A method and system for calculating compound flood risk based on the HEV framework

Abstract

The present invention discloses a method and system for calculating compound flood risk based on the HEV framework. The method includes the following steps: obtaining rainfall monitoring data, water level monitoring data, and terrain monitoring data, and using the feature matrix decomposition algorithm to obtain a basic feature matrix group; using the risk factor identification algorithm to obtain a standardized risk factor matrix set; using the data dynamic fusion algorithm to obtain a fusion data set; using the multi-dimensional risk coupling analysis method to obtain a risk coupling field; using the risk cumulative effect quantification method to obtain a cumulative effect field; and according to the risk coupling field and the cumulative effect field, using the dynamic comprehensive evaluation method to obtain a comprehensive risk assessment report. The present invention realizes the dynamic assessment of compound flood disaster risk through data processing algorithms, and improves the accuracy and timeliness of risk assessment.

Description

Technical Field

[0001] The present invention relates to flood disaster simulation technology, in particular to a method and system for calculating compound flood risk based on the HEV framework. Background Art

[0002] The research on calculating compound flood risk based on the HEV framework is of great significance for urban disaster prevention and mitigation. Compound flood disasters have characteristics such as multi-source, coupling, and chain effects, and are often formed by the combined action of multiple factors such as heavy rain, failure of flood control projects, and poor drainage systems. This complexity makes it difficult for traditional single-disaster risk assessment methods to cope. The risk assessment method based on the HEV framework can comprehensively describe the risk characteristics of compound flood disasters by systematically considering three dimensions: Hazard, Exposure, and Vulnerability, and provide a scientific basis for urban flood control project planning, emergency plan formulation, and risk management.

[0003] Currently, the research on compound flood risk assessment mainly focuses on the following aspects: one is the spatial analysis method based on GIS, which evaluates the spatial distribution of risk through overlay analysis; the second is to use the analytic hierarchy process to determine the weights of each evaluation index; the third is to establish a loss rate curve using historical disaster data; the fourth is to apply a hydrological and hydrodynamic model to simulate the flood evolution process. These methods have achieved a certain degree of quantitative assessment of compound flood risk, but most of them use static assessment methods and are difficult to reflect the dynamic evolution characteristics of risk. At the same time, existing research mostly focuses on direct economic losses and insufficiently considers indirect losses and social impacts.

[0004] However, the existing research still has the following technical problems: one is in data processing, lacking a dynamic fusion mechanism for multi-source heterogeneous data, especially the effective integration of real-time monitoring data such as remote sensing and the Internet of Things with historical statistical data; the second is in feature extraction, where existing methods are difficult to accurately identify and quantify the non-linear coupling relationship between risk factors, resulting in insufficient analysis of the risk chain transmission mechanism; the third is in vulnerability assessment, with insufficient assessment of the adaptation and recovery capabilities of disaster-bearing bodies, especially lacking the description of the co-evolution characteristics of the social-economic-engineering system; the fourth is in dynamic risk assessment, where existing methods are difficult to effectively handle the spatio-temporal scale conversion problem, resulting in low accuracy and reliability of risk prediction; the fifth is in risk grading, lacking a dynamic grading method considering the multi-level risk accumulation effect, and being difficult to accurately reflect the progressive evolution characteristics of risk; the sixth is in early warning, where existing methods do not accurately identify the key nodes of risk evolution and are difficult to achieve precise and differentiated risk early warning. These technical problems seriously restrict the accuracy and practicality of compound flood risk assessment. Summary of the Invention

[0005] Objective of the invention: To provide a method and a system for calculating compound flood risk based on the HEV framework, aiming to solve the above problems existing in the prior art.

[0006] Technical solution: A method for calculating compound flood risk based on the HEV framework, comprising the following steps:

[0007] Step S1: Obtain rainfall monitoring data, water level monitoring data, and terrain monitoring data, and use the feature matrix decomposition algorithm to obtain a basic feature matrix group; according to the basic feature matrix group, use the feature importance calculation method to obtain a feature importance vector; according to the feature importance vector and the basic feature matrix group, use the adaptive feature reconstruction algorithm to obtain a reconstructed feature field; according to the reconstructed feature field, use the multi-scale consistency test method to obtain a dynamic feature verification report;

[0008] Step S2: Obtain the reconstructed feature field, historical disaster data, and geographical information data, and use the multi-dimensional risk factor analysis method to obtain a standardized risk factor matrix set; according to the standardized risk factor matrix set, use the dynamic association network generation algorithm to obtain a dynamic association network sequence; according to the dynamic association network sequence, use the critical path extraction algorithm to obtain a critical path set and stability evaluation data; according to the critical path set and stability evaluation data, use the risk cascade propagation calculation method to obtain cascade effect evaluation data; according to the cascade effect evaluation data, critical path set, and standardized risk factor matrix set, use the multi-level risk map construction method to obtain a comprehensive risk map;

[0009] Step S3: Obtain the reconstructed feature field, comprehensive risk map, and pre-stored socio-economic data, and use the adaptive disaster-bearing body classification method to obtain a classified disaster-bearing body data set; according to the classified disaster-bearing body data set and historical disaster response data, use the multi-modal response analysis method to obtain a vulnerability response surface; according to the vulnerability response surface and socio-economic capacity data, use the dynamic adaptability evaluation method to obtain an adaptability evaluation matrix; according to the vulnerability response surface and adaptability evaluation matrix, use the evolution pattern recognition method to obtain an evolution pattern library; according to the evolution pattern library, adaptability evaluation matrix, and classified disaster-bearing body data set, use the multi-dimensional comprehensive evaluation method to obtain a comprehensive vulnerability evaluation field;

[0010] Step S4: Obtain the reconstructed feature field, the comprehensive risk map, and the comprehensive vulnerability assessment field, and use the heterogeneous data fusion method to obtain a fusion data set; according to the fusion data set, use the multi-dimensional risk coupling analysis method to obtain a risk coupling field; according to the risk coupling field and the historical risk evolution data, use the risk transformation mechanism identification method to obtain a set of risk transformation patterns; according to the risk coupling field and the set of risk transformation patterns, use the risk accumulation effect quantification method to obtain an accumulation effect field; according to the risk coupling field, the accumulation effect field, and the set of risk transformation patterns, use the dynamic comprehensive evaluation method to obtain a comprehensive risk assessment report.

[0011] According to another aspect of the present application, there is also provided a system for calculating compound flood risk based on the HEV framework, including:

[0012] At least one processor; and,

[0013] A memory communicatively connected to at least one of the processors; wherein,

[0014] The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method for calculating compound flood risk based on the HEV framework described in any one of the above technical solutions.

[0015] Beneficial effects: Through the data processing algorithm, the dynamic assessment of the compound flood disaster risk is realized, and the accuracy and timeliness of the risk assessment are improved. The technical effects will be described in combination with specific implementation cases later. Brief Description of the Drawings

[0016] Figure 1 is the flowchart of the present invention.

[0017] Figure 2 is the flowchart of step S1 of the present invention.

[0018] Figure 3 is the flowchart of step S2 of the present invention.

[0019] Figure 4 is the flowchart of step S3 of the present invention.

[0020] Figure 5 is the flowchart of step S4 of the present invention. Detailed Description of the Embodiments

[0021] As Figure 1 shown, a method for calculating compound flood risk based on the HEV framework includes the following steps:

[0022] Step S1: Obtain rainfall monitoring data, water level monitoring data, and terrain monitoring data, and use the feature matrix decomposition algorithm to obtain a basic feature matrix group; according to the basic feature matrix group, use the feature importance calculation method to obtain a feature importance vector; according to the feature importance vector and the basic feature matrix group, use the adaptive feature reconstruction algorithm to obtain a reconstructed feature field; according to the reconstructed feature field, use the multi-scale consistency test method to obtain a dynamic feature verification report.

[0023] Step S2: Obtain the reconstructed feature field output in Step S1, historical disaster data, and geographical information data, and use the multi-dimensional risk factor analysis method to obtain a standardized risk factor matrix set; according to the standardized risk factor matrix set, use the dynamic association network generation algorithm to obtain a dynamic association network sequence; according to the dynamic association network sequence, use the critical path extraction algorithm to obtain a critical path set and stability evaluation data; according to the critical path set and stability evaluation data, use the risk cascade propagation calculation method to obtain cascade effect evaluation data; according to the cascade effect evaluation data, critical path set, and standardized risk factor matrix set, use the multi-level risk map construction method to obtain a comprehensive risk map.

[0024] Step S3: Obtain the reconstructed feature field output in Step S1, the comprehensive risk map output in Step S2, and pre-stored socio-economic data, and use the adaptive disaster-bearing body classification method to obtain a classified disaster-bearing body data set; according to the classified disaster-bearing body data set and historical disaster response data, use the multi-modal response analysis method to obtain a vulnerability response surface; according to the vulnerability response surface and socio-economic capacity data, use the dynamic adaptability evaluation method to obtain an adaptability evaluation matrix; according to the vulnerability response surface and adaptability evaluation matrix, use the evolutionary pattern recognition method to obtain an evolutionary pattern library; according to the evolutionary pattern library, adaptability evaluation matrix, and classified disaster-bearing body data set, use the multi-dimensional comprehensive evaluation method to obtain a comprehensive vulnerability evaluation field.

[0025] Step S4: Obtain the reconstructed feature field output in Step S1, the comprehensive risk map output in Step S2, and the comprehensive vulnerability evaluation field output in Step S3, and use the heterogeneous data fusion method to obtain a fusion data set; according to the fusion data set, use the multi-dimensional risk coupling analysis method to obtain a risk coupling field; according to the risk coupling field and historical risk evolution data, use the risk transformation mechanism identification method to obtain a risk transformation mode set; according to the risk coupling field and risk transformation mode set, use the risk accumulation effect quantification method to obtain an accumulation effect field; according to the risk coupling field, accumulation effect field, and risk transformation mode set, use the dynamic comprehensive evaluation method to obtain a comprehensive risk assessment report.

