Urban subway flood anomaly positioning and display system fusing multi-source data

Abstract

The invention provides a multi-source data fused urban subway flood anomaly positioning and display system, which is characterized by comprising a data acquisition module, a data processing module and a data processing module, a data storage module; the factor analysis module is used for analyzing main factors of waterlogging and ponding; the flood prediction module is used for constructing input data according to data corresponding to main factors of waterlogging and ponding in the feature data, and inputting the input data into a flood prediction model to obtain a flood prediction site and a corresponding prediction severity; the waterlogging and ponding prediction module is used for performing calculation on each flood prediction site according to the corresponding feature data to obtain the waterlogging prediction range of the flood prediction site and the predicted ponding depth of each region as a waterlogging prediction result; the result positioning module is used for calculating and obtaining each subway station influenced by flood as a disaster-affected station according to the waterlogging prediction result and subway line map data; and a display module. In a word, the method can accurately predict urban inland inundation and mark and display disaster-affected subway stations.

Description

Technical Field

[0001] The invention belongs to the field of flood prediction, and in particular relates to an urban subway flood anomaly positioning and display system integrating multi-source data. Background Art

[0002] In recent years, an increasing number of floods and flood-related disasters, such as typhoons, landslides and mudslides, have caused catastrophic damage to many cities around the world. Urban waterlogging disasters are becoming increasingly serious in many cities, and their impact has gradually expanded from local areas to drainage networks and river systems. The occurrence of waterlogging disasters is affected by many factors, including the flow generation and convergence mechanism, the construction of the drainage system, and the topographic environment of the city. The differences in these factors lead to the fact that waterlogging disasters can occur in any location and are highly random. Low-lying areas, underground passages, underground garages, and blocks with poor drainage in cities are prone to waterlogging during heavy rains and become the hardest hit areas of waterlogging. When heavy rain exceeds the carrying capacity of the drainage system, rainwater cannot be discharged in time, resulting in waterlogging in the drainage network, further causing surface flooding; the water level of urban river systems rises during heavy rains, and when it exceeds the capacity of the river, it may overflow and flood the surrounding areas. Due to the randomness and complexity of waterlogging disasters, any urban area may be affected, which makes disaster forecasting face huge challenges, and it is difficult to guarantee accuracy and timeliness.

[0003] At present, the methods used in urban flood positioning are as follows:

[0004] Traditional rule-based methods usually judge the possibility of floods based on predefined rules and thresholds. For example, if the rainfall exceeds a certain threshold, it is considered a flood. The advantage of this method is that it is simple and easy to implement, but due to the ever-changing environment and insufficient data, it is difficult to accurately predict and respond to complex geographical and meteorological changes.

[0005] The statistical model-based method uses statistical models to predict the probability of flood occurrence and uses historical data and real-time data for prediction. Its advantage is that it takes into account historical data and changing trends, but it may not be accurate enough for nonlinear relationships and complex geographical environments. When the terrain is complex or rainfall distribution is uneven, the prediction accuracy of the statistical model may be greatly reduced.

[0006] Remote sensing data-based methods monitor surface conditions through satellite images, such as detecting waterlogged areas or changes in river water levels. Its advantages are good real-time performance and can cover a large area. However, the acquisition of remote sensing data is limited by factors such as cloud cover and sensor resolution, resulting in discontinuous or incomplete data.

[0007] In addition, single data sources such as remote sensing data often fail to provide comprehensive analysis and prediction when faced with complex flood situations. Although remote sensing data can reflect surface conditions in real time, it lacks the integration and analysis of multiple information such as underground drainage systems, terrain changes, and historical rainfall data. It is difficult to accurately predict and locate the specific location and severity of floods, and it is unable to fully capture the multiple factors and dynamic changes that cause floods, thus affecting the accuracy of early warnings and the effectiveness of prevention and control measures.

[0008] Therefore, the existing flood location prediction methods still have the problem of low prediction accuracy. Summary of the invention

[0009] The present invention is made to solve the above-mentioned problems, and aims to provide a system for locating and displaying urban subway flood anomalies by integrating multi-source data.

