Urban flood control toughness critical state identification method and system considering multiple pressure coupling

Abstract

The invention discloses an urban flood control toughness critical state identification method and system considering multiple pressure coupling. Performing space-time unified preprocessing on original meteorological, hydrological, engineering and social economic data, and performing pressure characteristic decomposition after abnormal value detection and correction; analyzing a coupling relation between pressure elements based on mutual information entropy and Granger causality test, constructing a dynamic network and extracting network evolution characteristics; state index construction is carried out in combination with historical toughness evaluation data, and a toughness state evolution model is established through time sequence decomposition and scene simulation; critical characteristic analysis and threshold optimization are performed based on real-time monitoring data, and dynamic identification of the flood control toughness critical state is realized. According to the method, the critical state of the urban flood control system under multiple pressure coupling can be accurately identified, and the early warning accuracy is improved.

Description

Technical Field

[0001] The invention relates to flood simulation technology, in particular to a method and system for identifying critical states of urban flood control resilience considering multiple pressure couplings. Background Art

[0002] Under the dual influence of global climate change and rapid urbanization, urban flood control systems are facing unprecedented challenges. The coupling of multiple stress factors such as frequent extreme rainfall events, expansion of urban impervious areas, and aging of drainage systems has led to increasingly complex mechanisms of urban flood disasters. Studies have shown that the urban flood resilience assessment method under a single stress source can no longer meet the needs of the current complex urban system. It is urgent to establish a critical state identification method for urban flood resilience under multiple pressure coupling conditions to enhance urban flood control and disaster reduction capabilities.

[0003] At present, the research on urban flood resilience mainly focuses on the assessment methods and determination of static thresholds under a single stress source. Traditional methods usually use deterministic hydrological models to simulate rainfall-runoff processes, or use statistical methods to analyze historical flood event data and establish an experience-based early warning indicator system. Some studies have attempted to introduce socioeconomic vulnerability indicators to build a comprehensive assessment framework. However, these methods often separate different stress sources for independent analysis, ignoring the dynamic coupling effects between stress factors. At the same time, the existing early warning thresholds are mostly determined based on static statistical analysis, lacking consideration of the dynamic evolution characteristics of the system.

[0004] In practical applications, the existing technologies have the following key problems: First, the inconsistent spatiotemporal scales of multi-source heterogeneous data lead to information distortion in the data integration process, making it difficult to accurately characterize the spatiotemporal distribution characteristics of different pressure factors. Second, traditional correlation analysis methods are difficult to capture the nonlinear coupling relationship between pressure factors, especially when considering the time lag effect, and cannot effectively identify the causal chain. Third, the existing resilience assessment models are mostly based on the principle of linear superposition, ignoring the synergy and antagonism between pressure factors, resulting in large errors in the judgment of the critical state of the system. In addition, the dynamic optimization problem of the warning threshold has not been effectively solved, especially when considering the multiple pressure coupling effects, how to establish an adaptive threshold update mechanism is still a challenge. The sensitivity analysis method of system parameters is relatively simple, and it is difficult to accurately assess the impact of parameter disturbances on model results, which affects the reliability of the warning results. Summary of the invention

[0005] The purpose of the invention is to provide a method and system for identifying the critical state of urban flood resilience considering multiple pressure couplings, in order to solve at least one technical problem existing in the prior art.

[0006] Technical solution, according to one aspect of the present application, provides a method for identifying critical states of urban flood resilience considering multiple pressure coupling, comprising the following steps:

[0007] Step S1: According to the characteristics of the urban flood control system, identify the pressure sources that affect the resilience and performance of the urban flood control system; obtain the research data and perform unified spatiotemporal preprocessing, outlier detection and correction to obtain a corrected data set; decompose the pressure characteristics of the corrected data set to obtain a pressure feature vector set including time dimension characteristics, space dimension characteristics and intensity dimension characteristics;

[0008] Step S2, obtaining a pressure feature vector set and performing coupling relationship analysis to obtain a coupling strength matrix and a coupling direction matrix; constructing a directed weighted network based on the coupling strength matrix and the coupling direction matrix to obtain a pressure coupling dynamic network; performing a topological structure analysis on the pressure coupling dynamic network to obtain a network evolution feature set;

[0009] Step S3: Comprehensively analyze the network evolution feature set and the pre-stored historical resilience assessment data to obtain a resilience state indicator set; perform time series decomposition and scenario simulation to obtain scenario simulation data; construct a state evolution prediction model based on the scenario simulation data and the resilience state indicator set to obtain a resilience state evolution model;

[0010] Step S4: perform critical feature analysis based on the toughness state evolution model and pre-stored real-time monitoring data to obtain a critical feature indicator set; perform threshold optimization calculation based on the critical feature indicator set to obtain an early warning threshold set.

[0011] According to one aspect of the present application, step S1 specifically comprises:

[0012] Step S11: according to the characteristics of the urban flood control system, identify the main stressors that affect the resilience and performance of the urban flood control system, including meteorological stressors, hydrological stressors, engineering stressors, and socio-economic stressors;

[0013] Step S12, obtaining research data, performing Kriging interpolation calculation, and obtaining temporary spatial interpolation data; performing linear interpolation on the temporary spatial interpolation data according to the time series to obtain temporary time interpolation data; calculating the time weight function according to the inverse of the data time interval, and performing weight correction on the temporary time interpolation data to obtain a unified spatiotemporal scale data set;

[0014] Step S13, read the unified spatiotemporal scale data set and calculate the mean and standard deviation to obtain statistical feature data; perform preliminary identification of outliers to obtain preliminary outlier data and compare it with physical constraints to obtain confirmed outlier data and perform correction to obtain corrected data; merge the corrected data with the normal value data in the unified spatiotemporal scale data set to obtain a corrected data set;

[0015] Step S14, extracting rainfall data from the corrected data set and performing rainfall-runoff simulation to obtain runoff simulation data; performing evolution calculation on the runoff simulation data to obtain flood inundation data; merging the flood inundation data with the corrected data set to obtain hydrodynamic characteristic data;

[0016] Step S15, perform wavelet transform on the hydrodynamic characteristic data to obtain a wavelet coefficient set; perform threshold decomposition on the wavelet coefficient set to obtain characteristic component data of different scales; reorganize the characteristic component data to obtain multidimensional characteristic data; standardize the multidimensional characteristic data to obtain standardized characteristic data; convert the standardized characteristic data into a vector form to obtain a pressure characteristic vector set.

[0017] According to one aspect of the present application, step S2 is specifically:

[0018] Step S21, obtaining and calculating the mutual information entropy for each pair of eigenvectors in the pressure eigenvector set to obtain a mutual information entropy matrix; calculating the coupling strength value to obtain a coupling strength matrix; calculating the Granger causality test statistic for each pair of eigenvectors in the pressure eigenvector set to obtain causality test data; determining the coupling direction according to the causality test data to obtain a coupling direction matrix;

[0019] Step S22: constructing network edge weights based on the coupling strength matrix to obtain a weighted edge set; determining the direction of the network edge based on the coupling direction matrix to obtain a directed edge set; combining the weighted edge set and the directed edge set, and adding a time tag to obtain a pressure-coupled dynamic network;

[0020] Step S23, calculating node degree feature data, clustering feature data, centrality feature data and community evolution data based on the pressure-coupled dynamic network; and combining them to obtain a network evolution feature set.

[0021] According to one aspect of the present application, step S3 is specifically:

[0022] Step S31, perform principal component analysis on the network evolution feature set to obtain principal component feature data; perform standardization processing on the pre-stored historical resilience assessment data to obtain standardized resilience data; perform correlation analysis on the principal component feature data and the standardized resilience data to obtain a feature correlation matrix; select key feature combinations according to the feature correlation matrix to obtain a resilience feature candidate set; perform weighted combination on the resilience feature candidate set to obtain a resilience state indicator set;

[0023] Step S32, performing time series decomposition on the toughness state indicator set to obtain trend component data and fluctuation component data; setting different boundary conditions according to the trend component data and the fluctuation component data to obtain scenario boundary data; using a hydrodynamic model to simulate and calculate the scenario boundary data to obtain scenario simulation data;

[0024] Step S33: construct an autoregressive model for the scenario simulation data and the resilience state indicator set to obtain trend prediction data; calculate the phase space reconstruction parameters based on the scenario simulation data to obtain reconstruction parameter data; construct the phase space according to the reconstruction parameter data to obtain state space data; combine the trend prediction data and the state space data to construct a hybrid prediction model to obtain a resilience state evolution model.

[0025] According to one aspect of the present application, step S4 is specifically:

[0026] Step S41: Calculate the system state change rate for the resilience state evolution model to obtain state change rate data; perform normalization processing and fluctuation analysis on the pre-stored real-time monitoring data to obtain dynamic fluctuation characteristic data; calculate the time correlation of the normalized monitoring data to obtain time correlation data; perform feature fusion on the dynamic fluctuation characteristic data and the time correlation data to obtain a critical feature indicator set;

[0027] Step S42, perform statistical distribution analysis on the critical characteristic indicator set to obtain distribution characteristic data; construct a probability density function based on the distribution characteristic data to obtain density function data; perform quantile analysis on the density function data to obtain quantile characteristic data; calculate the optimal split point based on the quantile characteristic data to obtain split point data; convert the split point data into warning thresholds to obtain a warning threshold set.

[0028] According to another aspect of the present application, a system for identifying critical states of urban flood resilience considering multiple pressure coupling is also provided, comprising:

[0029] at least one processor; and,

[0030] a memory communicatively connected to at least one processor; wherein,

[0031] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the critical state identification method of urban flood resilience considering multiple pressure coupling of any of the above technical solutions.

[0032] Beneficial effect: can accurately identify the critical state of the urban flood control system under multiple pressure coupling, and improve the accuracy of early warning. The relevant technical effects will be described in detail below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the method of the present invention.

[0034] Figure 2 It is a flow chart of step S1 of the present invention.

[0035] Figure 3It is a flow chart of step S2 of the present invention.

[0036] Figure 4 It is a flow chart of step S3 of the present invention.