[0026] In this embodiment, a complete composite flood risk assessment technical system is constructed through four key links: systematic integration feature extraction, risk analysis, vulnerability assessment, and comprehensive assessment. First, through the feature matrix decomposition and reconstruction algorithm, the efficient processing of multi-source monitoring data is realized; second, through the dynamic correlation network and critical path analysis, the law of risk propagation is accurately grasped; third, through the multi-modal response analysis and evolution pattern recognition, the accurate assessment of the vulnerability of disaster-bearing bodies is realized; finally, through the risk coupling analysis and cumulative effect quantification, the dynamic comprehensive assessment of composite risks is completed. This implementation not only overcomes the technical problems in data processing, risk propagation, vulnerability assessment, and comprehensive assessment in traditional methods, but also realizes the full-process intelligence of composite flood risk assessment through the organic connection of each link. Especially in the description of the dynamic characteristics of risks, this embodiment can accurately grasp the law of risk evolution, provide scientific decision-making support for urban flood prevention and mitigation, and improve the accuracy, timeliness, and reliability of composite flood risk assessment.

[0027] As Figure 2 shown, according to one aspect of the present application, step S1 is specifically as follows:

[0028] Step S11: Obtain the rainfall monitoring data, water level monitoring data, and terrain monitoring data of the monitoring stations, and construct a rainfall spatial distribution matrix, a water level spatial distribution matrix, and a terrain feature matrix according to the spatial position information; according to the rainfall spatial distribution matrix, the water level spatial distribution matrix, and the terrain feature matrix, obtain a set of standardized spatial distribution matrices through a linear transformation method.

[0029] Step S12: Obtain the set of standardized spatial distribution matrices in step S11, calculate the correlation coefficients between spatial positions to obtain a spatial correlation matrix; calculate the change characteristics of the time series according to the time series data in the set of standardized spatial distribution matrices to obtain a time evolution matrix; calculate the coupling degree between variables according to the different monitoring variable data in the set of standardized spatial distribution matrices to obtain a variable coupling matrix; according to the spatial correlation matrix, the time evolution matrix, and the variable coupling matrix, adopt a multi-level decomposition operation to obtain a set of basic feature matrices.

[0030] Step S13: Obtain the set of basic feature matrices in step S12, calculate the change amplitude of each feature in the time dimension to obtain a time-varying weight vector; calculate the spatial influence coefficient according to the spatial distribution range of the set of basic feature matrices to obtain a spatial influence matrix; according to the time-varying weight vector and the spatial influence matrix, adopt a weighted fusion operation to obtain a feature importance vector.

[0031] Step S14: Obtain the basic feature matrix group in step S12 and the feature importance vector in step S13, construct a non-linear weight function, calculate the dynamic weight coefficient of each feature to obtain a dynamic weight matrix; according to the dynamic weight matrix, perform weighted combination on the basic feature matrix group to obtain an initial reconstructed feature field; obtain the continuity constraint conditions of time and space, and perform optimization adjustment on the initial reconstructed feature field to obtain a reconstructed feature field.

[0032] Step S15: Obtain the reconstructed feature field in step S14 and the set of standardized spatial distribution matrices in step S11, calculate the feature consistency index of the local area to obtain a local consistency matrix; according to the reconstructed feature field, calculate the feature consistency index of the global range to obtain a global consistency vector; according to the local consistency matrix and the global consistency vector, construct a dynamic threshold judgment criterion to generate a dynamic feature verification report.

[0033] In this embodiment, through the dynamic fusion of multi-source data and the feature matrix decomposition algorithm, the efficient integration and feature extraction of rainfall, water level, and terrain monitoring data are realized. Specifically, using the feature matrix decomposition algorithm to process multi-source monitoring data can effectively reduce the data dimension and extract key feature information; through the feature importance calculation method, the contribution degree of different features can be quantitatively evaluated to realize the optimization of features; using the adaptive feature reconstruction algorithm, the reconstruction weight can be automatically adjusted according to the feature importance to improve the accuracy of the feature field; finally, through multi-scale consistency verification, the reliability of the reconstructed feature field is ensured. This embodiment not only solves the problem that multi-source heterogeneous data is difficult to effectively fuse in traditional methods, but also guarantees the accuracy and reliability of feature extraction through the feature reconstruction and verification mechanism. In practical applications, this embodiment can effectively extract key information such as rainfall intensity, water level change, and terrain features, provide a reliable data basis for subsequent risk assessment, and improve the accuracy of compound flood risk assessment.

[0034] As Figure 3 shown, according to one aspect of the present application, the specific content of step S2 is as follows:

[0035] Step S21: Obtain the reconstructed feature field output in step S1, the pre-stored historical disaster data and geographical information data, extract hydrometeorological parameters to obtain a hydrometeorological factor matrix; according to the geographical information data, extract topographic and geomorphic features to obtain a topographic and geomorphic factor matrix; obtain land use and flood control project data, extract human activity features to obtain a human activity factor matrix; according to the hydrometeorological factor matrix, the topographic and geomorphic factor matrix, and the human activity factor matrix, use a standardized processing method to obtain a set of standardized risk factor matrices.

[0036] Step S22: Obtain the standardized risk factor matrix set output in step S21, calculate the correlation intensity between risk factors at different times to obtain a time-varying correlation intensity matrix; according to the time-varying correlation intensity matrix, construct a dynamic threshold discrimination function, screen out significant correlation relationships to obtain a significant correlation matrix; according to the significant correlation matrix, construct a time-varying network structure to obtain a dynamic correlation network sequence.

[0037] Step S23: Obtain the dynamic correlation network sequence output in step S22, calculate the importance degree of each network node to obtain a node importance degree vector; according to the node importance degree vector and the dynamic correlation network sequence, identify the main paths of risk propagation to obtain a set of critical paths; according to the set of critical paths, evaluate the time stability of the paths to obtain stability evaluation data.

[0038] Step S24: Obtain the set of critical paths and stability evaluation data output in step S23, calculate the propagation intensity of risks on the critical paths to obtain a propagation intensity matrix; according to the propagation intensity matrix, calculate the delay effect of risk propagation to obtain a time-delay effect matrix; according to the propagation intensity matrix and the time-delay effect matrix, calculate the cumulative impact degree of risks to obtain cascade effect evaluation data.

[0039] Step S25: Obtain the cascade effect evaluation data output in step S24, the set of critical paths output in step S23, and the standardized risk factor matrix set output in step S21, calculate the basic risk distribution to obtain a basic risk layer; according to the basic risk layer and the set of critical paths, calculate the associated risk distribution to obtain an associated risk layer; according to the associated risk layer and the cascade effect evaluation data, calculate the cascade risk distribution to obtain a cascade risk layer; according to the basic risk layer, the associated risk layer, and the cascade risk layer, use a weighted superposition method to obtain a comprehensive risk map.

[0040] In this embodiment, through multi-dimensional risk factor analysis and dynamic correlation network generation algorithms, a comprehensive quantitative assessment of compound flood risk is realized. First, based on the reconstructed characteristic field, historical disaster data, and geographical information data, a multi-dimensional risk factor analysis method is used to extract standardized risk factors; then, through the dynamic correlation network algorithm, the time-varying correlation relationships between risk factors are captured; through the critical path extraction algorithm, the main ways of risk propagation are identified; finally, based on the cascade effect evaluation and multi-level risk map construction methods, the visualization expression of risks is realized. This embodiment overcomes the defect that it is difficult to depict the dynamic correlation relationships of risk factors in traditional risk assessment methods, and accurately grasps the propagation law of compound risks through dynamic correlation networks and critical path analysis. Especially in the quantification of the risk cascade effect, it can accurately evaluate the cumulative effect and propagation characteristics of risks, providing a scientific basis for risk prevention and control. This embodiment can effectively identify risk hotspots and critical propagation paths, providing important support for disaster prevention and mitigation decision-making.

[0041] As Figure 4 shown, according to one aspect of the present application, step S3 is specifically as follows:

[0042] Step S31: Obtain the reconstructed feature field output by step S1, the comprehensive risk map output by step S2, and the pre-stored socioeconomic data, extract the spatial distribution characteristics of disaster-bearing bodies to obtain a disaster-bearing body feature matrix; construct dynamic classification rules according to time series data to obtain dynamic classification criteria; classify the disaster-bearing bodies according to the disaster-bearing body feature matrix and the dynamic classification criteria to obtain a classified disaster-bearing body data set.

[0043] Step S32: Obtain the classified disaster-bearing body data set output by step S31 and the pre-stored historical disaster response data, extract the response characteristics of different types of disaster-bearing bodies to obtain a response feature matrix; calculate the sensitivity of the disaster-bearing bodies to disasters according to the response feature matrix to obtain a time-varying sensitivity matrix; evaluate the recovery ability of the disaster-bearing bodies according to the response feature matrix and the time-varying sensitivity matrix to obtain a recovery ability matrix; construct a response surface model according to the response feature matrix, the time-varying sensitivity matrix, and the recovery ability matrix to obtain a vulnerability response surface.

[0044] Step S33: Obtain the vulnerability response surface output by step S32 and the pre-stored socioeconomic capacity data, construct an adaptability evaluation index system to obtain an adaptability index matrix; calculate the resource allocation efficiency according to the socioeconomic capacity data to obtain a resource efficiency matrix; evaluate the system recovery resilience according to the adaptability index matrix and the resource efficiency matrix to obtain a system resilience matrix; use a comprehensive evaluation method according to the adaptability index matrix, the resource efficiency matrix, and the system resilience matrix to obtain an adaptability evaluation matrix.

[0045] Step S34: Obtain the vulnerability response surface output by step S32 and the adaptability evaluation matrix output by step S33, extract the vulnerability spatio-temporal change characteristics to obtain an evolution feature vector set; identify typical evolution patterns according to the evolution feature vector set to obtain key evolution patterns; predict the vulnerability change trend according to the key evolution patterns to obtain evolution trend data; construct an evolution pattern database according to the key evolution patterns and the evolution trend data to obtain an evolution pattern library.

[0046] Step S35: Obtain the evolution pattern library output by step S34, the adaptability evaluation matrix output by step S33, and the classified disaster-bearing body data set output by step S31, calculate the static vulnerability distribution to obtain a static vulnerability layer; calculate the dynamic vulnerability distribution according to the evolution pattern library to obtain a dynamic vulnerability layer; calculate the adaptive vulnerability distribution according to the adaptability evaluation matrix to obtain an adaptive vulnerability layer; use a multi-dimensional integration method according to the static vulnerability layer, the dynamic vulnerability layer, and the adaptive vulnerability layer to obtain a comprehensive vulnerability evaluation field.

