A typhoon-rainstorm flood combined disaster monitoring and assessment method and system

Abstract

The present invention discloses a typhoon-rainstorm-flood combined disaster monitoring and assessment method and system, belonging to the field of intelligent disaster monitoring. The method comprises the following steps: based on multi-factor data, a disaster identification model is established through a machine learning algorithm to obtain a combined disaster judgment result; based on the combined disaster judgment result, a disaster assessment model is constructed for the area causing the disaster; based on real-time monitoring data, the parameters of the disaster assessment model are dynamically updated to obtain a real-time combined disaster assessment result; based on the real-time combined disaster assessment result, the loss probability distribution is dynamically adjusted to obtain a comprehensive disaster loss assessment result; based on the comprehensive disaster loss assessment result, the spatiotemporal evolution of the disaster situation is performed to obtain a disaster development trend.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent disaster monitoring, and in particular relates to a monitoring and assessment method and system for typhoon-rainstorm-flooding compound disasters. Background Art

[0002] The monitoring and assessment of combined typhoon-rainstorm and flood disasters present the following technical challenges: First, how to accurately identify the occurrence of typhoons and rainstorms and determine whether they constitute a combined event. This requires comprehensive consideration of multiple factors, such as the typhoon's path, rainstorm location, and occurrence time, and the establishment of reasonable thresholds. Second, assessing the losses of combined disasters is challenging. Typhoons and rainstorms have different impact areas and loss mechanisms, and further research is needed to consider their coupling effects and establish a reasonable loss assessment model. Furthermore, the occurrence of combined typhoon-rainstorm events is highly random and uncertain, and the evolution of the disaster is complex and unpredictable. Real-time dynamic monitoring of the disaster process and the integration of damage assessment models to generate corresponding assessment results place high technical demands. Finally, typhoon-rainstorm disasters vary greatly in temporal and spatial scales, and are influenced by complex factors such as regional topography, landforms, and land use. Disaster response mechanisms vary across regions, so assessment models must be regionally applicable and capable of tailoring disaster monitoring and assessment to local conditions. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a typhoon-rainstorm flood combined disaster monitoring and assessment method and system to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above objectives, the present invention provides a method for monitoring and assessing typhoon-rainstorm flood combined disasters, comprising:

[0005] Based on multi-factor data, a disaster identification model is established through machine learning algorithms to obtain compound disaster judgment results;

[0006] Constructing a disaster assessment model for the area constituting the disaster based on the composite disaster judgment result;

[0007] Dynamically updating the parameters of the disaster assessment model based on real-time monitoring data to obtain real-time composite disaster assessment results;

[0008] Based on the real-time composite disaster assessment results, dynamically adjusting the loss probability distribution to obtain a comprehensive disaster loss assessment result;

[0009] Based on the comprehensive disaster loss assessment results, the spatiotemporal evolution of the disaster situation is performed to obtain the development trend of the disaster situation.

[0010] Optionally, the disaster identification model obtains a composite disaster judgment result by analyzing rainfall monitoring data of heavy rain occurring on the same day within a 300-kilometer buffer zone of the typhoon path.

[0011] Optionally, when a compound disaster is determined, a regional modeling strategy is adopted to divide the study area into several assessment units, and a compound disaster assessment model is constructed based on the natural geographical attributes of the several assessment units.

[0012] Optionally, the process of obtaining real-time composite disaster assessment results includes:

[0013] Input the real-time monitoring data of the disaster area into the disaster assessment model to obtain the loss distribution of each assessment unit;

[0014] Based on the loss distribution, when the loss of the assessment unit exceeds a preset threshold, the current assessment unit is judged to be a high-risk area, and an identification result of the high-risk area is obtained;

[0015] Based on the location distribution of high-risk areas and road network data, the optimal dispatch route of the rescue team is planned to obtain the rescue route plan;

[0016] Based on the continuous acquisition of real-time monitoring data and the re-evaluation of the disaster damage assessment model, the rescue plan is dynamically adjusted to obtain an adjusted rescue plan.

[0017] Optionally, the process of constructing the disaster assessment model also includes describing the interaction of the multi-factor data through a nonlinear function, introducing the interaction terms of the strong winds and heavy rains brought by the typhoon; and performing storm surge warning based on the disaster assessment model with the introduction of the interaction terms.

[0018] Optionally, the process of obtaining a comprehensive disaster damage assessment result includes:

[0019] Based on historical typhoon-rainstorm flood data, a probability distribution model for compound disaster events was established, and the probability of occurrence of different disaster scenarios was obtained;

[0020] Based on the probability of occurrence of different disaster scenarios, the Monte Carlo simulation method is used to estimate the loss distribution under different disaster scenarios;

[0021] Collect wind speed and water level data in real time, and update a probability distribution model of disaster events based on the wind speed and water level data to obtain an adjusted probability of disaster occurrence;

[0022] Based on the adjusted probability of disaster occurrence, the disaster loss distribution of different scenarios is weighted averaged to obtain a comprehensive disaster loss assessment result.

