construct a judgment matrix through the comparison results of two indicators, solve the judgment matrix to obtain the weight of each indicator, and perform consistency test.

9. The meteorological disaster risk assessment system based on disaster risk classification according to claim 8, characterized in that: The model building module includes: a model building unit and a risk assessment unit; The model building unit is used to build a disaster risk classification model according to the indicators and corresponding weights; The risk assessment unit is used to input the data of the area to be assessed into the disaster risk classification model, calculate the meteorological disaster risk value, and determine the risk level of the area to be assessed in combination with a preset risk warning threshold.

Images