[0037] Figure 5 It is a flow chart of step S4 of the present invention. DETAILED DESCRIPTION

[0038] like Figure 1 As shown, according to one aspect of the present application, a method for identifying critical states of urban flood resilience considering multiple pressure coupling is provided, comprising the following steps:

[0039] Step S1: According to the characteristics of the urban flood control system, identify the pressure sources that affect the resilience and performance of the urban flood control system; obtain the research data and perform unified spatiotemporal preprocessing to obtain a unified spatiotemporal scale data set; perform outlier detection and correction on the unified spatiotemporal scale data set to obtain a corrected data set; perform pressure feature decomposition on the corrected data set to obtain a pressure feature vector set including time dimension features, space dimension features and intensity dimension features;

[0040] Step S2, obtaining a pressure feature vector set and performing coupling relationship analysis to obtain a coupling strength matrix and a coupling direction matrix; constructing a directed weighted network based on the coupling strength matrix and the coupling direction matrix to obtain a pressure coupling dynamic network; performing a topological structure analysis on the pressure coupling dynamic network to obtain a network evolution feature set;

[0041] Step S3: Comprehensively analyze the network evolution feature set and the pre-stored historical resilience assessment data to obtain a resilience state indicator set; perform time series decomposition and scenario simulation on the resilience state indicator set to obtain scenario simulation data; construct a state evolution prediction model based on the scenario simulation data and the resilience state indicator set to obtain a resilience state evolution model;

[0042] Step S4: perform critical feature analysis based on the toughness state evolution model and pre-stored real-time monitoring data to obtain a critical feature indicator set; perform threshold optimization calculation based on the critical feature indicator set to obtain an early warning threshold set.

[0043] Through systematic data processing, network analysis, model construction and threshold identification, a complete set of critical state identification methods for urban flood control resilience has been established. Starting from data preprocessing, the quality of basic data is guaranteed through the spatiotemporal unification of multi-source data and correction of outliers; through pressure feature decomposition and coupled network construction, the complex interaction relationship between system pressure elements is revealed; then, a resilience state prediction model is established based on network evolution characteristics to achieve dynamic prediction of system state; finally, the warning threshold is determined through critical feature analysis, providing a scientific basis for flood control decision-making. The progressive and mutually supportive technical solutions not only improve the accuracy and reliability of urban flood control system resilience assessment, but also enhance the real-time and adaptability of the early warning system, providing innovative solutions for urban flood control and disaster reduction.

[0044] like Figure 2 As shown, according to one aspect of the present application, step S1 is specifically:

[0045] Step S11: According to the characteristics of the urban flood control system, identify the main stressors that affect the resilience and performance of the urban flood control system; including meteorological stressors, hydrological stressors, engineering stressors and socio-economic stressors; meteorological stressors include rainfall intensity and rainfall duration; hydrological stressors include water level changes and flow fluctuations in rivers or drainage systems; engineering stressors include gate pump status, drainage system capacity and pipe network status; socio-economic stressors include population density, economic activity intensity and traffic flow;

[0046] Step S12, obtaining research data, including original meteorological data, original hydrological data, original engineering data and original socio-economic data; extracting rainfall intensity and duration data from original meteorological data, water level and flow data from original hydrological data, sluice pump status, drainage system capacity and pipe network status data from original engineering data, and population density and asset distribution data from original socio-economic data, and performing Kriging interpolation calculation to obtain temporary spatial interpolation data; performing linear interpolation on the temporary spatial interpolation data according to the time series to obtain temporary time interpolation data; calculating the time weight function according to the inverse of the data time interval, and performing weight correction on the temporary time interpolation data to obtain a unified spatiotemporal scale data set;

[0047] Step S13, reading the unified spatiotemporal scale data set and calculating the mean and standard deviation to obtain statistical feature data; using the box plot method to preliminarily identify outliers on the unified spatiotemporal scale data set to obtain preliminary outlier data; comparing the preliminary outlier data with the physical constraint conditions to obtain confirmed outlier data; using the local polynomial regression method to correct the confirmed outlier data to obtain corrected data; merging the corrected data with the normal value data in the unified spatiotemporal scale data set to obtain a corrected data set;

[0048] Step S14, extracting rainfall data from the corrected data set and performing rainfall-runoff simulation to obtain runoff simulation data; performing evolution calculation on the runoff simulation data using a one-dimensional / two-dimensional coupled hydrodynamic model to obtain flood inundation data; merging the flood inundation data with the corrected data set to obtain hydrodynamic characteristic data;

[0049] Step S15, perform wavelet transform on the hydrodynamic characteristic data to obtain a wavelet coefficient set; perform threshold decomposition on the wavelet coefficient set according to energy distribution characteristics to obtain characteristic component data of different scales; reorganize the characteristic component data according to the time dimension, space dimension and intensity dimension to obtain multi-dimensional characteristic data; standardize the multi-dimensional characteristic data to obtain standardized characteristic data; convert the standardized characteristic data into a vector form to obtain a pressure characteristic vector set.

[0050] Through the systematic method of unified spatiotemporal preprocessing of multi-source data, outlier detection and correction, and pressure feature decomposition, high-quality integration of multi-dimensional pressure data of urban flood control system is achieved. Specifically, the Kriging interpolation method is used to spatially interpolate meteorological, hydrological, engineering and socio-economic data, and the time series interpolation is combined with the time weight function to ensure the spatial consistency and temporal continuity of data from different sources and scales. The outliers are initially identified by the box plot method, and the outliers are confirmed and corrected in combination with physical constraints, which effectively avoids the impact of data quality problems on subsequent analysis. Finally, the wavelet transform is used to decompose the pressure characteristics of the data, extract the characteristics of the time dimension, space dimension and intensity dimension, and form a standardized pressure feature vector set. Through the systematic data preprocessing and feature extraction methods, not only the data quality and reliability are improved, but also a high-quality data foundation is provided for the subsequent coupling relationship analysis, especially when dealing with multi-source heterogeneous data in urban flood control system, which can effectively capture the interaction relationship between different pressure factors.

[0051] like Figure 3 As shown, according to one aspect of the present application, step S2 is specifically:

[0052] Step S21, obtaining and calculating the mutual information entropy for each pair of eigenvectors in the pressure eigenvector set to obtain a mutual information entropy matrix; calculating the coupling strength value according to the mutual information entropy matrix to obtain a coupling strength matrix; calculating the Granger causality test statistic for each pair of eigenvectors in the pressure eigenvector set to obtain causal test data; determining the coupling direction according to the causal test data to obtain a coupling direction matrix;

[0053] Step S22: constructing network edge weights based on the coupling strength matrix to obtain a weighted edge set; determining the direction of the network edge based on the coupling direction matrix to obtain a directed edge set; combining the weighted edge set and the directed edge set, and adding a time tag to obtain a pressure-coupled dynamic network;

[0054] Through the construction method of directed weighted network, the dynamic network representation of pressure coupling relationship is realized. This step constructs the network edge weights based on the coupling strength matrix to ensure that the weights of the network edges can accurately reflect the intensity of the interaction between pressure elements. The direction of the network edge is determined according to the coupling direction matrix, and a directed edge set is constructed so that the network structure can reflect the path and direction of pressure transmission. Finally, by adding time tags, the static network is expanded to a dynamic network, and the time evolution representation of the pressure coupling relationship is realized. The pressure coupling representation method based on complex network theory can not only intuitively display the pressure transmission path in the system, but also track the dynamic changes of the coupling relationship. Especially when analyzing the multiple pressure action mechanisms of the urban flood control system, it can effectively identify the key pressure paths and evolution characteristics, providing a scientific basis for system vulnerability analysis.

[0055] Step S23, calculating the node degree distribution of the pressure-coupled dynamic network to obtain node degree characteristic data; calculating the clustering coefficient of the pressure-coupled dynamic network to obtain clustering characteristic data; calculating the centrality index of the pressure-coupled dynamic network to obtain centrality characteristic data; calculating the changes in the community structure of the pressure-coupled dynamic network at different time points to obtain community evolution data; combining the node degree characteristic data, clustering characteristic data, centrality characteristic data and community evolution data to obtain a network evolution characteristic set.

[0056] Through coupling relationship analysis and dynamic network construction methods, the complex interactions between pressure elements of the urban flood control system are accurately quantified. This step calculates the coupling strength between pressure feature vectors based on mutual information entropy, determines the coupling direction through Granger causality test, and constructs a directed weighted network reflecting the interaction between system pressure elements. The network construction method based on information theory and causal inference can accurately capture the nonlinear interaction relationship between different pressure elements. By analyzing the topological structure of the network, including the calculation of node degree distribution, clustering coefficient and centrality index, and extracting the evolution characteristics of community structure over time, the dynamic characteristics of the pressure coupling network of the flood control system are fully characterized. The dynamic network analysis method can not only identify key pressure elements and their impact paths, but also track the time evolution characteristics of pressure coupling relationships, providing an important theoretical basis for understanding the vulnerability and resilience of urban flood control systems.

[0057] like Figure 4 As shown, according to one aspect of the present application, step S3 is specifically:

[0058] Step S31, perform principal component analysis on the network evolution feature set to obtain principal component feature data; perform standardization processing on the pre-stored historical resilience assessment data to obtain standardized resilience data; perform correlation analysis on the principal component feature data and the standardized resilience data to obtain a feature correlation matrix; select key feature combinations according to the feature correlation matrix to obtain a resilience feature candidate set; perform weighted combination on the resilience feature candidate set to obtain a resilience state indicator set;

[0059] Step S32, performing time series decomposition on the toughness state indicator set to obtain trend component data and fluctuation component data; setting different boundary conditions according to the trend component data and the fluctuation component data to obtain scenario boundary data; using a hydrodynamic model to simulate and calculate the scenario boundary data to obtain scenario simulation data;

[0060] Step S33: construct an autoregressive model for the scenario simulation data and the resilience state indicator set to obtain trend prediction data; calculate the phase space reconstruction parameters based on the scenario simulation data to obtain reconstruction parameter data; construct the phase space according to the reconstruction parameter data to obtain state space data; combine the trend prediction data and the state space data to construct a hybrid prediction model to obtain a resilience state evolution model.

[0061] Through the comprehensive analysis of network evolution characteristics and historical resilience assessment data, a dynamic prediction model for the resilience state of the urban flood control system was established. This step performs principal component analysis on the network evolution feature set, extracts key feature combinations, and performs correlation analysis with historical resilience assessment data to construct a resilience state index system. Based on the data-driven feature selection method, the feature dimension is effectively reduced and the generalization ability of the model is improved. The resilience state index is separated into trend component and fluctuation component through time series decomposition, and scenario simulation is performed based on different boundary conditions to obtain the response characteristics of the system under different pressure scenarios. By combining the autoregressive model and the phase space reconstruction method, a hybrid prediction model is established, which can capture the long-term evolution trend of the system and characterize the short-term fluctuation characteristics, significantly improving the prediction accuracy. The hybrid modeling strategy that integrates multiple prediction methods not only improves the prediction ability of the model, but also enhances the interpretability of the prediction results, providing a reliable decision support tool for urban flood control resilience assessment.