[0047] In this embodiment, through the adaptive disaster-bearing body classification and multi-modal response analysis method, the accurate assessment of the vulnerability of disaster-bearing bodies is realized. First, the adaptive classification method is used to classify the disaster-bearing bodies, then the vulnerability response surface is established based on the historical disaster response data, and the recovery ability of the disaster-bearing bodies is quantified through the dynamic adaptability evaluation method. Finally, the comprehensive vulnerability assessment field is obtained through the evolutionary pattern recognition and multi-dimensional comprehensive evaluation method. This embodiment breaks through the limitation that it is difficult to depict the dynamic response characteristics of disaster-bearing bodies in traditional vulnerability assessment methods. Through multi-modal response analysis and dynamic adaptability evaluation, the response laws of disaster-bearing bodies in different disaster scenarios are accurately grasped. Especially in the aspect of evolutionary pattern recognition, it can predict the evolutionary trend of the vulnerability of disaster-bearing bodies and provide forward-looking guidance for risk prevention and control. This embodiment can accurately evaluate the vulnerability characteristics of different types of disaster-bearing bodies and provide a scientific basis for the formulation of differentiated protection measures.

[0048] As Figure 5 shown, according to one aspect of the present application, step S4 is specifically as follows:

[0049] Step S41: Obtain the reconstructed feature field output by step S1, the comprehensive risk map output by step S2, and the comprehensive vulnerability assessment field output by step S3, calculate the correlation features between the data to obtain a data correlation matrix; construct a consistency test criterion according to the spatio-temporal distribution characteristics to obtain a spatio-temporal consistency test matrix; perform fusion processing on the multi-source data according to the data correlation matrix and the spatio-temporal consistency test matrix to obtain a fusion data set.

[0050] Step S42: Obtain the fusion data set output by step S41, calculate the coupling degree between different risk types to obtain a risk coupling intensity matrix; calculate the risk amplification effect according to the risk coupling intensity matrix to obtain a risk amplification coefficient matrix; calculate the risk suppression effect according to the risk coupling intensity matrix to obtain a risk suppression coefficient matrix; adopt a coupling effect integration method according to the risk coupling intensity matrix, the risk amplification coefficient matrix, and the risk suppression coefficient matrix to obtain a risk coupling field.

[0051] Step S43: Obtain the risk coupling field output by step S42 and the pre-stored historical risk evolution data, extract the risk transformation features to obtain a transformation feature matrix; identify the key transformation nodes according to the transformation feature matrix to obtain key node data; calculate the transformation probability according to the transformation feature matrix and the key node data to obtain a transformation probability matrix; construct a transformation mode database according to the transformation feature matrix, the key node data, and the transformation probability matrix to obtain a risk transformation mode set.

[0052] Step S44: Obtain the risk coupling field output in step S42 and the risk transformation mode set output in step S43, calculate the risk accumulation intensity to obtain an accumulation intensity matrix; based on the accumulation intensity matrix, evaluate the time-delay effect to obtain a time-delay effect matrix; based on the accumulation intensity matrix and the time-delay effect matrix, calculate the long-term effect to obtain a long-term effect matrix; based on the accumulation intensity matrix, the time-delay effect matrix, and the long-term effect matrix, use the effect superposition method to obtain an accumulated effect field.

[0053] Step S45: Obtain the risk coupling field output in step S42, the accumulated effect field output in step S44, and the risk transformation mode set output in step S43, calculate the immediate risk distribution to obtain an immediate risk layer; based on the accumulated effect field, calculate the accumulated risk distribution to obtain an accumulated risk layer; based on the risk transformation mode set, calculate the evolutionary risk distribution to obtain an evolutionary risk layer; based on the immediate risk layer, the accumulated risk layer, and the evolutionary risk layer, construct a comprehensive risk index to obtain a comprehensive risk assessment report.

[0054] In this embodiment, through the heterogeneous data fusion and multi-dimensional risk coupling analysis method, the dynamic comprehensive assessment of the compound flood risk is realized. First, the heterogeneous data fusion method is used to integrate and reconstruct the feature field, the comprehensive risk map, and the comprehensive vulnerability assessment field. Then, the multi-dimensional risk coupling analysis method is used to identify the interaction relationships between risk factors, and based on the risk transformation mechanism identification and cumulative effect quantification method, a dynamic comprehensive assessment report is finally obtained. This embodiment overcomes the problem of difficult handling of multi-dimensional risk coupling effects in traditional risk assessment methods. Through risk coupling analysis and cumulative effect quantification, the comprehensive impact of compound risks is accurately evaluated. Especially in the aspect of risk transformation mechanism identification, it can reveal the internal law of risk evolution and provide a scientific basis for risk early warning. This embodiment can comprehensively evaluate the dynamic characteristics of compound flood risks and provide reliable support for urban flood control and disaster reduction decision-making.

[0055] According to one aspect of the present application, the step S11 is specifically as follows:

[0056] Step S111: Obtain the original rainfall monitoring data, original water level monitoring data, and original terrain monitoring data of the monitoring site, and use a multi-source data quality evaluation method (mainly including basic methods such as data integrity inspection, consistency inspection, and outlier detection) to calculate the data reliability index to obtain a data quality assessment matrix; based on the data quality assessment matrix, screen valid data points to obtain a valid monitoring data set.

[0057] Step S112: Obtain the effective monitoring data set output by step S111, use the intelligent spatio-temporal outlier identification algorithm to identify abnormal data points, and obtain an outlier label matrix; according to the outlier label matrix, correct the abnormal data to obtain a corrected monitoring data set; according to the corrected monitoring data set, use the intelligent data filling algorithm to supplement the missing data to obtain a complete monitoring data set. Specifically, the intelligent spatio-temporal outlier identification algorithm is as follows:

[0058] Construct a spatio-temporal correlation matrix ST(i,j) to represent the spatio-temporal correlation degree between monitoring points i and j; calculate the local outlier index: LAI(x) = Σ[w(i)*|x(i) - μ(i)| / σ(i)], where w(i) is the spatio-temporal weight; design a dynamic threshold function: θ(t) = βexp(-αt) + γ, where α, β, and γ are adaptive parameters; when LAI(x) > θ(t), it is determined as an outlier; where x is the data point to be detected; μ(i) is the local mean of the i-th monitoring point; σ(i) is the local standard deviation of the i-th monitoring point; θ(t) is the dynamic threshold function, and t is the time variable.

[0059] The intelligent data filling algorithm has the following process: construct a multi-layer spatio-temporal attention network MSTA; the time attention layer At(i,j) = softmax(Qt*Kt^T); the space attention layer As(i,j) = softmax(Qs*Ks^T); the output filling value y = MSTA(xt-k:t-1, xs), where xt is the time series, xs is the spatial feature, Qs and Ks are the spatial query matrix and the spatial key value matrix respectively; T is the transpose symbol, and xt-k:t-1 represents the historical time series from time t-k to t-1, and k is the backtracking time step.

[0060] Step S113: Obtain the complete monitoring data set output by step S112, use the flood numerical simulation method to simulate the process of levee breach, and obtain the breach process data; according to the breach process data, simulate the evolution process of the breach flow to obtain the flow evolution data; according to the flow evolution data, calculate the process of accumulated waterlogging to obtain the accumulated water process data; according to the breach process data, the flow evolution data and the accumulated water process data, use the simulation parameter adaptive optimization method to obtain the optimized simulation result.

[0061] Step S114: Obtain the optimized simulation result output by step S113, extract the maximum inundation depth data to obtain a water depth distribution matrix; according to the optimized simulation result, extract the maximum flow velocity data to obtain a flow velocity distribution matrix; according to the optimized simulation result, extract the inundation duration data to obtain an inundation duration matrix; according to the water depth distribution matrix, the flow velocity distribution matrix and the inundation duration matrix, construct a spatial distribution data set to obtain a spatial distribution matrix set.

[0062] Step S115: Obtain the set of spatial distribution matrices output by step S114. Use a spatial interpolation optimization algorithm (including classical spatial interpolation methods such as Kriging interpolation and inverse distance weighting method) to spatially process the discrete data to obtain a continuously distributed data set; according to the continuously distributed data set, use a scale conversion algorithm (upsampling, downsampling) to unify the spatial resolution and obtain a data set with a unified scale; according to the data set with a unified scale, use a normalization processing method to obtain a set of normalized spatial distribution matrices.

[0063] In this embodiment, through intelligent data processing and simulation analysis methods, high-quality preprocessing and spatialization of monitoring data are achieved. Specifically, first, a multi-source data quality evaluation method is used to evaluate the reliability of the original monitoring data, and effective data points are screened out; then, a spatio-temporal outlier intelligent recognition algorithm is used to correct the abnormal data, and at the same time, a data filling intelligent algorithm is used to fill in the missing values; then, a flood numerical simulation method is used to simulate the process of levee breach and water flow evolution to obtain accurate hydrodynamic parameters; finally, through spatial interpolation optimization and scale conversion algorithms, the standardized spatial distribution of the data is achieved. This embodiment overcomes problems in traditional data processing methods such as inaccurate outlier recognition, poor missing value filling effect, and low accuracy in simulating hydrodynamic processes. Especially in the aspect of data spatialization processing, through multi-level data quality control and optimization processing, the reliability of the data and the accuracy of spatial expression are improved. This embodiment can provide high-quality basic data support for subsequent risk assessment and effectively enhance the reliability of the entire assessment process.

[0064] According to one aspect of the present application, step S12 is specifically as follows:

[0065] Step S121: Obtain the set of normalized spatial distribution matrices output by step S11. Use a dynamic feature decomposition algorithm to extract temporal variation features to obtain a temporal feature matrix; according to the set of normalized spatial distribution matrices, use a spatial feature recognition algorithm to extract spatial distribution features to obtain a spatial feature matrix; according to the set of normalized spatial distribution matrices, use a multi-variable feature extraction algorithm to identify variable features to obtain a variable feature matrix.

[0066] Among them, the dynamic feature decomposition algorithm is F(t, s, v) = DFD(X); where F is the decomposed feature tensor; t, s, v are the time, space, and variable dimensions; X is the original data matrix; DFD is the dynamic feature decomposition function.

[0067] Step S122: Obtain the temporal feature matrix, spatial feature matrix, and variable feature matrix output by step S121. Using the adaptive correlation analysis method, calculate the correlation coefficient in the time dimension to obtain the time correlation matrix; calculate the spatial position correlation coefficient based on the spatial feature matrix to obtain the spatial correlation matrix; calculate the correlation coefficient between variables based on the variable feature matrix to obtain the variable correlation matrix.