[0010] The invention provides an urban subway flood anomaly positioning and display system integrating multi-source data, which has the following characteristics and comprises: a data acquisition module, which is used for real-time acquisition of rain and flood data, meteorological data and underground drainage data; a data storage module, which is used for storing existing terrain data, as well as rain and flood data, meteorological data and subway drainage data as characteristic data; a factor analysis module, which is used for analyzing the characteristic data to obtain a plurality of main factors of waterlogging; a flood prediction module, which stores a flood prediction model, which is used for constructing input data according to data corresponding to each main factor of waterlogging in the characteristic data, and inputting the input data into the flood prediction model to obtain a flood prediction location and a corresponding predicted severity; the waterlogging prediction module, which is used for calculating each flood prediction location according to the corresponding characteristic data, to obtain the waterlogging prediction range of the flood prediction location and the predicted waterlogging depth of each area as the waterlogging prediction result; a result positioning module, which stores subway line map data, which is used for calculating each subway station affected by the flood as the affected station according to the waterlogging prediction result and the subway line map data; and a display module, which is used for displaying the affected station.

[0011] The urban subway flood anomaly positioning and display system that integrates multi-source data provided by the present invention may also have the following features: wherein the factor analysis module includes: a correlation analysis unit, which is used to perform a correlation analysis on waterlogging events for each factor corresponding to the characteristic data to obtain a plurality of relevant factors; a collinearity test unit, which is used to perform a multicollinearity test on all relevant factors to screen out a plurality of relevant factors as the main factors of waterlogging.

[0012] The urban subway flood anomaly positioning and display system that integrates multi-source data provided by the present invention may also have the following features: wherein, the correlation analysis of waterlogging events is a statistical method or a method based on a tree model, the statistical method includes linear correlation calculation and chi-square test, and the method based on the tree model is to calculate the importance score corresponding to each factor according to the trained random forest model or XGBoost model, and select the factor corresponding to the large importance score as the relevant factor.

[0013] The urban subway flood anomaly positioning and display system for integrating multi-source data provided by the present invention may also have the following features: wherein the flood prediction module includes: an input data generation unit, which is used to preprocess, standardize and transform the data in sequence to generate an input matrix as input data; a first prediction unit, which stores a flood prediction model, which is used to input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity.

[0014] The urban subway flood anomaly positioning and display system for fusing multi-source data provided by the present invention may also have the following features: wherein the flood prediction model includes: a convolution layer, which is used to perform multiple convolution operations on the input data to extract local features; a pooling layer, which is used to aggregate local features to obtain global features; a fully connected layer, which is used to perform a fully connected operation on local features and global features to generate a feature vector; and an output layer, which is used to process the feature vector to obtain the predicted flood location and the corresponding predicted severity.

[0015] The urban subway flood anomaly positioning and display system that integrates multi-source data provided by the present invention can also have the following characteristics: wherein, the waterlogging and water accumulation prediction module includes: a flow simulation unit, which is used to calculate surface flow simulation data based on meteorological data and terrain data; a confluence simulation unit, which stores an underground drainage model constructed based on underground drainage data, and is used to calculate groundwater flow and drainage simulation data based on surface flow simulation data and the underground drainage model; a waterlogging and water accumulation calculation unit, which is used to calculate the groundwater flow and drainage simulation data and the surface flow simulation data to obtain a waterlogging prediction result.

[0016] The urban subway flood anomaly positioning and display system for integrating multi-source data provided by the present invention may also have the following features: wherein the result positioning module includes: a data matching unit storing subway line map data for coordinate matching of the waterlogging prediction result with the subway line map data to obtain a matching result; a positioning unit for calculating the distance between each waterlogging prediction range in the matching result and the nearest subway station through a nearest neighbor algorithm; and a disaster screening unit storing a distance threshold for treating subway stations whose distance is less than the distance threshold as disaster-affected stations.

[0017] The urban subway flood anomaly positioning and display system for integrating multi-source data provided by the present invention may also have such features, including: an early warning module for generating early warning information based on the disaster-stricken sites and waterlogging prediction results, and sending it to designated recipients.