[0023] Optionally, based on the comprehensive disaster loss assessment results, a spatiotemporal data analysis method is used to analyze the spatiotemporal evolution of the disaster to obtain the distribution characteristics of the disaster at different times and spaces. Based on the distribution characteristics of the disaster at different times and spaces, high-risk areas of the disaster are identified, key time nodes of the disaster are determined, and the severity and scope of the disaster are judged.

[0024] The present invention also provides a typhoon-rainstorm flood combined disaster monitoring and assessment system, comprising:

[0025] A composite disaster identification module, which is used to obtain typhoon and rainstorm data and determine whether it constitutes a composite disaster through machine learning;

[0026] A sub-regional modeling module, which is used to divide the assessment units and construct a regional disaster loss assessment model;

[0027] A real-time assessment module, which is used to obtain real-time monitoring data and dynamically update model parameters to perform disaster assessment;

[0028] A coupling effect evaluation module, wherein the coupling effect evaluation module is used to improve the evaluation accuracy by characterizing multi-factor interactions through nonlinear functions;

[0029] A probability statistics module, which is used to estimate the distribution of disaster losses under different scenarios and dynamically adjust the probability;

[0030] The disaster analysis module is used to analyze the spatiotemporal evolution of the disaster situation and predict development trends to provide a basis for decision-making.

[0031] Compared with the prior art, the present invention has the following advantages and technical effects:

[0032] The present invention discloses a method for monitoring and evaluating typhoon-rainstorm compound disasters. In view of the coupling effect of typhoon and rainstorm disasters, a compound disaster identification model is trained by a machine learning algorithm to determine whether a compound disaster is constituted. For situations where a compound disaster is constituted, a regional modeling strategy is adopted, and the study area is divided into assessment units according to natural attributes such as topography and landforms, and a regionally applicable disaster loss assessment model is constructed in combination with historical disaster data. The model introduces the interaction terms of strong winds and rainstorms brought by typhoons, characterizes the coupling effect of multiple factors through nonlinear functions, and adopts probabilistic statistical methods to deal with the uncertainty of disasters. When a disaster occurs, the model parameters are dynamically updated based on real-time monitoring data to realize real-time assessment of the losses of each assessment unit, and analyze the spatiotemporal evolution trend of the disaster situation. By taking into account the coupling effect and regional differences of disasters, the present invention improves the accuracy of compound disaster loss assessment, and provides a scientific basis for disaster emergency decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0034] Figure 1 This is a flow chart of a method for monitoring and assessing a typhoon-rainstorm-flooding combined disaster according to an embodiment of the present invention;

[0035] Figure 2 This is a flow chart of complex disaster identification according to an embodiment of the present invention;

[0036] Figure 3 This is a structural diagram of a typhoon-rainstorm-flooding combined disaster monitoring and assessment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] Example 1

[0040] like Figure 1 As shown, this embodiment provides a typhoon-rainstorm flood combined disaster monitoring and assessment method, including the following steps:

[0041] Step S101, as Figure 2 As shown in the figure, based on multi-factor data, a disaster identification model is established through machine learning algorithm to obtain the composite disaster judgment result; the multi-factor data includes typhoon path, rainstorm intensity, rainstorm range, and rainstorm duration.

[0042] Furthermore, multiple factors such as typhoon path, rainstorm intensity, rainstorm range, and rainstorm duration are obtained, and a composite disaster identification model is trained through a machine learning algorithm. The composite disaster identification model is used to determine whether the current typhoon and rainstorm event constitutes a composite disaster.