[0068] Step S123: Obtain the time correlation matrix, spatial correlation matrix, and variable correlation matrix output by step S122. Using the dynamic weight calculation method, determine the weight in the time dimension to obtain the time weight vector; calculate the spatial position weight based on the spatial correlation matrix to obtain the spatial weight vector; calculate the variable weight based on the variable correlation matrix to obtain the variable weight vector.

[0069] Step S124: Obtain the time weight vector, spatial weight vector, and variable weight vector output by step S123. Using the multi-dimensional coupling degree calculation method, calculate the spatio-temporal coupling strength to obtain the spatio-temporal coupling matrix; calculate the time-varying coupling strength based on the time weight vector and variable weight vector to obtain the time-varying coupling matrix; calculate the space-varying coupling strength based on the spatial weight vector and variable weight vector to obtain the space-varying coupling matrix.

[0070] Among them, the multi-dimensional coupling degree calculation method is: C(i,j) = [λtCt(i,j) + λsCs(i,j) + λv*Cv(i,j)] / Σλ; where C(i,j) is the comprehensive coupling degree; Ct, Cs, Cv are the coupling degrees in the time, space, and variable dimensions respectively; λt, λs, λv are the weight coefficients of each dimension; i, j are the feature index numbers.

[0071] Step S125: Obtain the spatio-temporal coupling matrix, time-varying coupling matrix, and space-varying coupling matrix output by step S124. Using the multi-level feature decomposition algorithm, extract the dominant feature pattern to obtain the dominant feature matrix; identify the secondary feature pattern based on the dominant feature matrix to obtain the secondary feature matrix; construct a feature hierarchy based on the dominant feature matrix and the secondary feature matrix to obtain the basic feature matrix group.

[0072] In this embodiment, through the multi-dimensional feature analysis and dynamic weight optimization method, the accurate extraction of basic features and the intelligent construction of the feature matrix are realized. First, the dynamic feature decomposition algorithm is adopted to extract features from three dimensions: time series, space, and variables respectively; then, through the adaptive correlation analysis method, the correlation coefficients of each dimension are calculated; next, the dynamic weight calculation method is used to determine the weight coefficients of each dimension; then, through the multi-dimensional coupling degree calculation method, the coupling relationship between features is evaluated; finally, the hierarchical feature matrix system is constructed by using the multi-level feature decomposition algorithm. This embodiment solves the problem that it is difficult to handle the dynamic association of multi-dimensional features in traditional feature extraction methods. Through adaptive weight optimization and multi-level decomposition, the hierarchical structure and dynamic characteristics of features are accurately described. Especially in the quantification of the feature coupling relationship, the dominant features and secondary features can be accurately identified, providing reliable feature support for risk assessment. This embodiment improves the accuracy of feature extraction and the rationality of feature expression.

[0073] According to one aspect of the present application, step S15 is specifically as follows:

[0074] Step S151: Obtain the reconstructed feature field output by step S14 and the set of standardized spatial distribution matrices output by step S11. Use the multi-scale decomposition algorithm to perform scale decomposition on the reconstructed feature field to obtain a multi-scale feature sequence; according to the multi-scale feature sequence, calculate the feature distribution at each scale to obtain a scale distribution matrix; according to the multi-scale feature sequence and the set of standardized spatial distribution matrices, calculate the corresponding relationship at each scale to obtain a scale correspondence matrix.

[0075] Step S152: Obtain the scale distribution matrix and the scale correspondence matrix output by step S151. Use the local feature consistency evaluation method to calculate the feature differences in the local area to obtain a local difference matrix; according to the local difference matrix, identify the feature mutation area to obtain a mutation area identifier; according to the local difference matrix and the mutation area identifier, evaluate the local consistency level to obtain a local consistency index.

[0076] The local feature consistency evaluation method LCI(x) = Σ[w(i)*exp(-d(x,i) / σ)*S(x,i)]; where LCI is the local consistency index; w(i) is the spatial weight coefficient; d(x,i) is the spatial distance function; σ is the spatial scale parameter, and S(x,i) is the feature similarity function.

[0077] Step S153: Obtain the local consistency index output by step S152 and the multi-scale feature sequence output by step S151. Use the index normalization algorithm to convert the reverse index to obtain a set of normalized indices; according to the set of normalized indices, construct an index polarity discrimination criterion to obtain a polarity discrimination matrix; according to the set of normalized indices and the polarity discrimination matrix, optimize the index direction to obtain an optimized set of indices.

[0078] Step S154: Obtain the optimized index set output by step S153, use the adaptive normalization algorithm to calculate the change range of the indexes, and obtain the index range matrix; determine the normalization parameters according to the index range matrix to obtain the normalization parameter set; perform index normalization operation according to the optimized index set and the normalization parameter set to obtain the normalized index matrix.

[0079] Step S155: Obtain the normalized index matrix output by step S154 and the local consistency index output by step S152, use the dynamic threshold construction algorithm to calculate the verification thresholds at each level to obtain the verification threshold sequence; perform multi-level verification according to the normalized index matrix and the verification threshold sequence to obtain the verification result matrix; generate a feature verification report according to the verification result matrix and the local consistency index to obtain the dynamic feature verification report.

[0080] The dynamic threshold construction algorithm is θ(t, s) = α(t)*β(s) + γ; where θ is the dynamic threshold function; t and s are time and space variables; α(t) is the time adjustment function; β(s) is the space adjustment function; γ is the reference threshold.

[0081] In this embodiment, through the multi-scale feature verification and dynamic threshold construction methods, the reliability evaluation of the feature reconstruction result is realized. First, use the multi-scale decomposition algorithm to perform scale decomposition on the reconstructed feature field; then, identify the feature mutation region through the local feature consistency evaluation method; then, use the index positive transformation and adaptive normalization algorithms to optimize the evaluation index system; finally, through the dynamic threshold construction algorithm, realize the intelligence of feature verification. This embodiment overcomes the problems of difficult processing of multi-scale features and determination of dynamic thresholds in traditional feature verification methods, and improves the accuracy of feature verification through local consistency evaluation and dynamic threshold optimization. Especially in the identification of feature mutation regions, it can accurately capture the abnormal changes of features and provide important support for risk early warning. This embodiment effectively guarantees the reliability of the feature reconstruction result and provides quality assurance for subsequent risk assessment.

[0082] According to one aspect of the present application, the specific content of step S21 is as follows:

[0083] Step S211: Obtain the reconstructed feature field output by step S1, the pre-stored historical disaster data and geographical information data, use the multi-dimensional risk factor identification algorithm to extract the hazard index set to obtain the hazard index matrix; extract the exposure index set according to the historical disaster data and geographical information data to obtain the exposure index matrix; extract the vulnerability index set according to the historical disaster data and geographical information data to obtain the vulnerability index matrix.

[0084] Multidimensional risk factor identification algorithm: H = f(R, P, V); where H is the comprehensive risk index; R is the hazard index; P is the exposure index; V is the vulnerability index; and f is the risk comprehensive assessment function.

[0085] Step S212: Obtain the hazard index matrix, exposure index matrix, and vulnerability index matrix output in step S211. Use the index correlation analysis method to calculate the correlation degree between the indexes and obtain the index correlation matrix. According to the index correlation matrix, identify redundant indexes to obtain the redundant index set. Based on the hazard index matrix, exposure index matrix, and vulnerability index matrix, eliminate the indexes in the redundant index set to obtain the preliminary index system.

[0086] Step S213: Obtain the preliminary index system output in step S212. Use the index sensitivity analysis method to calculate the influence degree of each index on the result and obtain the sensitivity matrix. According to the sensitivity matrix, determine the key indexes to obtain the key index set. Based on the key index set, construct the analytic hierarchy structure to obtain the index hierarchy system.

[0087] Index sensitivity analysis method: SI(i) = dY / dXi * Xi / Y + Σ(d²Y / dXidXj * Xi*Xj / Y); where SI is the sensitivity index; Y is the risk assessment result; Xi, Xj are risk indexes; and d is the partial derivative operator.

[0088] Step S214: Obtain the index hierarchy system output in step S213. Use the expert scoring method to collect expert scoring data and obtain the expert scoring matrix. According to the expert scoring matrix, calculate the consistency ratio to obtain the consistency test result. Based on the expert scoring matrix and the consistency test result, use the improved analytic hierarchy process to obtain the initial weight vector.

[0089] Analytic Hierarchy Process (AHP): W = AHP(A); where W is the weight vector; and A is the judgment matrix.

[0090] Step S215: Obtain the initial weight vector output in step S214 and the sensitivity matrix output in step S213. Use the adaptive weight optimization algorithm to fuse the sensitivity analysis results to obtain the optimized weight vector. Based on the optimized weight vector and the index hierarchy system, construct the HEV risk index system to obtain the risk index system. According to the risk index system and the optimized weight vector, determine the index attributes and thresholds to obtain the standardized risk factor matrix set.

[0091] Adaptive weight optimization algorithm: W*(t) = W(t) + ηgrad L(W(t)); where W*(t) is the optimized weight; W(t) is the initial weight; t is the iteration step; η is the learning rate; L is the loss function; and grad is the gradient operator.

[0092] This embodiment realizes the scientific quantification of risk factors through the construction of a multi-level indicator system and a dynamic weight optimization method. First, a multi-dimensional risk factor identification algorithm is used to extract the hazard, exposure and vulnerability indicators respectively; then, the indicator correlation analysis method is used to identify and eliminate redundant indicators; then, the indicator sensitivity analysis method is used to determine the key indicators; then, the indicator weights are preliminarily determined through expert scoring and hierarchical analysis methods; finally, an adaptive weight optimization algorithm is used to construct a scientific risk indicator system. This embodiment solves the problems of arbitrary indicator selection and subjective weight determination in traditional risk indicator construction methods, and improves the scientific nature of risk quantification through multi-level indicator screening and weight optimization. Especially in the identification of key indicators, it can accurately grasp the dominant factors affecting the formation of risks and provide targeted guidance for risk prevention and control. This embodiment improves the accuracy and reliability of risk factor quantification.