[0018] The urban subway flood anomaly positioning and display system that integrates multi-source data provided by the present invention may also have the following features: a disposal module, wherein the data storage module is also used to store disaster-stricken sites, waterlogging prediction results, flood response measures and processing results; the disposal module is used to conduct in-depth analysis of the data stored in the data storage module and generate an analysis report, which is used to optimize emergency plans and understand historical flood situations.

[0019] Functions and Effects of the Invention

[0020] According to the urban subway flood anomaly positioning and display system integrating multi-source data involved in the present invention, first, the main factors of waterlogging and water accumulation closely related to waterlogging are extracted from terrain data, rain and flood data, meteorological data and underground drainage data through the factor analysis module for predicting floods; second, the data corresponding to each main factor of waterlogging and water accumulation are analyzed and processed through the flood prediction model to obtain accurate flood prediction locations; third, the waterlogging and water accumulation prediction module simulates the underground drainage system through a one-dimensional model, simulates the surface runoff through a two-dimensional model, and uses numerical simulation to generate accurate waterlogging prediction results for each flood prediction location; fourth, the waterlogging prediction results are matched and screened with the subway station information through the result positioning module, and the subway stations that are prone to disasters are obtained as disaster-stricken stations, and displayed through the display module. Therefore, the urban subway flood anomaly positioning and display system integrating multi-source data of the present invention can accurately predict urban waterlogging and mark and display the affected subway stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a block diagram of a subway flood prediction system in an embodiment of the present invention;

[0022] Figure 2 is a block diagram of a flood prediction model in an embodiment of the present invention;

[0023] Figure 3 It is a schematic diagram of the process of locating and displaying abnormalities of urban subway floods in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the following embodiments and accompanying drawings specifically illustrate the urban subway flood anomaly positioning and display system integrating multi-source data of the present invention.

[0025] This embodiment provides a system for locating and displaying urban subway flood anomalies by integrating multi-source data, hereinafter referred to as a subway flood prediction system, which is used to predict subway floods.

[0026] Figure 1 is a block diagram of a subway flood prediction system in an embodiment of the present invention.

[0027] like Figure 1 As shown, the subway flood prediction system 100 includes a data acquisition module 11, a data storage module 12, a factor analysis module 13, a flood prediction module 14, an urban waterlogging prediction module 15, a result positioning module 16, a display module 17, an early warning module 18, a disposal module 19 and a control module 20 that controls the operation of the above modules.

[0028] The data collection module 11 is used to collect rainfall and flood data, meteorological data and underground drainage data in real time.

[0029] In this embodiment, by installing rainfall monitoring stations, groundwater level sensors and using field waterlogging detection technology, the data acquisition module 11 collects rainfall and drainage network hydraulic data in real time, and uses field waterlogging detection data analysis, on-site investigation, network public opinion and other technical means to integrate the above data through the GIS system to establish a surface-underground runoff data set and a flooding data set as rainwater data.

[0030] In this embodiment, the data acquisition module 11 obtains information such as rainfall, wind speed, temperature, humidity, etc. as meteorological data by accessing the real-time data interface of the National Meteorological Bureau, and updates the meteorological data in real time according to a preset automatic data update mechanism.

[0031] In this embodiment, the data acquisition module 11 collects the design and operation data of the subway drainage system, including the subway design drainage volume, pump station location, pipeline capacity, flow rate, etc. as underground drainage data.

[0032] The data storage module 12 is used to store existing terrain data, as well as rainfall and flood data, meteorological data and subway drainage data as characteristic data. The data storage module 12 is also used to store disaster-affected sites, waterlogging prediction results, flood response measures and processing results.

[0033] In this embodiment, the terrain data includes subway data and city data. The subway data is the detailed terrain data along the subway line collected using LiDAR technology, including height, slope, geological features, etc. The city data is the surface cover information extracted using radar images, drone aerial data, etc., including building distribution, vegetation coverage, etc.