[0043] As a specific implementation of this embodiment, in the process of building a composite disaster identification model, it is first necessary to collect and organize data on typhoon paths, rainstorm intensity, rainstorm range, and duration. For example, data on all recorded typhoon and rainstorm events over the past decade is obtained from the meteorological bureau's database. This data includes typhoon path coordinates, maximum wind speed, rainfall, and rainfall duration. During the data cleaning process, it is necessary to eliminate data entries that are incomplete or obviously erroneous, such as records of sudden interruptions in the typhoon path or abnormally low rainstorm intensity. Next, feature extraction is a key step. Specifically, features such as wind speed at typhoon path points, path buffer zone, rate of change of rainfall intersecting the buffer zone, and maximum duration of rainstorms are extracted from the raw meteorological data. These features help the model better understand the behavioral patterns of typhoons and rainstorms and their interactions. Data normalization ensures the effectiveness of model training. Because different data indicators, such as wind speed and rainfall, have different dimensions and magnitudes, directly using this data may lead to deviations during model training. By scaling all feature values to the same range, such as between 0 and 1, model training can be more stable and efficient. The support vector machine (SVM) algorithm is used for model training because SVMs demonstrate excellent performance in handling small sample sizes, nonlinearities, and high-dimensional patterns. Using grid search and cross-validation methods, different hyperparameter combinations (such as kernel function type, penalty parameter C, and kernel parameter γ) can be systematically searched and evaluated to find the optimal model parameter settings. After model training is complete, real-time typhoon and rainstorm data are fed into the model for prediction. For example, if the currently monitored typhoon path and rainstorm intensity patterns resemble those marked as complex disasters in the training data, the model may predict that the event will constitute a complex disaster. At this point, the early warning mechanism is triggered, and relevant departments receive the warning information and initiate emergency response plans based on the warning level. Continuous monitoring and dynamic updates are essential, as the actual path and intensity of typhoons and rainstorms may differ from initial predictions. Real-time updates to the model input data allow for adjustments to the prediction results, ensuring the timeliness and accuracy of emergency response measures. Finally, by collecting actual post-disaster impact data, such as the affected area and economic losses, the model's prediction performance can be evaluated and further optimized and improved. Regularly retraining the model to adapt to changes in disaster characteristics is a key measure to ensure the long-term effectiveness and adaptability of the model.

[0044] Furthermore, based on real-time monitoring data of multi-dimensional factors such as typhoon path, rainstorm intensity, and duration, a trained composite disaster identification model is used for prediction, and it is determined that if there is rainstorm within the 300-kilometer buffer zone of the typhoon path on the same day, it is a typhoon-rainstorm composite event.

[0045] As a specific implementation method of this embodiment, multi-dimensional real-time monitoring data such as typhoon path, rainstorm intensity, and duration are obtained to construct a training data set for the composite disaster identification model. Machine learning algorithms such as support vector machines or random forests are used to train and optimize the composite disaster identification model based on the training data set. When typhoon path data is monitored, a 300-kilometer buffer area is determined with the typhoon path as the center. Rainstorm monitoring data within the buffer area is obtained, and characteristic parameters such as rainstorm intensity and duration are extracted. Typhoon gale and rainstorm characteristic parameters are input into the trained composite disaster identification model to perform composite disaster assessment and analysis. If the assessment results of the composite disaster identification model show that there is a rainstorm event in the buffer area at the same time, it is determined to be a typhoon-rainstorm composite event. Based on the assessment results of the typhoon-rainstorm composite event, early warning information is automatically generated and released through multiple channels to guide relevant departments to take disaster prevention and mitigation measures.

[0046] Step S102, constructing a disaster assessment model for the disaster-prone area based on the composite disaster judgment result;

[0047] Furthermore, if the current typhoon and rainstorm events constitute a composite disaster, then the study area is divided into several assessment units using a regional modeling strategy based on the differences in the impact areas and loss mechanisms of the composite disasters. For each assessment unit, its topography, landform, land use and other natural geographical attributes are obtained, and the damage response characteristics of each assessment unit are extracted from historical disaster data to construct a regionally applicable disaster damage assessment model.