[0093] According to one aspect of the present application, step S25 is specifically as follows:

[0094] Step S251, obtain the cascade effect assessment data output by step S24, the critical path set output by step S23 and the standardized risk factor matrix set output by step S21, adopt the risk factor dynamic decomposition method to extract the time characteristics of the risk and obtain the time characteristic sequence; according to the spatial distribution of the cascade effect, extract the spatial characteristics of the risk and obtain the spatial characteristic sequence; according to the correlation between the risk factors, extract the element characteristics of the risk and obtain the element characteristic sequence.

[0095] The dynamic decomposition method of risk factors is RD(t,s) = α(t)*F(s) + β(t)*G(s) + ε(t,s), where RD is the risk decomposition result, t, s are time and space variables, F(s) is the spatial main mode function, G(s) is the spatial secondary mode function, α(t), β(t) are time coefficient functions, and ε is the residual term.

[0096] Step S252, obtain the time feature sequence, space feature sequence and element feature sequence output by step S251, use a multidimensional risk quantification algorithm to calculate the basic risk intensity, and obtain basic risk data; based on the basic risk data, construct a risk level classification criterion to obtain a risk level standard; based on the basic risk data and the risk level standard, classify the risks to obtain a basic risk layer.

[0097] Step S253: Obtain the basic risk layer output by step S252 and the set of critical paths output by step S23. Use the associated risk propagation model to calculate the risk propagation intensity and obtain the propagation intensity matrix. According to the propagation intensity matrix and the set of critical paths, evaluate the associated risk level to obtain the associated risk data. According to the associated risk data and the risk level standard, construct the associated risk distribution to obtain the associated risk layer.

[0098] Step S254: Obtain the cascade effect evaluation data output by step S24 and the associated risk layer output by step S253. Use the cascade effect superposition algorithm to calculate the cascade effect intensity and obtain the cascade effect intensity data. According to the cascade effect intensity data, evaluate the cascade risk level to obtain the cascade risk data. According to the cascade risk data and the risk level standard, construct the cascade risk distribution to obtain the cascade risk layer. Cascade effect superposition algorithm: CE(t) = Σ[Ki*Ri(t)exp(-λiτi)], where CE is the cascade effect intensity, Ki is the propagation coefficient, Ri is the risk intensity, λi is the attenuation coefficient, τi is the time delay parameter, and t is the time variable.

[0099] Step S255: Obtain the basic risk layer output by step S252, the associated risk layer output by step S253, and the cascade risk layer output by step S254. Use the multi-layer risk fusion algorithm to calculate the inter-layer risk coupling degree and obtain the risk coupling matrix. According to the risk coupling matrix, construct the risk map superposition rule to obtain the map superposition criterion. According to the basic risk layer, the associated risk layer, the cascade risk layer, and the map superposition criterion, generate the comprehensive risk distribution map to obtain the comprehensive risk map. Multi-layer risk fusion algorithm R = Σ(wi*Ri); where R is the comprehensive risk value; wi is the risk weight of each layer; Ri is the risk value of each layer.

[0100] This implementation realizes the intelligent construction of the comprehensive risk map through a multi-level risk analysis and dynamic fusion method. First, use the dynamic decomposition method of risk factors to extract the time, space, and factor feature sequences. Then, through the multi-dimensional risk quantification algorithm, calculate the basic risk intensity and grade it. Next, use the associated risk propagation model to evaluate the risk propagation characteristics. Then, through the cascade effect superposition algorithm, quantify the cascade effect intensity. Finally, use the multi-layer risk fusion algorithm to construct the comprehensive risk map. This embodiment overcomes the problems of difficult handling of multi-level risk coupling and dynamic evolution in the traditional risk map construction method. Through risk factor decomposition and multi-layer fusion, it accurately depicts the spatio-temporal distribution characteristics of risks. Especially in the quantification of the risk cascade effect, it can effectively evaluate the cumulative impact of risks and provide a global perspective for risk prevention and control. This embodiment improves the expression ability and practical value of the risk map and provides an intuitive spatial reference for disaster prevention and mitigation decision-making.

[0101] According to one aspect of the present application, step S31 is specifically as follows:

[0102] Step S311: Obtain pre-stored land use data, satellite remote sensing images, and historical land use records. Adopt the multi-temporal land use change analysis method to extract the change characteristics of land use types and obtain the land type change matrix; according to the land type change matrix, identify the main change areas and obtain the key area identifiers; according to the land type change matrix and the key area identifiers, construct the land use classification system and obtain the land use classification data.

[0103] Land use change analysis method: LUCC = (At - At-1) / At-1 * 100%; where At is the land use area at time t; At-1 is the land use area at time t-1.

[0104] Step S312: Obtain pre-stored statistical yearbook data, census data, and economic survey data. Adopt the social and economic data mining algorithm to extract the population distribution characteristics and obtain the population distribution matrix; according to the statistical yearbook data, extract the economic development indicators and obtain the economic indicator matrix; according to the population distribution matrix and the economic indicator matrix, construct the social and economic feature database and obtain the social and economic feature data.

[0105] Step S313: Obtain the land use classification data output by step S311 and the social and economic feature data output by step S312. Adopt the multi-source data correlation analysis method to establish the correspondence between land use and economic indicators and obtain the land use-economic index correlation matrix; according to the land use-economic index correlation matrix, calculate the economic value per unit area and obtain the unit value matrix; according to the land use classification data and the unit value matrix, calculate the regional asset distribution and obtain the asset distribution data.

[0106] Step S314: Obtain the asset distribution data output by step S313 and the social and economic feature data output by step S312. Adopt the spatial interpolation optimization algorithm (Kriging interpolation) to calculate the spatial distribution of economic data and obtain the economic spatial distribution matrix; according to the social and economic feature data, construct the population density distribution model and obtain the population density matrix; according to the economic spatial distribution matrix and the population density matrix, generate the social and economic spatial distribution data and obtain the spatialized social and economic data.

[0107] Step S315: Obtain the spatialized socio-economic data output by step S314, the reconstructed feature field output by step S1, and the comprehensive risk map output by step S2. Use the disaster-bearing body classification and recognition algorithm to identify the types of disaster-bearing bodies, and obtain the disaster-bearing body type matrix; according to the disaster-bearing body type matrix and the spatialized socio-economic data, evaluate the distribution characteristics of the disaster-bearing bodies, and obtain the disaster-bearing body distribution characteristics; according to the disaster-bearing body type matrix, the disaster-bearing body distribution characteristics, and the preset classification criteria, construct a disaster-bearing body classification system, and obtain the classified disaster-bearing body data set.

[0108] The multi-source data association analysis method: RAI(i,j) = w1S(i,j) + w2T(i,j) + w3*E(i,j); where RAI is the association strength index, S is the spatial association degree, T is the temporal association degree, E is the economic association degree, and w1, w2, w3 are weight coefficients.

[0109] The disaster-bearing body classification and recognition algorithm is: V(x) = Σ[αi*Fi(x)]exp(-βd(x)); where V is the vulnerability index; Fi is the feature function; αi is the feature weight; β is the spatial decay coefficient; d is the distance function.

[0110] In this embodiment, through the multi-source data mining and spatialization processing method, the accurate classification and spatial distribution expression of disaster-bearing bodies are realized. First, use the multi-temporal land use change analysis method to extract the land use change characteristics; then, through the socio-economic data mining algorithm, obtain the population and economic distribution characteristics; then, use the multi-source data association analysis method to establish the correspondence between land use and economic indicators; then, through the spatial interpolation optimization algorithm, realize the spatialization of socio-economic data; finally, use the disaster-bearing body classification and recognition algorithm to construct a classification system. This embodiment solves the problem that it is difficult to process multi-source heterogeneous data and spatial distribution characteristics in traditional disaster-bearing body classification methods. Through multi-dimensional data mining and spatialization processing, the accuracy of disaster-bearing body classification is improved. Especially in the spatial expression of socio-economic characteristics, it can accurately depict the spatial distribution law of disaster-bearing bodies and provide a reliable basis for vulnerability assessment. This embodiment improves the scientificity of disaster-bearing body classification and the accuracy of spatial expression.

[0111] According to one aspect of the present application, step S35 is specifically as follows:

[0112] Step S351: Obtain the evolution pattern library output by step S34, the adaptability evaluation matrix output by step S33, and the classified disaster-bearing body data set output by step S31. Use the direct loss assessment method to calculate the loss rate under different inundation depths, and obtain the basic loss rate matrix; according to the inundation duration and flow velocity data, correct the loss rate, and obtain the corrected loss rate matrix; according to the classified disaster-bearing body data set and the corrected loss rate matrix, calculate the direct economic loss, and obtain the direct loss data.

[0113] Step S352: Obtain the direct loss data output by step S351 and the classified disaster-bearing body dataset, and use the static vulnerability assessment algorithm to calculate the basic vulnerability of the disaster-bearing body to obtain the basic vulnerability matrix; according to the basic vulnerability matrix, extract the spatial distribution characteristics to obtain the vulnerability spatial characteristics; according to the basic vulnerability matrix and the vulnerability spatial characteristics, construct the static vulnerability distribution to obtain the static vulnerability layer.

[0114] Step S353: Obtain the evolution pattern library output by step S34 and the static vulnerability layer output by step S352, and use the dynamic vulnerability evolution model to calculate the time evolution characteristics of vulnerability to obtain the time-varying characteristic matrix; according to the time-varying characteristic matrix, identify the key evolution nodes to obtain the evolution node data; according to the time-varying characteristic matrix and the evolution node data, construct the dynamic vulnerability distribution to obtain the dynamic vulnerability layer.

[0115] Step S354: Obtain the adaptability evaluation matrix output by step S33 and the dynamic vulnerability layer output by step S353, and use the adaptability impact evaluation method to calculate the regulatory effect of adaptability on vulnerability to obtain the regulatory coefficient matrix; according to the regulatory coefficient matrix, evaluate the adaptability improvement effect to obtain the improvement effect data; according to the regulatory coefficient matrix and the improvement effect data, construct the adaptive vulnerability distribution to obtain the adaptive vulnerability layer.

[0116] Step S355: Obtain the static vulnerability layer output by step S352, the dynamic vulnerability layer output by step S353, and the adaptive vulnerability layer output by step S354, and use the multi-dimensional vulnerability integration algorithm to calculate the vulnerability weights of each layer to obtain the vulnerability weight vector; according to the vulnerability weight vector, construct the comprehensive vulnerability assessment criterion to obtain the comprehensive assessment criterion; according to the static vulnerability layer, the dynamic vulnerability layer, the adaptive vulnerability layer, and the comprehensive assessment criterion, generate the comprehensive vulnerability assessment result to obtain the comprehensive vulnerability assessment field.