[0062] like Figure 5 As shown, according to one aspect of the present application, step S4 is specifically:

[0063] Step S41, calculate the system state change rate for the toughness state evolution model to obtain state change rate data; normalize the pre-stored real-time monitoring data to obtain normalized monitoring data; use a simplified hydrodynamic model to quickly simulate the normalized monitoring data to obtain fast simulation data; perform fluctuation analysis on the state change rate data and the fast simulation data to obtain dynamic fluctuation characteristic data; calculate the time correlation of the normalized monitoring data to obtain time correlation data; perform feature fusion on the dynamic fluctuation characteristic data and the time correlation data to obtain a critical characteristic indicator set;

[0064] Step S42, perform statistical distribution analysis on the critical characteristic indicator set to obtain distribution characteristic data; construct a probability density function based on the distribution characteristic data to obtain density function data; perform quantile analysis on the density function data to obtain quantile characteristic data; calculate the optimal split point based on the quantile characteristic data to obtain split point data; convert the split point data into warning thresholds to obtain a warning threshold set.

[0065] Through the critical feature analysis of the resilience state evolution model and real-time monitoring data, the early warning threshold of the urban flood control system is accurately identified. This step calculates the rate of change of the system state, and combines the real-time monitoring data for rapid simulation, extracts dynamic fluctuation characteristics and time correlation characteristics, and constructs a critical feature indicator set. The feature extraction method based on multi-source data fusion can capture abnormal changes in the system state in a timely manner. Through statistical distribution analysis and probability density function construction, quantile analysis of critical features is performed to determine the optimal segmentation point, and finally the early warning threshold set is obtained. The threshold determination strategy that combines statistical theory and optimization methods not only considers the probability distribution characteristics of the system state, but also takes into account the accuracy and timeliness of the early warning, significantly improving the reliability and practicality of the early warning system.

[0066] According to one aspect of the present application, it also includes:

[0067] Step S5, performing parameter sensitivity analysis on the intermediate calculation results obtained from step S1 to step S4 to obtain a sensitivity evaluation report; performing a comprehensive reliability evaluation based on the sensitivity evaluation report and all data processing results to obtain a final reliability evaluation report.

[0068] Step S51, extract the pressure feature vector set, network evolution feature set, resilience state evolution model and warning threshold set to obtain the key result data set; perform perturbation analysis on each calculation parameter in the key result data set to obtain parameter perturbation data; calculate the influence of the parameter perturbation data on the final result to obtain influence degree data; classify the influence degree data to obtain sensitivity level data; organize the sensitivity level data into a report form to obtain a sensitivity assessment report. It can not only accurately identify key influencing parameters, but also reveal the interaction relationship between parameters, especially when evaluating complex models of urban flood control systems, it can provide a scientific basis for parameter optimization and model simplification.

[0069] Step S52, extract key indicators from the sensitivity assessment report to obtain key sensitivity indicators; perform uncertainty analysis on all data processing results from step S1 to step S4 to obtain uncertainty data; perform comprehensive scoring on key sensitivity indicators and uncertainty data to obtain comprehensive scoring data; establish reliability assessment standards based on the comprehensive scoring data to obtain assessment standard data; perform reliability assessment on the entire data processing flow based on the assessment standard data to obtain a final reliability assessment report.

[0070] Through systematic sensitivity analysis and reliability assessment methods, the quality control and reliability assurance of the entire technical solution are achieved. This step extracts key result data sets from the calculation results of S1 to S4, including pressure feature vector sets, network evolution feature sets, resilience state evolution models and warning threshold sets, and constructs a complete set of evaluation objects. Through parameter perturbation analysis, a combination of local sensitivity analysis and global sensitivity analysis is used to quantitatively evaluate the influence of each calculation parameter on the final result. In terms of sensitivity level classification, a multi-level classification method based on fuzzy comprehensive evaluation is used to make the sensitivity assessment results more practical. For reliability assessment, key sensitivity indicators are extracted, uncertainty analysis is performed in combination with Monte Carlo simulation methods, and the weights of each indicator are determined by entropy weight method, and a scientific comprehensive scoring system is established. Through multi-level quality control methods, not only can the key influencing factors in the calculation process be identified, but also the reliability level of the evaluation results can be quantified. Especially when dealing with complex systems such as urban flood control, the credibility of the warning results can be effectively improved, providing reliable technical support for the formulation of flood control decisions. Specifically, this step identified the key parameters that affect system performance through parameter sensitivity analysis, evaluated the confidence interval of the model prediction results through uncertainty analysis, and ensured the stable operation of the early warning system through reliability assessment. Ultimately, a complete quality assurance system was formed, which significantly improved the practical value and promotion potential of the entire technical solution.

[0071] According to one aspect of the present application, step S12 is specifically:

[0072] Step S121, perform spatial distribution characteristic analysis on rainfall intensity and duration data in the original meteorological data to obtain rainfall spatial characteristic data; perform spatial distribution characteristic analysis on water level and flow data in the original hydrological data to obtain hydrological spatial characteristic data; perform spatial distribution characteristic analysis on drainage system capacity and pipe network status data in the original engineering data to obtain engineering spatial characteristic data; perform spatial distribution characteristic analysis on population density and asset distribution data in the original socio-economic data to obtain social spatial characteristic data; perform variational interpolation calculation on rainfall spatial characteristic data, hydrological spatial characteristic data, engineering spatial characteristic data and social spatial characteristic data to obtain preliminary spatial interpolation data.

[0073] Step S122, performing local polynomial fitting on the preliminary spatial interpolation data to obtain local fitting data; using adaptive anisotropic kriging to optimize interpolation on the local fitting data to obtain optimized interpolation data; performing geographically weighted regression analysis on the optimized interpolation data to obtain temporary spatial interpolation data.

[0074] Kriging interpolation model Z*(x) = Σ(λ i ·Z(x i )) + μ(x)·[1 - Σλ i ]; where: variogram γ(h,θ) = C0 + C1 · [1 - exp(-h² / a(θ)²)]; anisotropy range function a(θ) = a0 · [1 + β · cos²(θ - φ)]; adaptive weight λ i = w i (x)·ρ i / Σ(w i (x)·ρ i ); local anisotropy parameter β(x) = [γmax(x) - γmin(x)] / [γmax(x) + γmin(x)]; where: Z*(x) is the predicted value at the point to be estimated x; Z(x i ) is a known sampling point x i The observed value at i is the kriging weight; μ(x) is the local mean; h is the spatial distance; θ is the direction angle; C0 is the nugget effect; C1 is the sill value; a0 is the maximum range; β is the anisotropy coefficient; φ is the main direction angle; w i (x) is the local window weight; ρ i is the data reliability weight; γmax(x) and γmin(x) are the local maximum and minimum variations respectively; this method improves the accuracy of spatial interpolation by introducing adaptive anisotropy parameters and local weight coefficients.

[0075] Step S123, perform time series decomposition on the temporary spatial interpolation data to obtain trend series data and period series data; process the trend series data using the cubic spline interpolation method to obtain trend interpolation data; process the period series data using the Fourier interpolation method to obtain period interpolation data; combine the trend interpolation data and the period interpolation data to obtain temporary time interpolation data.

[0076] Step S124, calculate the time weight function according to the sampling interval of the temporary time interpolation data to obtain the time weight data; standardize the pre-stored spatial correlation data to obtain the spatial weight data; use the bilateral filtering algorithm to perform multi-source fusion of the temporary time interpolation data, the time weight data and the spatial weight data to obtain a unified spatiotemporal scale data set.

[0077] Bilateral filtering algorithm: weighted fusion function F(x) = k(x)·Σ[Gs(||p - x||)·Gr(|Ip - Ix|)·Gt(|tp - tx|)·Ip] / Σ[Gs(||p - x||)·Gr(|Ip - Ix|)·Gt(|tp - tx|)]; where: spatial weight function Gs(||p - x||) = exp(-||p - x||² / 2σs²); numerical weight function Gr(|Ip - Ix|) =exp(-|Ip - Ix|² / 2σr²); temporal weight function Gt(|tp - tx|) = exp(-|tp - tx|² / 2σt²); adaptive kernel parameter k(x) = (1 + λ·v(x)) / (1 + λ); local variation coefficient v(x) = std(Wx) / mean(Wx); where: F(x) is the fused data value; p is the sampling point in the neighborhood; x is the current processing point; Ip is the data value of the sampling point; Ix is the data value of the current point; tp is the timestamp of the sampling point; tx is the timestamp of the current point; σs is the spatial smoothing parameter; σr is the numerical smoothing parameter; σt is the temporal smoothing parameter; λ is the adaptive adjustment coefficient; Wx is the data set in the local window; std is the standard deviation operator; mean is the mean operator; this method achieves the smooth fusion of spatiotemporal data by introducing time weight and adaptive kernel parameters.

[0078] Through the spatial feature analysis and spatiotemporal interpolation calculation of multi-source data, the unified spatiotemporal scale conversion of heterogeneous data is realized. This step analyzes the spatial distribution characteristics of different types of data (meteorology, hydrology, engineering, and social economy), and uses the variational interpolation method for preliminary spatial interpolation. The interpolation is optimized by local polynomial fitting and adaptive anisotropic kriging, which improves the accuracy of spatial interpolation. In the time dimension, the trend and periodic components are extracted by the time series decomposition method, and the cubic spline interpolation and Fourier interpolation are used for processing, respectively, to ensure the continuity of the time series and the maintenance of periodic characteristics. Finally, the time weight and space weight are multi-source fused by the bilateral filtering algorithm to obtain a data set with a unified spatiotemporal scale. The data unification method based on multiple interpolation and fusion not only ensures the spatiotemporal consistency of the data, but also effectively reduces the interpolation error. Especially when processing multi-source heterogeneous data in urban flood control systems, it can accurately characterize the spatiotemporal correlation characteristics between different data sources, providing a high-quality data foundation for subsequent analysis.

[0079] According to one aspect of the present application, step S13 is specifically:

[0080] Step S131, calculate the mean and standard deviation of each variable for the unified spatiotemporal scale data set to obtain basic statistical feature data; use the kernel density estimation method to calculate the probability distribution characteristics of each variable to obtain distribution feature data; perform sliding window analysis on the unified spatiotemporal scale data set, calculate the time series characteristics, and obtain time series feature data; perform feature fusion on the basic statistical feature data, distribution feature data, and time series feature data to obtain statistical feature data.

[0081] Step S132: use the isolation forest algorithm to perform preliminary screening of abnormal points on the statistical feature data to obtain preliminary screening abnormal data; use the local abnormal factor method to perform spatial anomaly detection on the unified spatiotemporal scale data set to obtain spatial anomaly data; use the dynamic time warping algorithm to perform time series anomaly detection on the unified spatiotemporal scale data set to obtain time series anomaly data; integrate the preliminary screening abnormal data, spatial anomaly data and time series anomaly data to obtain preliminary abnormal value data.