[0048] As a specific implementation of this embodiment, obtaining data on the study area's topography, landforms, land use, and other natural geographic attributes forms the basis for disaster damage assessment. For example, a study area located on the southeastern coast has complex terrain, including mountains, plains, and hills, and diverse land use types, including farmland, urban built-up areas, and forests. This data is divided into several assessment units based on topographical features and land use types, such as mountains and forests in one unit, plains and farmland in another, and urban built-up areas as a separate unit. For each assessment unit, damage data from typhoon and rainstorm events is extracted from a historical disaster database. Assume that the database contains records of typhoon and rainstorm events that occurred in the region over the past ten years, including data on the affected area, economic losses, and casualties for each event. When extracting this data, it is important to ensure its completeness and accuracy. For example, for the mountain and forest units, the extracted data may indicate that a typhoon caused widespread forest collapse, resulting in economic losses of tens of millions of yuan; whereas, for the urban built-up area unit, the data may indicate that a rainstorm caused urban flooding, resulting in even more severe economic losses and casualties. The extracted disaster loss data is preprocessed to remove outliers and missing values. For example, if the economic loss data in a particular record is abnormally high and verified to be due to data entry errors, it should be removed. Missing values can be filled through interpolation or using average values. After preprocessing, a standardized disaster loss dataset is obtained to ensure the reliability of subsequent analysis. The disaster loss data for each assessment unit is analyzed to extract key indicators that reflect the disaster loss response characteristics of the region. For example, the intensity of the disaster loss can be expressed as the ratio of economic losses to the affected area, and the scope of the disaster loss can be measured as the proportion of the affected area to the total area. For example, the disaster loss intensity in mountainous and forested units may be lower, but the damage coverage is wider; while the disaster loss intensity in urban built-up areas is higher, but the damage coverage is relatively concentrated. Based on the physical geographic attributes and disaster loss response characteristics of each assessment unit, machine learning algorithms such as support vector machines or random forests are used to train a disaster loss assessment model for the region. Assuming the support vector machine algorithm is chosen, the first step is to select an appropriate kernel function, such as the radial basis function (RBF). Then, model hyperparameters, such as the penalty parameter C and the kernel parameter γ, are optimized through grid search and cross-validation. Through training, a damage assessment model is developed for each assessment unit. This trained damage assessment model is then used to rapidly assess new combined typhoon and rainstorm disasters and predict their impact on each assessment unit. For example, when a new typhoon and rainstorm event occurs, the model, fed with real-time monitoring data, outputs the estimated economic losses and affected area for each assessment unit. Assume that the model predicts that economic losses for urban built-up areas will reach hundreds of millions of yuan, while the affected area for mountainous and forested areas will exceed thousands of hectares. The damage assessment results for each assessment unit are aggregated to produce a comprehensive damage assessment for the entire study area.For example, by aggregating the estimated economic losses and affected area for each unit, the overall economic losses and affected area for the entire study area can be determined, providing decision-making support for disaster emergency management and post-disaster reconstruction. Assuming that the comprehensive assessment results indicate that the total economic losses for the entire study area will reach billions of yuan and the affected area will exceed tens of thousands of hectares, relevant departments can use this assessment to formulate appropriate emergency response measures and post-disaster reconstruction plans. This approach is based on the fact that meticulous assessment unit division and damage data analysis can more precisely grasp the damage characteristics of different regions, thereby improving the accuracy and specificity of damage assessments. Using machine learning algorithms for model training can fully leverage information from historical data and enhance the reliability of predictions. The final comprehensive damage assessment provides decision makers with a comprehensive and scientific basis, helping to improve the efficiency and effectiveness of disaster response. Through continuous model training and updates, it can also adapt to changes in disaster characteristics, further enhancing the robustness and practicality of damage assessments.

[0049] Step S103, dynamically updating the parameters of the disaster assessment model based on the real-time monitoring data to obtain a real-time flood disaster assessment result; the process of obtaining the real-time flood disaster assessment result includes: inputting the real-time monitoring data of the disaster area into the disaster assessment model to obtain the loss distribution of each assessment unit; based on the loss distribution, when the loss of the assessment unit exceeds a preset threshold, the current assessment unit is judged to be a severely affected area, and the identification result of the severely affected area is obtained; based on the location distribution and road network data of the severely affected area, the optimal dispatch route of the rescue team is planned to obtain a rescue route plan; based on the continuous acquisition of real-time monitoring data and the re-evaluation of the disaster loss assessment model, the rescue plan is dynamically adjusted to obtain an adjusted rescue plan.

[0050] Furthermore, when a typhoon-rainstorm combined disaster occurs, real-time monitoring data such as rainfall, wind speed, and water level in the disaster area are obtained, and the real-time monitoring data are input into a pre-built disaster loss assessment model. The parameters of the disaster loss assessment model are dynamically updated through an online learning algorithm, and a real-time assessment of the disaster situation at the current moment is performed to obtain the loss distribution of each assessment unit.