[0117] Direct loss assessment method: L = Σ(ViDiRi), where L is the total loss, Vi is the value, Di is the loss rate, and Ri is the disaster-affected degree.

[0118] Dynamic vulnerability evolution model: DV(t) = V0 + ∫[f(V,t) + g(A,t)]dt, where DV is the dynamic vulnerability, V0 is the initial vulnerability, f is the internal evolution function, g is the external action function, A is the adaptability, and t is the time variable.

[0119] The multi-dimensional vulnerability integration algorithm IV = Σ[wiViexp(-μit) ][1 - AC(t)], where IV is the comprehensive vulnerability, wi is the weight coefficient, Vi is the vulnerability of each dimension, μi is the time decay coefficient, and AC is the adaptation ability function.

[0120] In this embodiment, through the multi-dimensional vulnerability assessment and dynamic integration method, the comprehensive assessment of the vulnerability of disaster-bearing bodies is realized. First, the direct loss assessment method is used to calculate the loss rate under different disaster scenarios; then, the static vulnerability assessment algorithm is used to construct the basic vulnerability distribution; then, the dynamic vulnerability evolution model is used to evaluate the time evolution characteristics; then, the adaptation ability impact assessment method is used to quantify the regulatory role of the adaptation ability; finally, the multi-dimensional vulnerability integration algorithm is used to generate the comprehensive assessment result. This embodiment overcomes the problems in traditional vulnerability assessment methods that it is difficult to handle multi-dimensional vulnerability characteristics and dynamic evolution processes, and accurately depicts the spatio-temporal evolution characteristics of vulnerability through multi-level assessment and dynamic integration. Especially in the aspect of adaptation ability assessment, it can effectively quantify the recovery ability of disaster-bearing bodies and provide targeted suggestions for risk prevention and control. This embodiment improves the comprehensiveness and accuracy of vulnerability assessment.

[0121] According to one aspect of the present application, step S42 is specifically as follows:

[0122] Step S421: Obtain the fusion data set output by step S41, adopt the multi-dimensional risk factor identification algorithm to extract the time change characteristics of risk factors to obtain the time feature matrix; according to the fusion data set, extract the spatial distribution characteristics of risk factors to obtain the spatial feature matrix; according to the time feature matrix and the spatial feature matrix, construct the risk factor feature space to obtain the risk feature space data.

[0123] Step S422: Obtain the risk feature space data output by step S421, adopt the coupling degree dynamic calculation method to calculate the time coupling strength between risk factors to obtain the time coupling matrix; according to the risk feature space data, calculate the spatial coupling strength between risk factors to obtain the spatial coupling matrix; according to the time coupling matrix and the spatial coupling matrix, construct the comprehensive coupling strength distribution to obtain the risk coupling strength matrix.

[0124] Step S423: Obtain the risk coupling strength matrix output by step S422, adopt the risk amplification effect identification algorithm to calculate the positive incentive effect between risk factors to obtain the positive incentive matrix; according to the risk coupling strength matrix, identify the risk chain amplification nodes to obtain the amplification node data; according to the positive incentive matrix and the amplification node data, evaluate the risk amplification effect to obtain the risk amplification coefficient matrix.

[0125] Step S424: Obtain the risk coupling intensity matrix output by step S422 and the risk amplification factor matrix output by step S423, adopt the risk suppression mechanism analysis method to identify risk suppression factors, and obtain a set of suppression factors; according to the set of suppression factors, calculate the suppression intensity to obtain suppression intensity data; according to the set of suppression factors and the suppression intensity data, construct a risk suppression effect model to obtain a risk suppression coefficient matrix.

[0126] Step S425: Obtain the risk coupling intensity matrix output by step S422, the risk amplification factor matrix output by step S423, and the risk suppression coefficient matrix output by step S424, adopt the risk effect comprehensive evaluation algorithm to calculate the net effect of the risk action, and obtain a risk net effect matrix; according to the risk net effect matrix, construct a risk field distribution model to obtain risk field distribution data; according to the risk net effect matrix and the risk field distribution data, generate a risk coupling field distribution map to obtain a risk coupling field.

[0127] Coupling degree calculation method C = sqrt(u*v) / (u+v); where u and v are coupling elements.

[0128] Risk amplification effect identification algorithm AE(t) = R0Π[1 + αiCi(t)], where AE is the amplification effect, R0 is the basic risk, αi is the amplification factor, and Ci is the coupling intensity.

[0129] Risk suppression mechanism analysis method SI(t) = Σ[βi*Ii(t)exp(-λit)], where SI is the suppression intensity, βi is the suppression coefficient, Ii is the intervention intensity, and λi is the time decay coefficient.

[0130] In this embodiment, through the multi-dimensional risk coupling and effect comprehensive evaluation method, the accurate construction of the risk coupling field is realized. First, the multi-dimensional risk factor identification algorithm is adopted to extract the spatio-temporal characteristics of risk factors; then, through the coupling degree dynamic calculation method, the coupling relationship between risk factors is evaluated; then, the risk amplification effect identification algorithm is adopted to quantify the positive incentive effect; then, through the risk suppression mechanism analysis method, the suppression effect is evaluated; finally, the risk effect comprehensive evaluation algorithm is adopted to generate the risk coupling field. This embodiment solves the problem that it is difficult to handle the multi-dimensional risk interaction and dynamic evolution characteristics in the traditional risk coupling analysis method. Through multi-level coupling analysis and effect evaluation, the composite action mechanism of risks is accurately characterized. Especially in the quantification of risk amplification and suppression effects, the net effect of risks can be effectively evaluated, providing a scientific basis for risk prevention and control. This embodiment improves the accuracy and reliability of risk coupling analysis.

[0131] According to one aspect of the present application, step S45 is specifically:

[0132] Step S451: Obtain the risk coupling field output in step S42, the cumulative effect field output in step S44, and the risk transformation mode set output in step S43. Adopt an instant risk assessment algorithm to calculate the risk intensity distribution at the current moment and obtain an instant intensity matrix; based on the instant intensity matrix, identify high-risk areas and obtain key area identifications; based on the instant intensity matrix and the key area identifications, construct an instant risk distribution map and obtain an instant risk layer.

[0133] Step S452: Obtain the cumulative effect field output in step S44 and the instant risk layer output in step S451. Adopt a risk cumulative effect analysis method to calculate the risk cumulative intensity and obtain a cumulative intensity matrix; based on the cumulative intensity matrix, evaluate the influence range of the cumulative effect and obtain influence range data; based on the cumulative intensity matrix and the influence range data, construct a cumulative risk distribution map and obtain a cumulative risk layer.

[0134] Step S453: Obtain the risk transformation mode set output in step S43 and the cumulative risk layer output in step S452. Adopt a risk evolution trend analysis algorithm to predict the risk development trend and obtain a trend prediction matrix; based on the trend prediction matrix, identify key evolution nodes and obtain evolution node data; based on the trend prediction matrix and the evolution node data, construct an evolution risk distribution map and obtain an evolution risk layer.

[0135] Step S454: Obtain the instant risk layer output in step S451, the cumulative risk layer output in step S452, and the evolution risk layer output in step S453. Adopt a multi-dimensional risk comprehensive assessment method to calculate the comprehensive risk index and obtain a comprehensive risk index matrix; based on the comprehensive risk index matrix, determine the risk level classification standard and obtain a classification criterion; based on the comprehensive risk index matrix and the classification criterion, conduct risk level classification and obtain a risk classification result.

[0136] Step S455: Obtain the risk classification result and the comprehensive risk index matrix output in step S454. Adopt an intelligent early warning analysis algorithm to identify early warning trigger conditions and obtain an early warning trigger rule; based on the early warning trigger rule, determine the early warning level and obtain early warning level data; based on the risk classification result, the early warning level data, and a preset report template, generate a comprehensive risk assessment report and obtain a comprehensive risk assessment report. This report includes a risk level distribution map, a risk evolution trend map, the identification result of key risk areas, and risk early warning suggestions.

[0137] Risk cumulative effect analysis: CR = Σ(Ri*ti); where CR is the cumulative risk; Ri is the risk intensity; ti is the action time.

[0138] Risk evolution trend analysis algorithm, RT(t) = αR(t) + β∫R(τ)dτ + γ*dR / dt; where RT is the risk trend; R is the risk intensity; α, β, γ are weight coefficients; τ is the integration variable;

[0139] Intelligent early warning analysis algorithm WL(t) = f[R(t), ΔR(t), ∫R(t)dt], where WL is the early warning level, R is the risk value, ΔR is the risk change rate, and f is the early warning discrimination function.

[0140] In this embodiment, through the multi-dimensional risk assessment and intelligent early warning analysis methods, the dynamic assessment and early warning of comprehensive risks are realized. First, the instant risk assessment algorithm is used to calculate the current risk intensity distribution; then, the risk accumulation effect analysis method is used to evaluate the cumulative risk characteristics; then, the risk evolution trend analysis algorithm is used to predict the risk development trend; then, the multi-dimensional risk comprehensive assessment method is used to calculate the comprehensive risk index; finally, the intelligent early warning analysis algorithm is used to generate a risk assessment report. This embodiment overcomes the problems in traditional risk assessment methods that are difficult to handle the risk evolution and early warning trigger of multiple time scales. Through multi-dimensional risk analysis and intelligent early warning, the timeliness of risk assessment is improved. Especially in terms of risk early warning, it can accurately identify the early warning trigger conditions and provide timely support for disaster prevention and mitigation decision-making. This embodiment improves the predictability of risk assessment and the accuracy of early warning, and provides important decision-making support for urban flood control and disaster reduction. It should be noted that since there are many methods, the existing methods are not described in detail.

[0141] According to another aspect of the present application, there is also provided a system for calculating compound flood risk based on the HEV framework, including:

[0142] At least one processor; and,

[0143] A memory communicatively connected to at least one of the processors; wherein,

[0144] The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method for calculating compound flood risk based on the HEV framework described in any one of the above embodiments.

[0145] It should be noted that in the above specific embodiments, the various specific technical features described can be combined in any suitable manner without conflict. To avoid unnecessary repetition, the present invention does not separately describe various possible combination methods.