[0082] Isolation Forest Algorithm: Anomaly scoring function s(x) = 2^(-E[h(x)] / E[h(T)])·[1 + α·d(x)]; where: Path length expectation E[h(x)] = Σ(c i ·h i (x)) / n; tree height expectation E[h(T)] = 2·(ln(ψ - 1) +0.5772156649) - 2·(ψ - 1) / ψ; distance weight coefficient d(x) = Σ[w(x i )·d i st(x, x i)] / Σw(x i ); adaptive weight w(x i ) = exp(-s(x i )² / 2σ²); Split selection probability P(j) = Iθ(j) / ΣIθ(j); Information gain Iθ(j) = H(D) - Σ(|Dv| / |D|)·H(Dv); Where: s(x) is the anomaly score; h(x) is the path length of sample x; h i (x) is the path length of sample x in the i-th tree; c i is the tree weight; n is the number of trees; ψ is the number of samples; d(x) is the distance weight term; α is the weight adjustment parameter; dist(x, x i ) is the distance between samples; σ is the kernel width parameter; P( j ) is the selection probability of feature j; Iθ( j ) is the information gain of feature j; H(D) is the entropy of data set D; Dv is the sub-dataset; this method improves the accuracy of anomaly detection by introducing distance weights and adaptive feature selection.

[0083] The improvement of the local anomaly factor method is as follows: local anomaly factor calculation LOF(x) = [Σ(lrd(p) / lrd(x)) / k]·[1 + β·entropy(x)]; where: local reachability density lrd(x) = 1 / [Σ(reach-distk(x,p)) / k]; reachable distance reach- distk (x,p) = max{k-dist(p), d(x,p)}·w(x,p); neighborhood entropy entropy(x)= -Σ[p i ·log(p i )]; adaptive weight w(x,p) = exp(-||xp||² / [2·σ(x)²]); local scale parameter σ(x) = [Σ(k-dist(x,p)²) / k]^(1 / 2); density probability p i = density(x, i ) / Σdensity(x, j ), where: LOF(x) is the local anomaly factor of sample x; lrd(x) is the local reachability density of point x; k is the number of neighbors; β is the entropy weight coefficient; reach-distk(x,p) is the reachability distance; d(x,p) is the Euclidean distance; w(x,p) is the distance weight; k-dist(p) is the kth nearest neighbor distance; entropy(x) is the neighborhood entropy; σ(x) is the local scale parameter; density(x, i) is the density value of point x in the i-th density interval; this method enhances the accuracy of local density estimation by introducing neighborhood entropy and adaptive weight.

[0084] The dynamic time warping algorithm is as follows: the cumulative distance function DTW ( i , j ) = d(x i ,y j ) + min{γ·DTW( i-1 , j-1 ), ω·DTW( i-1 , j ), ω·DTW( i , j-1 )}·exp(-λ·|v i -v j |); where: local distance calculation d(x i ,y j ) = ||x i -y j ||·[1 + α·cos(θ ij )]; velocity vector v i = (x i -x i-1 ) / Δt; direction angle θ ij =arccos[(x i -x i-1 )·(y j -y j-1 ) / (||x i -x i-1 ||·||y j -y j-1 ||)]; step weight ω = 1 + β·|v i | / max(|v|); path penalty γ = 1 - β·|v i -v j | / max(|v|); where: DTW( i , j ) is the sequence x and y at position ( i , j ) at the cumulative distance; d(x i ,y j ) is the local distance; x i ,y j are the values ​​of the corresponding positions of the two sequences; v i ,v j is the corresponding velocity vector; θ ijis the direction angle; α is the direction weight coefficient; β is the speed weight coefficient; λ is the time attenuation coefficient; ω is the step weight; γ is the path penalty factor; this method improves the accuracy of timing matching by introducing speed and direction information.

[0085] The specific ensemble learning algorithm is: ensemble prediction function E(x) = Σ[w i ·f i (x)]·[1 + α·D(x)]·[1+ β·T(t)]; where: model weight w i = exp(-E i / θ)·[1 + λ·V i (x)] / Σexp(-E j / θ); Diversity measure D(x) = Σ[I(f i (x)≠f j (x))·S ij ] / [M(M-1)]; time modulation T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); model variance V i (x) = E[(f i (x)-f*(x))²]·[1 + μ·ρ i (x)]; similarity matrix S ij = exp(-||f i -f j ||² / 2σ²)·[1 + γ·cos(θ ij )]; local density ρ i (x) = Σexp(-||x-xk||² / 2η²)·I(f i (xk)=y i ); where: E(x) is the integrated prediction result; f i (x) is the base learner; α is the diversity weight; β is the time series weight; λ is the variance weight; E i is the base learner error; θ is the temperature parameter; M is the number of models; τ is the time scale; ω is the period parameter; μ is the density weight; σ is the similarity scale; γ is the direction weight; η is the density scale; this method improves the stability of integrated prediction by introducing diversity measurement and timing modulation.

[0086] Step S133, perform constraint verification on the preliminary outlier data according to the hydrological physical constraint conditions to obtain physical constraint verification data; use the water balance equation to perform balance verification on the preliminary outlier data to obtain balance verification data; use the hydrodynamic model to perform dynamic rationality verification on the preliminary outlier data to obtain dynamic verification data; comprehensively evaluate the physical constraint verification data, balance verification data and dynamic verification data through a multi-criteria decision-making method to obtain confirmed outlier data.

[0087] Step S134, reconstruct missing values ​​of confirmed outlier data using a tensor decomposition method to obtain reconstructed data; smooth the reconstructed data using a local weighted scatter point smoothing method to obtain smoothed data; suppress noise on the smoothed data using a wavelet threshold denoising method to obtain corrected data; fuse the corrected data with the normal value data in a unified spatiotemporal scale data set to obtain a corrected data set.

[0088] Improved tensor decomposition method: tensor reconstruction model T ≈ G ×1 U⁽ 1 ⁾ ×2 U⁽ 2 ⁾ ×3 U⁽ 3 ⁾ + λ·S; where: the core tensor update G = T ×1 (U⁽ 1 ⁾) T ×2 (U⁽ 2 ⁾) T ×3 (U⁽ 3 ⁾) T ; Factor matrix update U⁽ n ⁾ = T⁽ n ⁾·G⁽ n ⁾·[(G⁽ n ⁾)T·G⁽ n ⁾ + αI] -1 ;Sparse term update S = Sτ(T - G ×1 U⁽ 1 ⁾ ×2 U⁽ 2 ⁾ ×3U⁽ 3 ⁾); soft threshold operator Sτ(x) = sign(x)·max(|x| - τ,0); adaptive regularization parameter α = η·||T –T*||F / ||T||F; where: T is the original tensor; G is the core tensor; U⁽ n ⁾ is the factor matrix of the nth dimension; λ is the sparse term weight; S is the sparse tensor; T⁽ n ⁾ is the expansion matrix along the nth dimension; G⁽ n⁾ is the mode expansion of the core tensor; τ is the threshold parameter; α is the regularization parameter; η is the scaling factor; ||·||F is the Frobenius norm; This method improves the robustness of tensor decomposition by introducing adaptive regularization and sparse constraints.

[0089] Through multi-level outlier detection and correction methods, the data quality has been comprehensively improved. This step uses the kernel density estimation method to calculate the probability distribution characteristics, combines the sliding window analysis to extract the time series characteristics, and constructs a complete statistical feature system. The isolation forest algorithm is used to screen outliers, and the local anomaly factor method and dynamic time warping algorithm are used to detect spatial and temporal anomalies, realizing multi-dimensional anomaly identification. In the outlier confirmation stage, multiple verifications are carried out through hydrological physical constraints, water balance equations, and hydrodynamic rationality verification to ensure the accuracy of outlier determination. Finally, the tensor decomposition method is used to reconstruct missing values, and data correction is performed through local weighted scatter point smoothing and wavelet threshold denoising. Not only does it improve the reliability of the data, but it also maintains the physical rationality of the data. Especially when processing the monitoring data of complex urban flood control systems, it can effectively identify and correct various types of outliers, providing high-quality data support for subsequent analysis.

[0090] According to one aspect of the present application, step S14 is specifically:

[0091] Step S141, extracting rainfall data from the corrected data set and performing spatiotemporal distribution analysis to obtain rainfall distribution characteristic data; using the Green-Ampt model to calculate infiltration loss to obtain infiltration loss data; using surface roughness data to calculate surface interception loss to obtain interception loss data; performing water balance calculation on rainfall distribution characteristic data, infiltration loss data and interception loss data to obtain effective rainfall data; using the nonlinear unit line method to perform confluence calculation on the effective rainfall data to obtain runoff simulation data;

[0092] Green-Ampt model: Infiltration flux equation f(t) = Ks·(1 + [ψf·Δθ] / F)·[1 + β·exp(-αt)]; where: Cumulative infiltration update F(t+Δt) = F(t) + f(t)·Δt + γ·[θs - θ i]·[1 -exp(-λ·I(t))]; effective suction head ψf = ψb·(Se)^(-1 / m); saturation Se = (θ - θr) / (θs - θr); soil hydraulic conductivity Ks = Ks0·[1 + ω·cos(2πt / T)]; where: f(t) is the infiltration flux at time t; F(t) is the cumulative infiltration; Ks is the saturated hydraulic conductivity; ψf is the wetting front suction head; Δθ is the soil water deficit; β and α are time-varying adjustment parameters; γ is the cumulative correction coefficient; θs is the saturated water content; θ i is the initial water content; θr is the residual water content; ψb is the bubble pressure; m is the pore distribution parameter; λ is the rainfall intensity influence coefficient; I(t) is the accumulated rainfall; Ks0 is the benchmark hydraulic conductivity; ω is the seasonal variation amplitude; T is the period; By introducing time-varying parameters and seasonal changes, the accuracy of infiltration calculation is improved.

[0093] Step S142: performing one-dimensional river hydrodynamic calculation based on the runoff simulation data to obtain river hydrodynamic data; performing urban terrain evolution calculation on the runoff simulation data using a two-dimensional overland flow model to obtain overland flow data; performing coupling calculation on the river hydrodynamic data and overland flow data using an interactive iterative algorithm to obtain one- and two-dimensional coupled data; performing inundation range calculation on the one- and two-dimensional coupled data according to pre-stored terrain elevation data to obtain flood inundation data;

[0094] Step S143, extracting spatiotemporal features from the corrected data set to obtain basic feature data; calculating hydrodynamic indicators from the flood and waterlogging inundation data to obtain inundation feature data; combining the basic feature data and the inundation feature data using a multi-source data fusion algorithm to obtain combined feature data; optimizing the combined feature data using an adaptive weight method to obtain hydrodynamic feature data;

[0095] Step S144, perform quality verification on the hydrodynamic characteristic data to obtain characteristic verification data; use physical constraints to verify the validity of the characteristic verification data to obtain characteristic verification data; use a multi-criteria evaluation method to perform reliability evaluation on the characteristic verification data to obtain characteristic evaluation data; compare and correct the characteristic evaluation data with the original hydrodynamic characteristic data to obtain final hydrodynamic characteristic data.