[0051] As a specific implementation of this embodiment, real-time rainfall, wind speed, and water level data from disaster-stricken areas is obtained as the basis for damage assessment. For example, during the passage of Typhoon Haiyan, a meteorological monitoring station in a coastal city recorded rainfall reaching 100 mm per hour, wind speeds reaching 30 meters per second, and water levels rising to 2 meters above the warning line. This data is transmitted in real time to a data processing center via a sensor network, providing the foundation for subsequent damage assessment. This monitoring data is input into a pre-built damage assessment model, which is typically trained based on historical disaster data and machine learning algorithms. Assume that the city has already built a damage assessment model based on a random forest algorithm. The model inputs include parameters such as rainfall, wind speed, and water level, and the output is the damage level for each assessment unit. After inputting the real-time monitoring data, the model provides a preliminary assessment of the damage situation in different areas. Dynamically updating the parameters of the damage assessment model using an online learning algorithm allows the model to adapt to changes in the current disaster situation. For example, over time, a typhoon's path and intensity may change, leading to significant increases in rainfall and wind speed in certain areas. Using an online learning algorithm, the model can adjust parameters in real time, such as increasing the weight of rainfall on damage, thereby making the assessment results more accurate. The updated damage assessment model is used to conduct a real-time assessment of the current typhoon-rainstorm combined disaster, determining the loss distribution within each assessment unit. Suppose the model's assessment results indicate that the damage level in the eastern district of a city is "severe," the western district is "moderate," and the southern district is "light." This distribution can help decision makers quickly identify the most severely affected areas. If the damage level in an assessment unit exceeds a preset threshold, it is considered a severely affected area and requires priority rescue efforts. For example, if the damage level is set to "severe," the eastern district is identified as a severely affected area. In this case, rescue agencies must immediately mobilize resources and prioritize rescue efforts in this area. Based on the location distribution of severely affected areas and combined with road network data, optimal dispatch routes are planned for rescue teams to ensure they reach the most severely affected areas in the shortest possible time. Assuming there are three possible rescue routes for the eastern district, a Geographic Information System (GIS) analysis selects the optimal route that avoids congested and damaged roads, potentially reducing rescue time by 20 minutes. During the rescue process, real-time monitoring data from the disaster area was continuously collected and fed into the damage assessment model for reassessment, allowing for dynamic adjustments to the rescue plan. For example, if a sudden increase in rainfall was detected in a certain area of the East District during the rescue process, the model's reassessment indicated that the damage level in that area had risen to "extremely severe," prompting the rescue authorities to immediately adjust their plan and deploy additional rescue forces. The resulting loss distribution was correlated with the population distribution data in the disaster area to predict potential casualties and property losses, providing a basis for decision-making in post-disaster recovery and reconstruction. Assuming the East District is densely populated, the model predicted the potential for significant casualties and property losses. Based on this, government departments developed a detailed evacuation and resettlement plan and prioritized reconstruction efforts in that area.Through this series of steps, the disaster damage assessment model not only reflects changes in the disaster situation in real time but also provides a scientific basis for rescue and reconstruction. Real-time monitoring data acquisition and dynamic model updates ensure the accuracy of assessment results; optimal dispatch route planning improves rescue efficiency; dynamic adjustment of rescue plans reduces the risk of secondary disasters; and correlation analysis of population distribution data provides strong support for post-disaster recovery and reconstruction. This comprehensive disaster damage assessment and rescue strategy has significantly enhanced disaster response capabilities and protected people's lives and property.

[0052] In step S104, taking into account the coupling effect of typhoons and rainstorms, the interaction term of typhoons and rainstorms is introduced into the disaster damage assessment model, and the interaction of factors such as typhoon intensity, rainstorm intensity, and duration is characterized by nonlinear functions to improve the assessment accuracy of the comprehensive impact of compound disasters and perform storm surge warnings.

[0053] Furthermore, historical data on typhoons and rainstorms are obtained, including data on factors such as typhoon intensity, rainstorm intensity, and duration; the obtained typhoon and rainstorm data are preprocessed to remove outliers and missing values, and the data are standardized; based on the preprocessed typhoon and rainstorm data, a nonlinear disaster loss assessment model containing interaction terms is constructed, wherein the interaction terms are used to characterize the interaction of factors such as typhoon intensity, rainstorm intensity, and duration; machine learning algorithms such as support vector machines or random forests are used to train the constructed disaster loss assessment model to obtain the optimal parameters of the model; new typhoon and rainstorm data are predicted using the trained disaster loss assessment model to obtain a comprehensive impact assessment result of the compound disaster; the assessment results are analyzed to determine whether the assessment accuracy meets the preset threshold. If not, return to step 3 and adjust the model structure or parameters until the accuracy requirements are met; the disaster loss assessment model that meets the accuracy requirements is applied to actual typhoon and rainstorm disaster warning and loss assessment to provide decision support for disaster prevention and mitigation.