Claims

1. A method for calculating compound flood risk based on the HEV framework, characterized in that, It includes the following steps: Step S1: Obtain rainfall monitoring data, water level monitoring data, and terrain monitoring data, and use the feature matrix decomposition algorithm to obtain a basic feature matrix group; according to the basic feature matrix group, use the feature importance calculation method to obtain a feature importance vector; According to the feature importance vector and the basic feature matrix group, use the adaptive feature reconstruction algorithm to obtain a reconstructed feature field; according to the reconstructed feature field, use the multi-scale consistency test method to obtain a dynamic feature verification report; Step S2: Obtain the reconstructed feature field, historical disaster data, and geographical information data, and use the multi-dimensional risk factor analysis method to obtain a standardized risk factor matrix set; according to the standardized risk factor matrix set, use the dynamic association network generation algorithm to obtain a dynamic association network sequence; According to the dynamic association network sequence, use the critical path extraction algorithm to obtain a critical path set and stability evaluation data; according to the critical path set and stability evaluation data, use the risk cascade propagation calculation method to obtain cascade effect evaluation data; according to the cascade effect evaluation data, critical path set, and standardized risk factor matrix set, use the multi-level risk map construction method to obtain a comprehensive risk map; Step S3: Obtain the reconstructed feature field, comprehensive risk map, and pre-stored socio-economic data, and use the adaptive disaster-bearing body classification method to obtain a classified disaster-bearing body data set; according to the classified disaster-bearing body data set and historical disaster response data, use the multi-modal response analysis method to obtain a vulnerability response surface; according to the vulnerability response surface and socio-economic capacity data, use the dynamic adaptability evaluation method to obtain an adaptability evaluation matrix; according to the vulnerability response surface and adaptability evaluation matrix, use the evolutionary pattern recognition method to obtain an evolutionary pattern library; according to the evolutionary pattern library, adaptability evaluation matrix, and classified disaster-bearing body data set, use the multi-dimensional comprehensive evaluation method to obtain a comprehensive vulnerability evaluation field; Step S4: Obtain the reconstructed feature field, comprehensive risk map, and comprehensive vulnerability evaluation field, and use the heterogeneous data fusion method to obtain a fused data set; According to the fused data set, use the multi-dimensional risk coupling analysis method to obtain a risk coupling field; According to the risk coupling field and historical risk evolution data, use the risk transformation mechanism identification method to obtain a risk transformation mode set; According to the risk coupling field and risk transformation mode set, use the risk accumulation effect quantification method to obtain an accumulation effect field; according to the risk coupling field, accumulation effect field, and risk transformation mode set, use the dynamic comprehensive evaluation method to obtain a comprehensive risk assessment report.

2. The method for calculating composite flood risk based on the HEV framework according to claim 1, wherein The specific content of step S1 is as follows: Step S11: Obtain the rainfall monitoring data, water level monitoring data, and terrain monitoring data of the monitoring sites, and construct a rainfall spatial distribution matrix, a water level spatial distribution matrix, and a terrain feature matrix according to the spatial position information; according to the rainfall spatial distribution matrix, water level spatial distribution matrix, and terrain feature matrix, use the linear transformation method to obtain a standardized spatial distribution matrix set; Step S12: Obtain the set of standardized spatial distribution matrices, calculate the correlation coefficients between spatial positions to obtain the spatial correlation matrix; calculate the change characteristics of the time series based on the time series data in the set of standardized spatial distribution matrices to obtain the time evolution matrix; calculate the coupling degree between variables based on the different monitoring variable data in the set of standardized spatial distribution matrices to obtain the variable coupling matrix; use multi-level decomposition operations based on the spatial correlation matrix, time evolution matrix, and variable coupling matrix to obtain the basic feature matrix group; Step S13: Obtain the basic feature matrix group, calculate the change amplitude of each feature in the time dimension to obtain the time-varying weight vector; calculate the spatial influence coefficient based on the spatial distribution range of the basic feature matrix group to obtain the spatial influence matrix; use weighted fusion operations based on the time-varying weight vector and spatial influence matrix to obtain the feature importance vector; Step S14: Obtain the basic feature matrix group and the feature importance vector, construct a non-linear weight function, calculate the dynamic weight coefficient of each feature to obtain the dynamic weight matrix; perform weighted combination on the basic feature matrix group according to the dynamic weight matrix to obtain the initial reconstructed feature field; obtain the continuity constraint conditions of time and space, and optimize and adjust the initial reconstructed feature field to obtain the reconstructed feature field; Step S15: Obtain the reconstructed feature field and the set of standardized spatial distribution matrices, calculate the feature consistency index of the local area to obtain the local consistency matrix; calculate the feature consistency index of the global scope based on the reconstructed feature field to obtain the global consistency vector; construct a dynamic threshold judgment criterion based on the local consistency matrix and the global consistency vector to generate a dynamic feature verification report.

3. A method for calculating compound flood risk based on the HEV framework according to claim 2, characterized in that, The specific content of step S2 is as follows: Step S21: Obtain the reconstructed feature field, pre-stored historical disaster data, and geographical information data, extract hydrometeorological parameters to obtain the hydrometeorological factor matrix; extract topographic and geomorphic features based on the geographical information data to obtain the topographic and geomorphic factor matrix; Obtain land use and flood control project data, extract human activity characteristics to obtain the human activity factor matrix; use the standardized processing method based on the hydrometeorological factor matrix, topographic and geomorphic factor matrix, and human activity factor matrix to obtain the set of standardized risk factor matrices; Step S22: Obtain the set of standardized risk factor matrices, calculate the correlation intensity between each risk factor at different times to obtain the time-varying correlation intensity matrix; construct a dynamic threshold discrimination function based on the time-varying correlation intensity matrix, screen out significant correlation relationships to obtain the significant correlation matrix; Construct a time-varying network structure based on the significant correlation matrix to obtain a dynamic correlation network sequence; Step S23: Obtain the dynamic correlation network sequence, calculate the importance degree of each network node to obtain the node importance vector; identify the main paths of risk propagation based on the node importance vector and the dynamic correlation network sequence to obtain the set of key paths; evaluate the time stability of the paths based on the set of key paths to obtain the stability evaluation data; Step S24: Obtain the set of key paths and the stability evaluation data, calculate the propagation intensity of the risk on the key paths to obtain the propagation intensity matrix; Calculate the delay effect of risk propagation according to the propagation intensity matrix to obtain the time-delay effect matrix; Calculate the cumulative impact degree of the risk according to the propagation intensity matrix and the time-delay effect matrix to obtain the cascade effect evaluation data; Step S25: Obtain the cascade effect evaluation data, the critical path set, and the standardized risk factor matrix set, calculate the basic risk distribution to obtain the basic risk layer; Calculate the associated risk distribution according to the basic risk layer and the critical path set to obtain the associated risk layer; Calculate the cascade risk distribution according to the associated risk layer and the cascade effect evaluation data to obtain the cascade risk layer; According to the basic risk layer, the associated risk layer, and the cascade risk layer, use the weighted superposition method to obtain the comprehensive risk map.

4. A method for calculating composite flood risk based on the HEV framework according to claim 3, wherein, The specific steps of step S3 are as follows: Step S31: Obtain the reconstructed feature field, the comprehensive risk map, and the pre-stored socio-economic data, extract the spatial distribution characteristics of the disaster-bearing bodies to obtain the disaster-bearing body feature matrix; construct dynamic classification rules according to the time series data to obtain dynamic classification criteria; classify the disaster-bearing bodies according to the disaster-bearing body feature matrix and the dynamic classification criteria to obtain the classified disaster-bearing body data set; Step S32: Obtain the classified disaster-bearing body data set and the pre-stored historical disaster response data, extract the response characteristics of different types of disaster-bearing bodies to obtain the response feature matrix; Calculate the sensitivity of the disaster-bearing body to the disaster according to the response feature matrix to obtain the time-varying sensitivity matrix; evaluate the recovery ability of the disaster-bearing body according to the response feature matrix and the time-varying sensitivity matrix to obtain the recovery ability matrix; construct a response surface model according to the response feature matrix, the time-varying sensitivity matrix, and the recovery ability matrix to obtain the vulnerability response surface; Step S33: Obtain the vulnerability response surface and the pre-stored socio-economic capacity data, construct an adaptation ability evaluation index system to obtain the adaptation ability index matrix; calculate the resource allocation efficiency according to the socio-economic capacity data to obtain the resource efficiency matrix; evaluate the system recovery elasticity according to the adaptation ability index matrix and the resource efficiency matrix to obtain the system elasticity matrix; use the comprehensive evaluation method according to the adaptation ability index matrix, the resource efficiency matrix, and the system elasticity matrix to obtain the adaptation ability evaluation matrix; Step S34: Obtain the vulnerability response surface and the adaptation ability evaluation matrix, extract the spatio-temporal change characteristics of the vulnerability to obtain the evolution feature vector set; According to the evolution feature vector set, identify the typical evolution patterns to obtain the key evolution patterns; predict the vulnerability change trend according to the key evolution patterns to obtain the evolution trend data; construct an evolution pattern database according to the key evolution patterns and the evolution trend data to obtain the evolution pattern library; Step S35: Obtain the evolution pattern library, the adaptation ability evaluation matrix, and the classified disaster-bearing body data set, calculate the static vulnerability distribution to obtain the static vulnerability layer; calculate the dynamic vulnerability distribution according to the evolution pattern library to obtain the dynamic vulnerability layer; calculate the adaptive vulnerability distribution according to the adaptation ability evaluation matrix to obtain the adaptive vulnerability layer; use the multi-dimensional integration method according to the static vulnerability layer, the dynamic vulnerability layer, and the adaptive vulnerability layer to obtain the comprehensive vulnerability evaluation field.