[0096] According to one aspect of the present application, step S21 is specifically:

[0097] Step S211, calculating the mutual information entropy for each pair of eigenvectors in the pressure eigenvector set to obtain preliminary mutual information data; correcting the preliminary mutual information data using a kernel density estimation method to obtain corrected mutual information data;

[0098] Reconstruct the matrix of the corrected mutual information data to obtain the mutual information entropy matrix;

[0099] Density estimation function f(x) = [1 / (nh)] · Σ{K[(xx i ) / h]·[1 + α·L(x,x i )]}·[1 +β·S(x)]; where: local bandwidth h(x) = h o ·[f o (x) / g]^(-γ); similarity measure L(x,x i ) = exp(-||xx i ||² / 2σ²)·cos(θx i ); spatial correlation S(x) = Σ[w i exp(-d i ² / 2τ²)]; kernel function K(u) = (1-u²)·I(|u|≤1)·[1 + λ·|u|]; adaptive weight w i = exp[-μ·(f o (x i ) – f* o )²]; where: f(x) is the estimated density; n is the number of samples; h is the bandwidth parameter; α is the similarity weight; β is the spatial weight; h o is the reference bandwidth; f o (x) is the initial density estimate; g is the geometric mean; γ is the adaptive coefficient; σ is the kernel width; θx i is the sample angle; d i is the spatial distance; τ is the spatial scale; λ is the kernel function adjustment parameter; μ is the weight adjustment coefficient; this method improves the accuracy of density estimation by introducing local adaptive bandwidth and spatial correlation.

[0100] Step S212: Obtain the mutual information entropy matrix and perform normalization processing to obtain normalized mutual information data; perform intensity conversion on the normalized mutual information data using a nonlinear mapping method to obtain intensity mapping data; perform matrix reconstruction on the intensity mapping data to obtain a coupling intensity matrix C ij =exp(-λI ij ),1≤ i , j ≤n; where C ij is the coupling strength matrix.

[0101] where: mapping function M(x) = σ[W·φ(x) + b]·[1 + α·R(x)]·[1 + β·T(x)]; where: nonlinear transformation φ(x) = tanh(ωx)·[1 + λ·||grad x||]; time series regularization T(x) = exp(-|t- t o |² / 2σt²)·cos(θ·|t - t o |); spatial regularization R(x) = Σ[w i ·exp(-||x - x i ||² / 2σs²)]; adaptive weight w i = [1 + γ·cos(θ i )] / [1 + ||x - x i ||]; activation function σ(z) = max(0,z) +μ min(0,z); gradient term grad x = (x – x*) / std(x); where: M(x) is the mapping result; W is the weight matrix; b is the bias term; α is the spatial weight coefficient; β is the temporal weight coefficient; ω is the nonlinear degree parameter; λ is the gradient weight; t is the current time; t0 is the reference time; σt is the time scale parameter; θ is the period parameter; σs is the spatial scale parameter; γ is the direction weight; θ i is the spatial direction angle; μ is the negative slope; the stability of the nonlinear mapping is improved by introducing spatiotemporal regularization and adaptive weights.

[0102] Step S213, performing time lag analysis on each pair of feature vectors in the pressure feature vector set to obtain time lag feature data; τ ij =argmax τ corr(x i (t), x j (t+τ)); where the time lag τ ij It can be calculated by maximizing the cross-correlation function.

[0103] Granger causality test is performed on the pressure characteristic vector set and the time-lag characteristic data to obtain preliminary causal data; X j (t) = α + ∑ p k=1 βx j (tk)+∑ p k=1 γ k x i (tk)+o* t ; where α is a constant term, β k and γ k is the coefficient to be estimated, ϵ t is the error term, and p is the lag period. If the coefficient γk If it is significantly different from zero, then the null hypothesis is rejected.

[0104] Use confidence test method to conduct significance analysis on preliminary causal data to obtain causal test data;

[0105] Test statistic Z(x) = [μ1(x) – μ2(x)] / [s(x)·√(1 / n1+ 1 / n2)]·[1 + α·V(x)]·[1 + β·C(x)]; where: sample variance s²(x) = [(n1-1)s1² + (n2-1)s2²] / (n1+n2-2)·[1+ λ·H(x)]; variance heterogeneity correction V(x) = max(s1² / s2², s2² / s1²)·exp(-γ·|r 12 |); autocorrelation correction C(x) = [1 - ρ(x)]·exp(-ω·|Δt|); heterogeneity measure H(x) = Σ|x i - x*| / [n·std(x)]; autocorrelation coefficient ρ(x) = Σ[(x i -x*)(x i+1 -x*)] / Σ(x i -x*)²; where: Z(x) is the test statistic; μ1, μ2 are sample means; s(x) is the pooled standard deviation; n1, n2 are sample sizes; α is the variance weight; β is the autocorrelation weight; λ is the heterogeneity weight; γ is the correlation weight; ω is the time weight; r 12 is the sample correlation coefficient; Δt is the time interval; the reliability of the test is improved by introducing variance heterogeneity and autocorrelation correction.

[0106] Step S214, perform threshold segmentation on the causal test data to obtain causal determination data; perform directionality analysis on the causal determination data to obtain directional feature data; perform matrix reconstruction on the directional feature data to obtain a coupling direction matrix.

[0107] Through the multi-dimensional coupling relationship quantification method, the accurate characterization of the interaction between pressure elements is achieved. This step uses the kernel density estimation method to correct the mutual information entropy, which improves the accuracy of information quantification. The mutual information is converted into coupling intensity through the nonlinear mapping method, and a coupling intensity matrix reflecting the intensity of the interaction between the elements is constructed. In terms of coupling direction determination, time lag analysis is performed to determine the optimal time delay, and causal relationship determination is performed based on the Granger causality test and confidence test methods, and finally a coupling direction matrix is ​​constructed. Combining the coupling relationship of information theory, nonlinear mapping and causal inference can not only accurately quantify the interaction intensity between pressure elements, but also identify the directionality of the action. Especially when dealing with the complex relationship between multiple pressures in urban flood control systems, it can effectively capture the nonlinear and time-varying coupling characteristics, providing a reliable data basis for building a pressure coupling network.

[0108] According to one aspect of the present application, step S23 is specifically:

[0109] Step S231, calculate the in-degree and out-degree of each node in the pressure-coupled dynamic network to obtain basic metric data; use the local connection density algorithm to calculate the local connection characteristics of the pressure-coupled dynamic network to obtain connection density data; perform weighted combination of the basic metric data and the connection density data to obtain node degree feature data.

[0110] Connection density function D(x) = [Σ(K(x,x i )·w(x i )) / V(x)]·[1 + α·L(x)]·[1 + β·T(x)]; where: kernel function K(x,x i ) = exp(-||xx i ||² / 2h²)·[1 + λ·cos(θx i )]; adaptive volume V(x) = πr²(x)·[1 + γ·std(Nx)]; local scale r(x) = r0·[f(x) / g]^(-ω); topological feature L(x) = Σ[δ ij exp(-d ij / σ)] / k(k-1); time-varying feature T(x) = exp(-|t-t0|² / 2τ²)·cos(μ·|t-t0|); weight function w(x i ) = [1 + η·ρ(x i )] / [1 + ||xx i ||]; where: D(x) is the local connection density; K(x,x i ) is the kernel function; h is the bandwidth parameter; V(x) is the adaptive volume; α is the topological weight coefficient; β is the time-varying weight coefficient; λ is the direction weight; θxi is the spatial angle; γ is the variation weight; r(x) is the local radius; r0 is the reference radius; f(x) is the initial density estimate; g is the geometric mean; ω is the adaptive index; δ ij is the connection indicator; d ij is the path distance; σ is the scale parameter; k is the number of neighbors; τ is the time scale; μ is the period parameter; η is the density weight; ρ(x i ) is the point density; this method improves the accuracy of connection density estimation by introducing adaptive volume and topological features.

[0111] Step S232, extracting triangle structure features from the pressure-coupled dynamic network to obtain triangle feature data; performing cluster analysis on the pressure-coupled dynamic network using a local clustering coefficient algorithm to obtain cluster analysis data; and performing feature fusion on the triangle feature data and the cluster analysis data to obtain cluster feature data.

[0112] Local clustering coefficient algorithm: Clustering coefficient C( i ) = [2·Σ(w ij ·w jk ·w ki )·(1 + α·θ ijk )]·[1 + β·T( i )] / [k i ·(k i-1 )]; where: edge weight w ij = exp(-||x i -x j ||² / 2σ²)·[1 + λ·cos(φ ij )]; time-varying characteristics T( i ) = exp(-|t i -t0|² / 2τ²)·cos(ω·|t i -t0|); angle characteristic θ ij k = exp[γ·cos(ψ ij k)]; local metric k i = Σ j [I(w ij > δ)·(1 + μ·ρ ij )]; density correlation ρ ij = min(ρ i ,ρ j ) / max(ρ i ,ρ j ); where: C( i ) is a node i The clustering coefficient w ij ,w jk ,wki is the edge weight; α is the angle weight coefficient; β is the time-varying weight coefficient; λ is the direction weight; φ ij is the spatial direction angle; τ is the time scale parameter; ω is the period parameter; γ is the angle adjustment coefficient; ψ ijk is the triangle angle; δ is the connection threshold; μ is the density weight; ρ i ,ρ j is the node density; this method improves the accuracy of clustering coefficient calculation by introducing angle features and time-varying features.

[0113] Step S233, calculating the eigenvector centrality of the pressure-coupled dynamic network to obtain eigenvector data; calculating the betweenness centrality of the pressure-coupled dynamic network to obtain betweenness characteristic data; calculating the importance distribution of the pressure-coupled dynamic network using the PageRank algorithm to obtain importance distribution data; comprehensively evaluating the eigenvector data, betweenness characteristic data and importance distribution data to obtain centrality characteristic data.

[0114] The PageRank algorithm is specifically: importance score PR ( i ) = (1-d)·[1 + α·S( i )] + d·Σ[PR( j )·w ji ·T( j , i )] / Σw ji ; Among them: edge weight calculation w ji = exp(-||x j -x i ||² / 2σ²)·[1 + β·cos(θ ji )]; Timing transfer function T( j , i ) = exp(-|t j -t i |² / 2τ²)·[1 + λ·v( j , i )]; Node strength S( i ) =(k i , i n·k i ,out)^(1 / 2) / max(k); speed correlation v( j , i ) = cos(φ j -φ i )·exp(-|v j -v i | / v0); local importance k i , i n = Σwji ·[1 + μ·ρ( i )]; local impact k i ,out = Σw ij ·[1 + μ·ρ( i )]; where: PR( i ) is a node i The importance score of is; d is the damping coefficient; α is the intensity weight; β is the direction weight; θ ji is the spatial direction angle; τ is the time scale parameter; λ is the velocity weight; φ j ,φ i is the flow angle; v j ,v i is the flow velocity; v0 is the reference flow velocity; μ is the density weight; ρ( i ) is the node density; this method improves the accuracy of importance evaluation by introducing time series transmission and flow field characteristics.