[0054] As a specific implementation of this embodiment, obtaining historical data on typhoons and rainstorms is fundamental to damage assessment. For example, typhoon and rainstorm data for a coastal area over the past decade is collected, including key factors such as typhoon intensity (such as maximum central wind speed), rainstorm intensity (such as 24-hour rainfall), and duration. This data can be obtained from historical records maintained by meteorological departments or compiled through a combination of satellite remote sensing data and ground monitoring station data. Preprocessing the acquired data is a crucial step in ensuring data quality. First, outliers are removed, such as abnormally high wind speeds or rainfall recorded by a monitoring station due to equipment failure. Second, missing values are filled. For example, if rainfall data is missing on a particular day due to equipment failure, this can be interpolated using data from neighboring monitoring stations. Finally, the data is normalized so that data of different dimensions can be compared on the same scale. For example, wind speed and rainfall can be converted to standard scores (Z scores). Constructing a nonlinear damage assessment model with interaction terms is intended to more accurately reflect the combined impact of typhoons and rainstorms. For example, the model includes not only the two main effect terms of typhoon intensity and rainstorm intensity, but also their interaction terms (such as typhoon intensity × rainstorm intensity). This interaction term captures the nonlinear effects of the combined effects of typhoons and heavy rainfall. For example, when a strong typhoon is accompanied by heavy rainfall, disaster losses increase significantly. Model training using machine learning algorithms such as support vector machines (SVM) or random forests (RF) aims to find optimal model parameters. For example, when using the random forest algorithm, parameters such as the number of trees and tree depth are adjusted to find the parameter combination that optimizes model performance on historical data. During training, cross-validation is used to divide the data into training and validation sets to ensure the model's generalization ability. Using the trained model to predict new typhoon and heavy rainfall data can yield a comprehensive impact assessment of the combined disaster. For example, when Typhoon Maria was about to make landfall, the meteorological authorities predicted a maximum wind speed of 40 meters per second and 24-hour rainfall of 200 mm. This data was input into the model, which then output a comprehensive impact assessment of the combined typhoon and heavy rainfall event, including estimated economic losses and casualties. The assessment results were analyzed to determine whether their accuracy met a preset threshold to ensure model reliability. For example, if the model's accuracy threshold is set at 90%, and the model's accuracy on the validation set is only 85%, it does not meet the requirement. In this case, it is necessary to return to step 3 and adjust the model structure or parameters, such as adding more interaction terms or replacing the machine learning algorithm, until the model's accuracy reaches the preset threshold. Applying damage assessment models that meet accuracy requirements to actual typhoon and rainstorm disaster warnings and loss assessments, as well as storm surge warnings, can provide decision-making support for disaster prevention and mitigation. For example, before Typhoon Maria made landfall, the model predicted a "severe" damage level in the eastern district of a coastal city. Based on this prediction, government departments deployed rescue forces in advance, evacuated residents in high-risk areas, and reduced casualties and property losses.Through this series of steps, the damage assessment model not only more accurately reflects the combined impact of typhoons and heavy rains, but also provides a scientific basis for disaster prevention and mitigation. Data preprocessing ensures the quality of the model input, the introduction of interaction terms improves the model's fit, the application of machine learning algorithms optimizes the model's parameters, and the accuracy verification of the assessment results ensures the model's reliability. Ultimately, practical application transforms the model's value into actual disaster prevention and mitigation results. This comprehensive damage assessment method significantly enhances disaster response capabilities through a variety of technical means and rigorous implementation procedures. Data preprocessing and standardization ensure data availability and consistency, the introduction of interaction terms and the application of machine learning algorithms improve the model's predictive accuracy, and accuracy verification ensures the model's reliability. Ultimately, practical application maximizes the model's value, providing strong decision-making support for disaster prevention and mitigation.

[0055] Step S105, dynamically adjusting the loss probability distribution based on the real-time flood disaster assessment result to obtain a comprehensive disaster loss assessment result;

[0056] Among them, in view of the uncertainty of complex disasters, the disaster loss assessment model adopts a probabilistic statistical method to estimate the disaster loss distribution under different scenarios based on the probability distribution of disaster events; obtains real-time monitoring data of the disaster area, dynamically adjusts the probability of disaster scenarios, and obtains a dynamically changing loss probability distribution.

[0057] Furthermore, based on historical disaster data from the disaster area, a probability distribution model for complex disaster events was established to determine the probability of occurrence of different disaster scenarios. For each disaster scenario, a Monte Carlo simulation method was used to estimate the loss distribution under that scenario based on the disaster loss function. Real-time monitoring data from the disaster area, including multi-source heterogeneous data such as meteorological, geological, and hydrological data, was obtained and preprocessed using data fusion technology. Based on this real-time monitoring data, the probability distribution model for disaster events was dynamically updated to determine the real-time changes in the probability of occurrence of various disaster scenarios. For disaster scenarios with changed probabilities, Monte Carlo simulations were re-performed to obtain dynamically changing loss distributions. The loss distributions of different scenarios were weighted averaged, with the weights being the dynamic probability of each scenario, to obtain a comprehensive loss assessment result. Machine learning algorithms such as support vector machines and random forests were used to train prediction models based on the loss assessment results, enabling rapid loss assessment for new disaster scenarios.