5. A method for calculating compound flood risk based on the HEV framework according to claim 4, characterized in that, The specific steps of step S4 are as follows: Step S41: Obtain the reconstructed feature field, the comprehensive risk map, and the comprehensive vulnerability assessment field, calculate the correlation features between the data to obtain the data correlation matrix; according to the spatio-temporal distribution features, construct a consistency test criterion to obtain the spatio-temporal consistency test matrix; According to the data correlation matrix and the spatio-temporal consistency test matrix, perform fusion processing on the multi-source data to obtain a fused data set; Step S42: Obtain the fused data set, calculate the coupling degree between different risk types to obtain the risk coupling intensity matrix; According to the risk coupling intensity matrix, calculate the risk amplification effect to obtain the risk amplification coefficient matrix; According to the risk coupling intensity matrix, calculate the risk suppression effect to obtain the risk suppression coefficient matrix; According to the risk coupling intensity matrix, the risk amplification coefficient matrix, and the risk suppression coefficient matrix, adopt a coupling effect integration method to obtain the risk coupling field; Step S43: Obtain the risk coupling field and the pre-stored historical risk evolution data, extract the risk transformation features to obtain the transformation feature matrix; according to the transformation feature matrix, identify the key transformation nodes to obtain the key node data; according to the transformation feature matrix and the key node data, calculate the transformation probability to obtain the transformation probability matrix; according to the transformation feature matrix, the key node data, and the transformation probability matrix, construct a transformation mode database to obtain the risk transformation mode set; Step S44: Obtain the risk coupling field and the risk transformation mode set, calculate the risk accumulation intensity to obtain the accumulation intensity matrix; According to the accumulation intensity matrix, evaluate the time-delay effect to obtain the time-delay effect matrix; According to the accumulation intensity matrix and the time-delay effect matrix, calculate the long-term effect to obtain the long-term effect matrix; according to the accumulation intensity matrix, the time-delay effect matrix, and the long-term effect matrix, adopt an effect superposition method to obtain the cumulative effect field; Step S45: Obtain the risk coupling field, the cumulative effect field, and the risk transformation mode set, calculate the immediate risk distribution to obtain the immediate risk layer; According to the cumulative effect field, calculate the cumulative risk distribution to obtain the cumulative risk layer; According to the risk transformation mode set, calculate the evolutionary risk distribution to obtain the evolutionary risk layer; According to the immediate risk layer, the cumulative risk layer, and the evolutionary risk layer, construct a comprehensive risk index to obtain a comprehensive risk assessment report.

6. The method for calculating the composite flood risk based on the HEV framework according to claim 5, wherein The specific content of the said Step S11 is as follows: Step S111: Obtain the original rainfall monitoring data, the original water level monitoring data, and the original terrain monitoring data of the monitoring sites, adopt a multi-source data quality evaluation method to calculate the data reliability index to obtain the data quality assessment matrix; according to the data quality assessment matrix, screen the valid data points to obtain the valid monitoring data set; Step S112: Obtain the valid monitoring data set, adopt a spatio-temporal outlier intelligent identification algorithm to identify the outlier data points to obtain the outlier label matrix; According to the outlier label matrix, correct the outlier data to obtain the corrected monitoring data set; according to the corrected monitoring data set, adopt a data filling intelligent algorithm to supplement the missing data to obtain the complete monitoring data set; Step S113: Obtain the complete monitoring data set, adopt a flood numerical simulation method to simulate the process of levee breach to obtain the breach process data; Based on the breach process data, simulate the evolution process of the breach flow to obtain the flow evolution data; according to the flow evolution data, calculate the waterlogging process to obtain the waterlogging process data; Based on the breach process data, the flow evolution data, and the waterlogging process data, use the simulation parameter adaptive optimization method to obtain the optimized simulation result; Step S114: Obtain the optimized simulation result, extract the maximum inundation depth data to obtain the water depth distribution matrix; according to the optimized simulation result, extract the maximum flow velocity data to obtain the flow velocity distribution matrix; according to the optimized simulation result, extract the inundation duration data to obtain the inundation duration matrix; based on the water depth distribution matrix, the flow velocity distribution matrix, and the inundation duration matrix, construct a spatial distribution dataset to obtain a set of spatial distribution matrices; Step S115: Obtain the set of spatial distribution matrices, use the spatial interpolation optimization algorithm to spatially process the discrete data to obtain a continuous distribution dataset; according to the continuous distribution dataset, use the scale conversion algorithm to unify the spatial resolution to obtain a unified scale dataset; according to the unified scale dataset, use the standardization processing method to obtain a set of standardized spatial distribution matrices.

7. A method for calculating compound flood risk based on the HEV framework according to claim 5, characterized in that The specific content of step S12 is as follows: Step S121: Obtain the set of standardized spatial distribution matrices, use the dynamic eigen - decomposition algorithm to extract the temporal variation characteristics to obtain the temporal characteristic matrix; according to the set of standardized spatial distribution matrices, use the spatial feature recognition algorithm to extract the spatial distribution characteristics to obtain the spatial characteristic matrix; according to the set of standardized spatial distribution matrices, use the multi - variable feature extraction algorithm to identify the variable characteristics to obtain the variable characteristic matrix; Step S122: Obtain the temporal characteristic matrix, the spatial characteristic matrix, and the variable characteristic matrix, use the adaptive correlation analysis method to calculate the correlation coefficient in the time dimension to obtain the time - related matrix; According to the spatial characteristic matrix, calculate the spatial position correlation coefficient to obtain the spatial - related matrix; According to the variable characteristic matrix, calculate the correlation coefficient between variables to obtain the variable - related matrix; Step S123: Obtain the time - related matrix, the spatial - related matrix, and the variable - related matrix, use the dynamic weight calculation method to determine the weight in the time dimension to obtain the time - weight vector; according to the spatial - related matrix, calculate the spatial position weight to obtain the spatial - weight vector; According to the variable - related matrix, calculate the variable weight to obtain the variable - weight vector; Step S124: Obtain the time - weight vector, the spatial - weight vector, and the variable - weight vector, use the multi - dimensional coupling degree calculation method to calculate the spatio - temporal coupling strength to obtain the spatio - temporal coupling matrix; according to the time - weight vector and the variable - weight vector, calculate the time - varying coupling strength to obtain the time - varying coupling matrix; according to the spatial - weight vector and the variable - weight vector, calculate the space - varying coupling strength to obtain the space - varying coupling matrix; Step S125: Obtain the spatio - temporal coupling matrix, the time - varying coupling matrix, and the space - varying coupling matrix, use the multi - level eigen - decomposition algorithm to extract the dominant feature patterns to obtain the dominant feature matrix; According to the dominant feature matrix, identify the secondary feature patterns to obtain the secondary feature matrix; According to the dominant feature matrix and the secondary feature matrix, construct a feature hierarchy to obtain a basic feature matrix group.

8. A method for calculating compound flood risk based on the HEV framework according to claim 5, characterized in that, The specific content of step S15 is as follows: Step S151: Obtain the reconstructed feature field and the set of standardized spatial distribution matrices. Use the multi-scale decomposition algorithm to perform scale decomposition on the reconstructed feature field to obtain a multi-scale feature sequence. Calculate the feature distribution at each scale according to the multi-scale feature sequence to obtain a scale distribution matrix. Calculate the corresponding relationship at each scale according to the multi-scale feature sequence and the set of standardized spatial distribution matrices to obtain a scale correspondence matrix. Step S152: Obtain the scale distribution matrix and the scale correspondence matrix. Use the local feature consistency evaluation method to calculate the feature differences in the local area to obtain a local difference matrix. Identify the feature mutation regions according to the local difference matrix to obtain a mutation region identifier. Evaluate the local consistency level according to the local difference matrix and the mutation region identifier to obtain a local consistency index. Step S153: Obtain the local consistency index and the multi-scale feature sequence. Use the index positive transformation algorithm to transform the reverse index to obtain a set of positive transformation indexes. Construct an index polarity discrimination criterion according to the set of positive transformation indexes to obtain a polarity discrimination matrix. Optimize the index direction according to the set of positive transformation indexes and the polarity discrimination matrix to obtain an optimized index set. Step S154: Obtain the optimized index set. Use the adaptive normalization algorithm to calculate the change range of the indexes to obtain an index range matrix. Determine the normalization parameters according to the index range matrix to obtain a set of normalization parameters. Perform index normalization operations according to the optimized index set and the set of normalization parameters to obtain a normalized index matrix. Step S155: Obtain the normalized index matrix and the local consistency index. Use the dynamic threshold construction algorithm to calculate the verification thresholds at each level to obtain a verification threshold sequence. Perform multi-level verification according to the normalized index matrix and the verification threshold sequence to obtain a verification result matrix. Generate a feature verification report according to the verification result matrix and the local consistency index to obtain a dynamic feature verification report.

9. A method for calculating composite flood risk based on the HEV framework according to claim 5, characterized in that The specific content of step S21 is as follows: Step S211: Obtain the reconstructed feature field, the pre-stored historical disaster data, and the geographical information data. Use the multi-dimensional risk factor identification algorithm to extract the set of hazard indicators to obtain a hazard indicator matrix. Extract the set of exposure indicators according to the historical disaster data and the geographical information data to obtain an exposure indicator matrix. Extract the set of vulnerability indicators according to the historical disaster data and the geographical information data to obtain a vulnerability indicator matrix. Step S212: Obtain the hazard indicator matrix, the exposure indicator matrix, and the vulnerability indicator matrix. Use the index correlation analysis method to calculate the correlation degree between the indicators to obtain an index correlation matrix. Identify the redundant indicators according to the index correlation matrix to obtain a set of redundant indicators. Remove the indicators in the set of redundant indicators from the hazard indicator matrix, the exposure indicator matrix, and the vulnerability indicator matrix to obtain a preliminary index system. Step S213: Obtain the preliminary index system. Use the index sensitivity analysis method to calculate the influence degree of each indicator on the result to obtain a sensitivity matrix. Determine the key indicators according to the sensitivity matrix to obtain a set of key indicators. Construct an analytic hierarchy structure according to the set of key indicators to obtain an index hierarchy system. Step S214: Obtain the index hierarchy system, use the expert scoring method to collect expert scoring data, and obtain the expert scoring matrix; according to the expert scoring matrix, calculate the consistency ratio to obtain the consistency test result; according to the expert scoring matrix and the consistency test result, use the improved analytic hierarchy process to obtain the initial weight vector. Step S215: Obtain the initial weight vector and the sensitivity matrix, use the adaptive weight optimization algorithm to fuse the sensitivity analysis results, and obtain the optimized weight vector. According to the optimized weight vector and the index hierarchy system, construct the HEV risk index system to obtain the risk index system; according to the risk index system and the optimized weight vector, determine the index attributes and thresholds to obtain the standardized risk factor matrix set.

10. A system for calculating compound flood risk based on the HEV framework, characterized in that, Including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method for calculating the compound flood risk based on the HEV framework according to any one of claims 1 to 9.

Images