[0115] Step S234, extracting community structures at different time points of the pressure-coupled dynamic network to obtain time series community data; performing evolution analysis on the time series community data using a dynamic community detection algorithm to obtain evolution feature data; extracting stability and variability features from the evolution feature data to obtain community evolution data.

[0116] Dynamic community detection algorithm: community quality function Q(t) = Σ[w ij (t)·δ(c i (t),c j (t)) - P ij (t)]·[1 + α·M(t)]·[1 + β·E(t)]; where: time-varying weight w ij (t) = w 0ij ·exp(-|t-t0|² / 2τ²)·[1 + λ·R( i , j ,t)]; zero model P ij (t) = k i (t)·k j (t) / 2m(t)·[1 + γ·C( i , j , t )]; community migration M(t) = Σ|c i (t)-c i (t-1)| / N·exp(-ω·Δt); community entropy E(t) = -Σ[ns(t) / N·log(ns(t) / N)]; correlation feature R( i , j ,t) = cos(θ ij)·exp(-||v i -v j || / v0); Aggregate features C( i , j , t ) = |N i ∩N j | / |N i ∪N j |; where: Q(t) is the time-varying modularity; w ij (t) is the time-varying edge weight; c i (t) is the node i The community label at time t; α is the migration weight; β is the entropy weight; λ is the correlation weight; γ is the aggregation weight; τ is the time scale; ω is the time decay coefficient; ns(t) is the size of community s; N is the total number of nodes; θ ij v is the direction angle; i ,v j is the node speed; v0 is the reference speed; N i ,N j is the node neighborhood; this method improves the dynamic adaptability of community division by introducing time-varying features and migration features.

[0117] Step S235, perform time series sorting on the node degree feature data to obtain time series degree feature data; perform time series sorting on the cluster feature data to obtain time series cluster data; perform time series sorting on the centrality feature data to obtain time series centrality data; perform multi-dimensional integration on the time series degree feature data, time series cluster data, time series centrality data and community evolution data to obtain a network evolution feature set.

[0118] According to one aspect of the present application, step S32 is specifically:

[0119] Step S321, obtain the toughness state indicator set and perform empirical mode decomposition to obtain initial component data; use the change point detection algorithm to identify the mutation characteristics of the initial component data to obtain mutation characteristic data; reconstruct the components of the initial component data and the mutation characteristic data to obtain trend component data and fluctuation component data.

[0120] Step S322: perform trend extrapolation on the trend component data to obtain trend prediction data; perform fluctuation intensity analysis based on the fluctuation component data to obtain fluctuation intensity data; use a scenario generation algorithm to convert the trend prediction data and fluctuation intensity data into boundary conditions to obtain boundary solution data; perform feasibility verification on the boundary solution data to obtain scenario boundary data.

[0121] Step S323, construct a two-dimensional hydrodynamic model calculation grid for the scenario boundary data to obtain calculation grid data; use an adaptive time step algorithm to perform dynamic solution on the calculation grid data to obtain hydrodynamic calculation data; extract results from the hydrodynamic calculation data to obtain simulation results data; organize the simulation results data according to the scenario to obtain scenario simulation data.

[0122] Through the comprehensive method of time series decomposition and scenario simulation, multi-scenario prediction of resilience state is achieved. This step uses empirical mode decomposition and change point detection algorithm to decompose the resilience state index and accurately identify trend components and fluctuation components. Through trend extrapolation and fluctuation intensity analysis, combined with scenario generation algorithm, different boundary condition schemes are constructed. Finally, the adaptive time step algorithm is used to perform hydrodynamic simulation to obtain the response characteristics of the system under different scenarios. By combining the prediction method of time series analysis, scenario generation and hydrodynamic simulation, it can not only accurately characterize the long-term evolution trend of the system, but also simulate the system response under different pressure scenarios. Especially when evaluating the resilience of urban flood control systems, it can provide comprehensive scenario analysis results and provide a scientific basis for resilience improvement decisions.

[0123] According to one aspect of the present application, step S41 is specifically:

[0124] Step S411, numerically differentiate the toughness state evolution model to obtain initial change rate data; use a singular value decomposition algorithm to perform noise reduction processing on the initial change rate data to obtain noise-reduced change rate data; perform time scale analysis on the noise-reduced change rate data to obtain state change rate data;

[0125] Singular value decomposition algorithm: signal reconstruction function S(X) = U·[Σ + α·W(σ)]·Vᵀ·[1 + β·T(t)]; where: adaptive weight matrix W(σ) = diag[w(σ1),w(σ2),...,w(σ r )]; weight function w(σ i ) = exp(-|σ i -σ*|² / 2η²)·[1 + λ·h(σ i )]; timing modulation T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); entropy function h(σ i ) = -Σ[p i ·log(p i )]; probability distribution p i = σ i / Σσ j; Noise threshold η = σ1·√(2·log(n)) / n; where: S(X) is the reconstructed signal; U, V are the left and right singular vectors; Σ is the singular value matrix; α is the weight coefficient; β is the timing weight; λ is the entropy weight; τ is the time scale; ω is the period parameter; σ i is the singular value; n is the number of samples; this method improves the accuracy of signal reconstruction by introducing adaptive weights and timing modulation.

[0126] Step S412: identify abnormal values ​​of pre-stored real-time monitoring data to obtain cleaned monitoring data; normalize the cleaned monitoring data to obtain preliminary normalized data; and use the quantile mapping method to adjust the distribution of the preliminary normalized data to obtain normalized monitoring data;

[0127] Quantile mapping method: distribution transformation function Q(x) = F -1 γ [Fx(x)]·[1 + α·K(x)]·[1 + β·T(t)]; where: empirical distribution function Fx(x) = (1 / n)·Σ[I(x i ≤x)·w(x i )]; Kernel density correction K(x) = Σ[Kh(xx i )·exp(-|v i | / v0)]; timing modulation T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); adaptive weight w(x i ) = [1 + λ·ρ(x i )] / [1 + ||xx i ||]; kernel function Kh(u) = (1 / h)·K(u / h)·[1+ γ·|u / h|]; where: Q(x) is the mapping result; F -1 γ is the inverse function of the target distribution; α is the kernel density weight; β is the time series weight; λ is the density weight; τ is the time scale; ω is the period parameter; v i is the local change rate; v0 is the reference change rate; h is the bandwidth parameter; γ is the scale weight; this method improves the smoothness of the distribution mapping by introducing kernel density correction and time series modulation.

[0128] Step S413, constructing a simplified Saint-Venant equation group based on the normalized monitoring data to obtain simplified equation data; using a feature extraction network to quickly extract features from the normalized monitoring data to obtain feature extraction data; and quickly solving the simplified equation data and the feature extraction data to obtain fast simulation data;

[0129] The feature extraction network is specifically as follows: feature mapping function F(x) = σ[W·φ(x) + b]·[1 + α·A(x)]·[1 + β·R(x)]; where: nonlinear transformation φ(x) = tanh(ωx)·[1 + λ·||grad x||]; attention mechanism A(x) = softmax(Q·K^T / √d)·[1 + μ·cos(θx)]; residual connection R(x) = x + γ·g(x)·[1 + η·ρ(x)]; local density ρ(x) = Σexp(-||xx i ||² / 2σ²); gradient feature ||grad x|| =√(Σ(dx / dx i )²); where: F(x) is the extracted feature; σ is the activation function; W,b is the network parameter; α is the attention weight; β is the residual weight; λ is the gradient weight; μ is the direction weight; γ is the residual coefficient; η is the density weight; σ is the kernel width; By introducing the attention mechanism and residual connection, the efficiency of feature extraction is improved.

[0130] Step S414, performing multi-scale decomposition on the state change rate data and the fast simulation data to obtain decomposed fluctuation data; performing feature extraction on the decomposed fluctuation data using random matrix theory to obtain fluctuation characteristic data; and reconstructing the fluctuation characteristic data to obtain dynamic fluctuation characteristic data;

[0131] The specific random matrix theory is: feature extraction function E(X) = Σ[λ i ·v i ·v i T ·I(λ i > λc)]·[1 +α·H(λ)]·[1 + β·T(t)]; where: critical threshold λc = μ(1 + √(n / p))²·[1 + γ·σ(λ)]; entropy correction H(λ) = -Σ[p i ·log(p i )]·exp(-|λ i -λ*| / λ0); timing modulation T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); characteristic probability p i = λ i / Σλ j ;Local varianceσ(λ) = √[Σ(λ i -λ*)²·w(λ i )] / n; weight function w(λ i ) = [1 + η·ρ(λ i )] / [1 + |λ i-λ*|]; where: E(X) is the extracted feature matrix; λ i is the eigenvalue; v i is the feature vector; α is the entropy weight; β is the time series weight; γ is the variance weight; μ is the mean; λ0 is the reference eigenvalue; τ is the time scale; ω is the period parameter; η is the density weight; n, p are the matrix dimensions; By introducing entropy correction and time series modulation, the stability of feature extraction is improved.

[0132] Step S415, calculating the autocorrelation function of the normalized monitoring data to obtain autocorrelation feature data; calculating the cross-correlation function of the normalized monitoring data to obtain cross-correlation feature data; performing feature fusion on the autocorrelation feature data and the cross-correlation feature data to obtain time-related data;

[0133] Step S416, extracting stability indicators from dynamic fluctuation feature data to obtain stability indicator data; extracting correlation indicators from time-related data to obtain correlation indicator data; using a deep feature fusion network to fuse the stability indicator data and the correlation indicator data to obtain a critical feature indicator set.

[0134] The deep feature fusion network is specifically: feature fusion function F(X) = σ[W·(X + α·M(X)) + b]·[1+ β·A(X)]·[1 + λ·R(X)]; where: multi-scale feature M(X) = Σ[w i Conv(X,k i )]·[1 + γ·S(X)]; attention mechanism A(X) = softmax(Q·K^T / √d)·[1 + μ·cos(θx)]; residual term R(X) = G(X)- X + η·L(X); scale correlation S(X) = exp(-|s i -s j |² / 2σs²); local feature L(X) = Σ[φ(x i )·exp(-||xx i ||² / 2σ²)]; where: F(X) is the fusion feature; σ is the activation function; W,b is the network parameter; α is the multi-scale weight; β is the attention weight; λ is the residual weight; w i is the convolution weight; k i is the convolution kernel; γ is the scale weight; μ is the direction weight; η is the local weight; σs is the scale parameter; σ is the spatial parameter; G(X) is the nonlinear transformation; By introducing multi-scale features and attention mechanism, the effect of feature fusion is improved.