[0058] As a specific implementation of this embodiment, establishing a probability distribution model for complex disaster events is a key step in disaster risk management. For example, by analyzing historical flood data, a model can be developed to predict the probability of such a disaster. Monte Carlo simulation is an effective technical approach for estimating the loss distribution under specific disaster scenarios. Through large-scale random sampling, the Monte Carlo method can generate a loss distribution that is close to the actual situation. The acquisition and preprocessing of real-time monitoring data is another important step in disaster management. For example, water level sensors and anemometers can collect real-time water level and wind speed data. After processing this data using data fusion technology, it can be used to update the probability distribution model for disaster events, making it more relevant to the current environment and conditions. Dynamically updating the probability distribution model for disaster events is an ongoing process. As new data is continuously input, the model adjusts the probability of disaster occurrence in real time. For example, if several consecutive days of rainfall cause a sharp rise in river water levels, the probability of flooding will increase. This dynamic adjustment makes disaster warnings more accurate and timely. When the probability of a disaster scenario changes, it is necessary to re-run the Monte Carlo simulation. This allows for an updated loss distribution based on the latest probability distribution, providing data support for adjusting disaster response measures. A key step in obtaining a comprehensive loss assessment is to weight the loss distributions of different scenarios, where the weights are the dynamic probability of each scenario occurring. This ensures that the assessment results reflect the losses corresponding to the most likely disaster scenario. Finally, using machine learning algorithms such as support vector machines and random forests to train a predictive model based on the loss assessment results can enable rapid loss assessment for new disaster scenarios. This approach, using models trained using historical data, can quickly provide loss forecasts when new disasters occur, helping decision makers respond quickly.

[0059] Step S106, performing temporal and spatial evolution of the disaster situation based on the comprehensive disaster damage assessment results to obtain a disaster development trend;

[0060] Among them, on the basis of loss assessment, the temporal and spatial evolution process of the disaster is further analyzed, high-risk areas and key time nodes of the disaster are identified, and the development trend of the disaster is predicted to generate decision-making basis for disaster emergency response.

[0061] Furthermore, based on the loss assessment results, spatiotemporal data analysis methods are used to analyze the spatiotemporal evolution of the disaster, determining its distribution characteristics across time and space. This analysis of the spatiotemporal distribution of the disaster identifies high-risk areas, identifies key time points, and assesses the severity and scope of the impact. Machine learning algorithms, such as time series prediction and spatial interpolation, are used to predict the development trend of the disaster and estimate how it will change over time. Based on the identification of high-risk areas and key time points, key areas and time periods for emergency response are identified, allowing for the formulation of targeted emergency measures. Disaster trend prediction results are used to determine the direction and changing trends of the disaster, adjust emergency response strategies, and rationally allocate rescue resources. The results of the loss assessment, high-risk area identification, key point identification, and trend prediction are integrated to form a basis for emergency response decision-making, supporting emergency command decisions. Visualization technology is used to present the disaster analysis and prediction results in the form of maps and curves, visually demonstrating the spatiotemporal evolution and development trends of the disaster, enabling emergency management personnel to quickly understand the dynamics of the disaster.

[0062] As a specific implementation of this embodiment, when conducting disaster loss assessments, a spatiotemporal data model is established by analyzing historical disaster data. For example, in a coastal area, by analyzing the typhoon paths and impact areas over the past decade, it is possible to identify certain low-lying areas that are frequently affected by floods. This analysis can be performed using a geographic information system (GIS). By overlaying data on historical disaster events onto a map, it is possible to visually see which areas were most severely affected during a specific time period. After identifying high-risk areas, time series forecasting methods can be used to predict the timing and potential impact of future disasters. For example, if a region experiences floods every rainy season, the rainfall and flooding time points over the past few years can be analyzed to predict flood trends during future rainy seasons. This forecast can help local governments and rescue organizations prepare in advance, such as stockpiling disaster relief supplies and developing evacuation plans. After identifying key disaster time nodes and high-risk areas, the key areas and time periods for emergency response are also clarified. For example, if an upcoming typhoon is predicted to make landfall in a coastal city, that city and its surrounding areas become the focus of emergency response. The critical period is typically the days before and after a typhoon makes landfall, when rescue resources, such as rescue teams and relief supplies, need to be intensively deployed. Disaster trend forecasts can be used to adjust emergency response strategies. For example, if forecasts indicate that a flood will affect not only low-lying areas but also several small towns upstream, the emergency response strategy needs to be adjusted to include these newly identified high-risk areas. This adjustment ensures that rescue resources can be allocated more effectively, thereby reducing the impact of the disaster. Finally, integrating all this information and presenting it through visualization techniques is key to ensuring efficient and accurate communication. For example, a dynamic disaster monitoring dashboard can be created that displays real-time weather data, high-risk areas, and predicted disaster trends. Such a dashboard not only helps emergency managers quickly access the latest disaster information, but also helps the public understand impending risks and take appropriate preventative measures.

[0063] Example 2

[0064] like Figure 3 As shown, this embodiment also provides a typhoon-rainstorm flood combined disaster monitoring and assessment system, which mainly includes:

[0065] The composite disaster identification module is used to obtain typhoon and rainstorm data and determine whether it constitutes a composite disaster through machine learning;

[0066] The regional modeling module is used to divide the assessment units and build a disaster loss assessment model with regional applicability;

[0067] Real-time assessment module, used to obtain real-time monitoring data and dynamically update model parameters for disaster assessment;

[0068] The coupling effect evaluation module is used to improve the evaluation accuracy by characterizing multi-factor interactions through nonlinear functions;

[0069] Probabilistic statistics module, used to estimate the distribution of disaster losses under different scenarios and dynamically adjust the probability;

[0070] The disaster analysis module is used to analyze the temporal and spatial evolution of the disaster and predict development trends to provide a basis for decision-making.

[0071] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for monitoring and assessing typhoon-rainstorm flood combined disasters, characterized in that: The following steps are involved: Based on multi-factor data, a disaster identification model is established through machine learning algorithms to obtain complex disaster judgment results; wherein the multi-factor data includes typhoon path, rainstorm intensity, rainstorm range and rainstorm duration; Based on the composite disaster judgment results, a disaster assessment model is constructed for the area that constitutes the disaster; when it is determined to be a composite disaster, a regional modeling strategy is adopted to divide the study area into a number of assessment units, and a composite disaster assessment model is constructed based on the natural geographical attributes of the several assessment units; the process of constructing the disaster assessment model also includes describing the interaction of the multi-factor data through nonlinear functions, introducing interaction terms of strong winds and heavy rains brought by typhoons; storm surge warning is issued based on the disaster assessment model that introduces the interaction terms; Dynamically updating the parameters of the disaster assessment model based on real-time monitoring data to obtain real-time composite disaster assessment results; The process of obtaining real-time composite disaster assessment results includes: inputting real-time monitoring data of the disaster area into the disaster assessment model to obtain the loss distribution of each assessment unit; based on the loss distribution, when the loss of the assessment unit exceeds a preset threshold, the current assessment unit is judged to be a high-risk area, and the high-risk area identification result is obtained; based on the location distribution and road network data of the high-risk area, the optimal dispatch route of the rescue team is planned to obtain a rescue route plan; based on the continuous acquisition of real-time monitoring data and the re-evaluation of the disaster loss assessment model, the rescue plan is dynamically adjusted to obtain the adjusted rescue plan; Based on the real-time composite disaster assessment results, the loss probability distribution is dynamically adjusted to obtain a comprehensive disaster loss assessment result; the process of obtaining the comprehensive disaster loss assessment result includes: establishing a probability distribution model of composite disaster events based on historical typhoon-rainstorm flood data, and obtaining the probability of occurrence of different disaster scenarios; based on the probability of occurrence of different disaster scenarios, using the Monte Carlo simulation method to estimate the loss distribution under different disaster scenarios; collecting wind speed and water level data in real time, updating the probability distribution model of the disaster event based on the wind speed and water level data, and obtaining an adjusted probability of disaster occurrence; and performing weighted averaging on the disaster loss distribution of different scenarios based on the adjusted probability of disaster occurrence to obtain a comprehensive disaster loss assessment result; Based on the comprehensive disaster loss assessment results, the spatiotemporal evolution of the disaster situation is performed to obtain the development trend of the disaster situation.

2. The typhoon-rainstorm flood combined disaster monitoring and assessment method according to claim 1 is characterized in that: The disaster identification model is based on the analysis of rainfall monitoring data of heavy rain occurring on the same day within the 300-kilometer buffer zone of the typhoon path to obtain the composite disaster judgment result.

3. The typhoon-rainstorm flood combined disaster monitoring and assessment method according to claim 1 is characterized in that: Based on the comprehensive disaster loss assessment results, a spatiotemporal data analysis method is used to analyze the spatiotemporal evolution of the disaster to obtain the distribution characteristics of the disaster at different times and spaces. Based on the distribution characteristics of the disaster at different times and spaces, high-risk areas of the disaster are identified, key time nodes of the disaster are determined, and the severity and scope of the disaster are judged.

4. A typhoon-rainstorm flood combined disaster monitoring and assessment system, characterized in that: For implementing the method according to claim 1, the system comprises: A composite disaster identification module, which is used to obtain typhoon and rainstorm data and determine whether it constitutes a composite disaster through machine learning; A sub-regional modeling module, which is used to divide the assessment units and construct a regional disaster loss assessment model; A real-time assessment module, which is used to obtain real-time monitoring data and dynamically update model parameters to perform disaster assessment; A coupling effect evaluation module, wherein the coupling effect evaluation module is used to improve the evaluation accuracy by characterizing multi-factor interactions through nonlinear functions; A probability statistics module, which is used to estimate the distribution of disaster losses under different scenarios and dynamically adjust the probability; The disaster analysis module is used to analyze the spatiotemporal evolution of the disaster situation and predict development trends to provide a basis for decision-making.

Images