[0135] Through the multi-dimensional extraction and fusion method of critical features, the accurate characterization of system state changes is achieved. This step numerically differentiates the resilience state evolution model and uses the singular value decomposition algorithm for noise reduction to obtain an accurate state change rate. The real-time monitoring data is identified and normalized for outliers, and the distribution is adjusted by the quantile mapping method to ensure the quality of the monitoring data. In terms of rapid simulation, the system state is rapidly evaluated through the simplified Saint-Venant equations and feature extraction network. Finally, the fluctuation features are extracted through multi-scale decomposition and random matrix theory, and the time-related features are obtained by combining autocorrelation and cross-correlation analysis, and the deep feature fusion network is used to achieve feature integration. Through the multi-dimensional critical feature extraction method, not only can the dynamic changes of the system state be accurately captured, but also the early signals of critical transitions can be effectively identified. Especially when monitoring the resilience state of urban flood control systems, potential risk factors can be discovered in a timely manner, providing a reliable basis for early warning decisions.

[0136] According to one aspect of the present application, step S421 is further:

[0137] The basic statistics are calculated for the critical characteristic indicator set to obtain basic statistical data; the distribution characteristics of the critical characteristic indicator set are extracted using the kernel density estimation method to obtain empirical distribution data; the basic statistical data and the empirical distribution data are fitted to obtain distribution characteristic data.

[0138] The kernel density estimation method is as follows: probability density function f(x) = [1 / (nh(x))] · Σ[K((xx i ) / h(x))·w(x i )]·[1 + α·L(x)]·[1 + β·T(t)]; where: adaptive bandwidth h(x) = h0·[f0(x) / g]^(-γ)·[1 + λ·v(x)]; local weight w(x i ) = exp(-||xx i ||² / 2σ²)·[1 + μ·ρ(x i )]; time series feature T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); local variation v(x) = std(Nx) / mean(Nx); spatial correlation L(x) = Σ[exp(-d i ² / 2η²)·cos(θ i )]; density feature ρ(x i ) = Σexp(-||x i -x j||² / 2ξ²); where: f(x) is the estimated density; n is the number of samples; h(x) is the adaptive bandwidth; K is the kernel function; α is the spatial weight; β is the temporal weight; h0 is the reference bandwidth; f0 is the prior density; γ is the adaptive exponent; λ is the variation weight; μ is the density weight; σ, τ, η, ξ are scale parameters; ω is the period parameter; this method improves the accuracy of density estimation by introducing adaptive bandwidth and spatiotemporal features.

[0139] Step S422, perform parameter estimation on the distribution characteristic data to obtain distribution parameter data; use a mixed Gaussian model to perform probability density modeling on the distribution characteristic data to obtain probability model data; reconstruct the distribution parameter data and the probability model data as a function to obtain density function data.

[0140] The Gaussian mixture model is specifically: probability model function P(x) = Σ[π i ·N(x|μ i ,Σ i )]·[1 + α·M(x)]·[1 + β·T(t)]; where: adaptive weight π i = exp(-E i / θ)·[1 + λ·V i (x)] / Σexp(-E j / θ); covariance matrix Σ i = S i + γ·R i ; Mixed metric M(x) = -Σ[p i ·log(p i )]·exp(-||x-μ*||² / 2σ²); timing modulation T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); local variance V i (x) = Σ[(x-μ i )ᵀΣ i - ¹(x-μ i )]·w(x); where: P(x) is the mixing probability; N(·) is the Gaussian distribution; π i is the mixing weight; μ i is the mean vector; α is the mixing weight; β is the timing weight; λ is the variance weight; θ is the temperature parameter; γ is the regularization coefficient; σ,τ are the scale parameters; ω is the period parameter; this method improves the fitting ability of the model by introducing adaptive weights and timing modulation.

[0141] Step S423, calculating the cumulative distribution function for the density function data to obtain the cumulative distribution data; performing quantile calculation on the cumulative distribution data to obtain preliminary quantile data; and using the quantile regression method to correct the preliminary quantile data to obtain quantile characteristic data.

[0142] The quantile regression method is as follows: quantile function Q(τ|x) = argmin{Σ[ρτ(yf(x,β))·w(x)]+ α·||β||1}·[1 + λ·S(x)]·[1 + μ·T(t)]; where: loss function ρτ(u) = u·(τ-I(u<0)); sample weight w(x) = exp(-||xx*||² / 2σ²)·[1 + γ·ρ(x)]; spatial feature S(x) = Σ[exp(-d i ² / 2η²)·cos(θ i )]; time series characteristics T(t) = exp(-|t-t0|² / 2τ²)·cos(ω·|t-t0|); local density ρ(x) = Σexp(-||xx i ||² / 2ξ²); where: Q(τ|x) is the τ quantile; f(x,β) is the regression function; α is the regularization parameter; λ is the spatial weight; μ is the temporal weight; γ is the density weight; σ,η,τ,ξ are scale parameters; ω is the period parameter; this method improves the robustness of quantile estimation by introducing weighted loss and spatiotemporal features.

[0143] Step S424|, perform threshold sensitivity analysis on the quantile feature data to obtain sensitivity data; use the maximum between-class variance method to optimize the segmentation points of the quantile feature data and sensitivity data to obtain optimized segmentation data; perform feasibility verification on the optimized segmentation data to obtain segmentation point data.

[0144] The maximum inter-class variance method is as follows: the partition function V(t) = [ω1(t)·ω2(t)·(μ1(t)-μ2(t))²]·[1 + α·H(t)]·[1 + β·S(t)]; where: the intra-class weight ω i (t) = Σ[p(x)·I(x∈C i )]·[1 +λ·v i (t)]; class mean μ i (t) = Σ[x·p(x)·I(x∈C i )] / ω i (t); entropy characteristic H(t) = -Σ[p i ·log(p i)]·exp(-|tt*|² / 2τ²); smoothing term S(t) = exp(-|t-t0|² / 2σ²)·cos(ω·|t-t0|); intra-class variance v i (t) = Σ[(x-μ i (t))²·p(x)·I(x∈C i )] / ω i (t); where: V(t) is the between-class variance; ω i (t) is the class weight; μ i (t) is the class mean; α is the entropy weight; β is the smoothing weight; λ is the variance weight; p(x) is the probability density; C i is the category; τ, σ are scale parameters; ω is the period parameter; this method improves the stability of segmentation point selection by introducing entropy features and smoothing terms.

[0145] Step S425, perform graded assignment on the segmentation point data to obtain warning level data; perform uncertainty analysis on the segmentation point data to obtain threshold interval data; perform threshold integration on the warning level data and the threshold interval data to obtain a warning threshold set.

[0146] Through the multi-level warning threshold optimization method, the scientific division of warning levels is achieved. This step estimates the parameters and fits the distribution of the critical characteristic indicator set, and uses the mixed Gaussian model to construct the probability density function, which accurately describes the distribution characteristics of the indicators. Robust quantile characteristics are obtained through cumulative distribution function calculation and quantile regression method. In terms of threshold determination, the segmentation point is optimized through threshold sensitivity analysis and maximum inter-class variance method, and feasibility verification is performed to ensure the rationality of the threshold. Finally, through hierarchical assignment and uncertainty analysis, a complete warning system including warning levels and threshold intervals is constructed. The threshold determination strategy based on statistical theory and optimization methods not only takes into account the distribution characteristics of the indicators, but also takes into account the accuracy and practicality of the warning. Especially in the warning practice of urban flood control systems, it can effectively reduce the false alarm rate and missed alarm rate and improve the reliability of the warning system.

[0147] According to another aspect of the present application, a system for identifying critical states of urban flood resilience considering multiple pressure coupling is also provided, comprising:

[0148] at least one processor; and,

[0149] a memory communicatively connected to at least one processor; wherein,

[0150] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the critical state identification method of urban flood resilience considering multiple pressure coupling of any of the above technical solutions.

[0151] It should be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

Claims

1. A method for identifying the critical state of urban flood resilience considering multiple pressure couplings, characterized in that: The steps include: Step S1: According to the characteristics of the urban flood control system, identify the pressure sources that affect the resilience and performance of the urban flood control system; obtain the research data and perform unified spatiotemporal preprocessing to obtain a unified spatiotemporal scale data set; perform outlier detection and correction on the unified spatiotemporal scale data set to obtain a corrected data set; Decomposing the pressure characteristics of the corrected data set to obtain a pressure feature vector set including time dimension characteristics, space dimension characteristics and intensity dimension characteristics; Step S2, obtaining a pressure characteristic vector set and performing coupling relationship analysis to obtain a coupling strength matrix and a coupling direction matrix; constructing a directed weighted network based on the coupling strength matrix and the coupling direction matrix to obtain a pressure coupling dynamic network; The topological structure of the pressure-coupled dynamic network is analyzed to obtain the network evolution feature set; Step S3: Comprehensively analyze the network evolution feature set and the pre-stored historical resilience assessment data to obtain a resilience state indicator set; perform time series decomposition and scenario simulation on the resilience state indicator set to obtain scenario simulation data; construct a state evolution prediction model based on the scenario simulation data and the resilience state indicator set to obtain a resilience state evolution model; Step S4: perform critical feature analysis based on the toughness state evolution model and pre-stored real-time monitoring data to obtain a critical feature indicator set; perform threshold optimization calculation based on the critical feature indicator set to obtain an early warning threshold set.

2. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: According to the characteristics of the urban flood control system, identify the main stressors that affect the resilience and performance of the urban flood control system; including meteorological stressors, hydrological stressors, engineering stressors and socio-economic stressors; meteorological stressors include rainfall intensity and rainfall duration; hydrological stressors include water level changes and flow fluctuations in rivers or drainage systems; engineering stressors include gate pump status, drainage system capacity and pipe network status; socio-economic stressors include population density, economic activity intensity and traffic flow; Step S12, obtaining research data, including original meteorological data, original hydrological data, original engineering data and original socio-economic data; extracting rainfall intensity and duration data from original meteorological data, water level and flow data from original hydrological data, sluice pump status, drainage system capacity and pipe network status data from original engineering data, and population density and asset distribution data from original socio-economic data, and performing Kriging interpolation calculation to obtain temporary spatial interpolation data; performing linear interpolation on the temporary spatial interpolation data according to the time series to obtain temporary time interpolation data; calculating the time weight function according to the inverse of the data time interval, and performing weight correction on the temporary time interpolation data to obtain a unified spatiotemporal scale data set; Step S13, reading the unified spatiotemporal scale data set and calculating the mean and standard deviation to obtain statistical feature data; The box plot method is used to preliminarily identify outliers in the uniform spatiotemporal scale dataset to obtain preliminary outlier data; the preliminary outlier data is compared with the physical constraints to obtain confirmed outlier data; The local polynomial regression method is used to correct the confirmed outlier data to obtain the corrected data; The corrected data is merged with the normal value data in the dataset with uniform spatiotemporal scale to obtain the corrected dataset; Step S14, extracting rainfall data from the corrected data set and performing rainfall-runoff simulation to obtain runoff simulation data; The runoff simulation data is calculated using a one-dimensional / two-dimensional coupled hydrodynamic model to obtain flood and inundation data; the flood and inundation data are combined with the corrected data set to obtain hydrodynamic characteristic data; Step S15, performing wavelet transform on the hydrodynamic characteristic data to obtain a wavelet coefficient set; performing threshold decomposition on the wavelet coefficient set according to energy distribution characteristics to obtain characteristic component data of different scales; The characteristic component data are reorganized according to the time dimension, space dimension and intensity dimension to obtain multi-dimensional characteristic data; The multi-dimensional feature data is standardized to obtain standardized feature data; the standardized feature data is converted into a vector form to obtain a pressure feature vector set.

3. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 2 is characterized in that: Step S2 is specifically as follows: Step S21, obtaining and calculating the mutual information entropy for each pair of eigenvectors in the pressure eigenvector set to obtain a mutual information entropy matrix; calculating the coupling strength value according to the mutual information entropy matrix to obtain a coupling strength matrix; calculating the Granger causality test statistic for each pair of eigenvectors in the pressure eigenvector set to obtain causality test data; Determine the coupling direction according to the causal test data and obtain the coupling direction matrix; Step S22: constructing network edge weights based on the coupling strength matrix to obtain a weighted edge set; determining the direction of the network edge based on the coupling direction matrix to obtain a directed edge set; combining the weighted edge set and the directed edge set, and adding a time tag to obtain a pressure-coupled dynamic network; Step S23, calculating the node degree distribution of the pressure-coupled dynamic network to obtain node degree characteristic data; Calculate the clustering coefficient of the pressure-coupled dynamic network and obtain clustering feature data; The centrality index of the pressure-coupled dynamic network is calculated to obtain the centrality feature data; the changes in the community structure of the pressure-coupled dynamic network at different time points are calculated to obtain the community evolution data; the node degree feature data, clustering feature data, centrality feature data and community evolution data are combined to obtain the network evolution feature set.

4. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 3 is characterized in that: Step S3 is specifically as follows: Step S31, performing principal component analysis on the network evolution feature set to obtain principal component feature data; performing standardization processing on the pre-stored historical resilience assessment data to obtain standardized resilience data; performing correlation analysis on the principal component feature data and the standardized resilience data to obtain a feature correlation matrix; According to the feature association matrix, a key feature combination is selected to obtain a candidate set of toughness features; a weighted combination of the candidate set of toughness features is performed to obtain a set of toughness state indicators; Step S32, performing time series decomposition on the toughness state indicator set to obtain trend component data and fluctuation component data; Different boundary conditions are set according to the trend component data and the fluctuation component data to obtain scenario boundary data; the scenario boundary data is simulated and calculated using a hydrodynamic model to obtain scenario simulation data; Step S33: construct an autoregressive model for the scenario simulation data and the resilience status indicator set to obtain trend prediction data; The phase space reconstruction parameters are calculated based on the scenario simulation data to obtain the reconstruction parameter data; the phase space is constructed according to the reconstruction parameter data to obtain the state space data; the trend prediction data and the state space data are combined to construct a hybrid prediction model to obtain the resilience state evolution model.

5. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 4 is characterized in that: Step S4 is specifically as follows: Step S41, calculating the system state change rate for the toughness state evolution model to obtain state change rate data; normalizing the pre-stored real-time monitoring data to obtain normalized monitoring data; using a simplified hydrodynamic model to quickly simulate the normalized monitoring data to obtain fast simulation data; performing fluctuation analysis on the state change rate data and the fast simulation data to obtain dynamic fluctuation characteristic data; calculating the time correlation of the normalized monitoring data to obtain time correlation data; The dynamic fluctuation characteristic data and time-related data are subjected to feature fusion to obtain a critical characteristic index set; Step S42, perform statistical distribution analysis on the critical characteristic indicator set to obtain distribution characteristic data; construct a probability density function based on the distribution characteristic data to obtain density function data; perform quantile analysis on the density function data to obtain quantile characteristic data; calculate the optimal split point based on the quantile characteristic data to obtain split point data; convert the split point data into warning thresholds to obtain a warning threshold set.

6. The method for identifying critical states of urban flood resilience considering multiple pressure coupling according to claim 5 is characterized in that: Step S14 is specifically as follows: Step S141, extracting rainfall data from the corrected data set and performing spatiotemporal distribution analysis to obtain rainfall distribution characteristic data; using the Green-Ampt model to calculate infiltration loss to obtain infiltration loss data; using surface roughness data to calculate surface interception loss to obtain interception loss data; performing water balance calculation on rainfall distribution characteristic data, infiltration loss data and interception loss data to obtain effective rainfall data; using the nonlinear unit line method to perform confluence calculation on the effective rainfall data to obtain runoff simulation data; Step S142: performing one-dimensional river hydrodynamic calculation based on the runoff simulation data to obtain river hydrodynamic data; performing urban terrain evolution calculation on the runoff simulation data using a two-dimensional overland flow model to obtain overland flow data; performing coupling calculation on the river hydrodynamic data and overland flow data using an interactive iterative algorithm to obtain one- and two-dimensional coupled data; performing inundation range calculation on the one- and two-dimensional coupled data according to pre-stored terrain elevation data to obtain flood inundation data; Step S143, extracting spatiotemporal features from the corrected data set to obtain basic feature data; calculating hydrodynamic indicators from the flood and waterlogging inundation data to obtain inundation feature data; combining the basic feature data and the inundation feature data using a multi-source data fusion algorithm to obtain combined feature data; optimizing the combined feature data using an adaptive weight method to obtain hydrodynamic feature data; Step S144, performing quality verification on the hydrodynamic characteristic data to obtain characteristic verification data; performing validity verification on the characteristic verification data using physical constraint conditions to obtain characteristic verification data; The reliability of the feature inspection data is evaluated by using a multi-criteria evaluation method to obtain feature evaluation data; The characteristic evaluation data are compared and corrected with the original hydrodynamic characteristic data to obtain the final hydrodynamic characteristic data.

7. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 5 is characterized in that: Step S21 is specifically as follows: Step S211, calculating the mutual information entropy for each pair of eigenvectors in the pressure eigenvector set to obtain preliminary mutual information data; correcting the preliminary mutual information data using a kernel density estimation method to obtain corrected mutual information data; Reconstruct the matrix of the corrected mutual information data to obtain the mutual information entropy matrix; Step S212, obtaining the mutual information entropy matrix and performing normalization processing to obtain normalized mutual information data; The normalized mutual information data is intensity-converted using a nonlinear mapping method to obtain intensity mapping data; Reconstruct the matrix of the intensity mapping data to obtain the coupling intensity matrix; Step S213, performing time lag analysis on each pair of feature vectors in the pressure feature vector set to obtain time lag feature data; Granger causality test is performed on the pressure characteristic vector set and the time-lag characteristic data to obtain preliminary causal data; the preliminary causal data is analyzed for significance using the confidence test method to obtain causal test data; Step S214, performing threshold segmentation on the causal test data to obtain causal determination data; performing directionality analysis on the causal determination data to obtain directional feature data; The directional characteristic data are reconstructed into a matrix to obtain a coupling direction matrix.

8. The critical state identification method of urban flood resilience considering multiple pressure coupling according to claim 5 is characterized in that: Step S32 is specifically as follows: Step S321, obtaining a toughness state indicator set and performing empirical mode decomposition to obtain initial component data; using a change point detection algorithm to perform mutation feature recognition on the initial component data to obtain mutation feature data; The initial component data and the mutation characteristic data are reconstructed to obtain the trend component data and the fluctuation component data; Step S322, performing trend extrapolation on the trend component data to obtain trend prediction data; Perform fluctuation intensity analysis based on fluctuation component data to obtain fluctuation intensity data; The trend forecast data and fluctuation intensity data are converted into boundary conditions using the scenario generation algorithm to obtain boundary solution data; the feasibility of the boundary solution data is verified to obtain scenario boundary data; Step S323: construct a two-dimensional hydrodynamic model calculation grid for the scenario boundary data to obtain calculation grid data; use an adaptive time step algorithm to perform dynamic solution on the calculation grid data to obtain hydrodynamic calculation data; extract results from the hydrodynamic calculation data to obtain simulation results data; organize the simulation results data according to the scenario to obtain scenario simulation data.

9. The method for identifying critical states of urban flood resilience considering multiple pressure coupling according to claim 5 is characterized in that: Step S41 is specifically as follows: Step S411, numerically differentiate the toughness state evolution model to obtain initial change rate data; use a singular value decomposition algorithm to perform noise reduction processing on the initial change rate data to obtain noise-reduced change rate data; perform time scale analysis on the noise-reduced change rate data to obtain state change rate data; Step S412: performing abnormal value identification on the pre-stored real-time monitoring data to obtain cleaned monitoring data; The cleaning monitoring data is normalized to the maximum and minimum values ​​to obtain preliminary normalized data; the preliminary normalized data is distributed adjusted using the quantile mapping method to obtain normalized monitoring data; Step S413, constructing a simplified Saint-Venant equation group based on the normalized monitoring data to obtain simplified equation data; The feature extraction network is used to quickly extract features from the normalized monitoring data to obtain feature extraction data; the simplified equation data and feature extraction data are quickly solved to obtain fast simulation data; Step S414, performing multi-scale decomposition on the state change rate data and the fast simulation data to obtain decomposed fluctuation data; performing feature extraction on the decomposed fluctuation data using random matrix theory to obtain fluctuation feature data; Reconstructing the fluctuation characteristic data to obtain dynamic fluctuation characteristic data; Step S415, calculating the autocorrelation function of the normalized monitoring data to obtain autocorrelation feature data; calculating the cross-correlation function of the normalized monitoring data to obtain cross-correlation feature data; performing feature fusion on the autocorrelation feature data and the cross-correlation feature data to obtain time-related data; Step S416, extracting stability indicators from dynamic fluctuation feature data to obtain stability indicator data; extracting correlation indicators from time-related data to obtain correlation indicator data; using a deep feature fusion network to fuse the stability indicator data and the correlation indicator data to obtain a critical feature indicator set.

10. A critical state identification system for urban flood control resilience considering multiple pressure coupling, characterized in that: include: at least one processor; as well as, a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the method for identifying the critical state of urban flood resilience considering multiple pressure coupling as described in any one of claims 1 to 9.

Images