[0034] The factor analysis module 13 is used to analyze the characteristic data to obtain multiple main factors of waterlogging. In this embodiment, after generating the main factors of waterlogging, the factor analysis module 13 can continue to use these main factors of waterlogging until the type of collected data changes or the flood prediction model needs to be further optimized.

[0035] The factor analysis module 13 includes a correlation analysis unit 131 and a collinearity testing unit 132 .

[0036] The correlation analysis unit 131 is used to perform a correlation analysis of waterlogging events on the corresponding factors in the feature data to obtain a plurality of correlation factors.

[0037] Among them, the correlation analysis of waterlogging events is a statistical method or a method based on a tree model.

[0038] Statistical methods include linear correlation calculation and chi-square test. In linear correlation calculation, the correlation coefficient between each continuous feature and waterlogging is calculated, and the feature with a larger absolute value is selected as the relevant factor. In chi-square test, the continuous variable is discretized, and then the chi-square test is performed, and the feature with a smaller p value is selected as the relevant factor.

[0039] The tree model-based method is to calculate the importance score corresponding to each factor according to the trained random forest model or XGBoost model, and select the factor corresponding to the large importance score as the relevant factor.

[0040] In this embodiment, the correlation analysis of waterlogging events includes correlation analysis of waterlogging elements, temporal continuity analysis of rainfall and flood, and spatial continuity analysis of rainfall and flood.

[0041] The correlation analysis of waterlogging elements aligns the features in space and time, integrates historical waterlogging events and factors into a data framework and calculates the correlation coefficient; or uses scatter plots or regression plots to intuitively display the correlation between waterlogging elements and waterlogging events, so as to analyze and obtain factors that have a significant impact on waterlogging as relevant factors.

[0042] The temporal continuity analysis of rainfall and floods collects rainfall and flood data at different time steps, such as hours or days, and uses time series analysis methods to calculate the temporal continuity of rainfall and flood events, and obtains the temporal patterns of rainfall and floods and their corresponding factors as relevant factors. Time series analysis methods include the autocorrelation function ACF and the partial autocorrelation function PACF, which are used to detect the periodicity of rainfall and flood events, such as seasonality and daily periodicity.

[0043] The spatial continuity analysis of rainfall and flood is carried out by collecting rainfall and flood data at different spatial locations and using spatial interpolation methods such as Kriging interpolation to analyze the spatial distribution of rainfall and flood events, and identify the waterlogging risk in a specific area and its corresponding factors as relevant factors.

[0044] The collinearity test unit 132 is used to perform a multicollinearity test on all relevant factors, and screen out multiple relevant factors as the main factors of urban waterlogging.

[0045] In this embodiment, the variance inflation factor VIF is used to detect multicollinearity problems. Each relevant factor is used as a variable to calculate the VIF value. The higher the VIF value, the stronger the collinearity between the variable and other variables. In this embodiment, when VIF>10 is set, there is a serious multicollinearity problem. When there is a serious multicollinearity problem, delete the indifferent variables or perform variable transformation such as principal component analysis to eliminate the collinearity problem. Then, the remaining variables are the main factors of urban waterlogging. In this embodiment, the collinearity test unit 132 is used to check the multicollinearity problem in the relevant factors to ensure the independence of each factor and avoid overfitting of the model.

[0046] The flood prediction module 14 stores a flood prediction model, which is used to construct input data according to the data corresponding to each main factor of waterlogging in the characteristic data, and input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity.

[0047] The flood prediction module 14 includes an input data generating unit 141 and a first prediction unit 142 .

[0048] The input data generating unit 141 is used to perform preprocessing, standardization and data conversion on the data in sequence, and generate an input matrix as input data.

[0049] In this embodiment, the input data is a multi-channel input matrix formed by stacking the corresponding feature maps generated by various data sources. For example, the terrain data, rainfall data and meteorological data are aligned on the same spatial and temporal scales. For spatial data such as terrain, pipe network information, etc., grid processing is used to match them with temporal data such as rainfall, meteorological data, etc. Multi-source data are combined into a complete input matrix, and each feature vector represents a comprehensive state of a time and spatial position.

[0050] The first prediction unit 142 stores a flood prediction model, which is used to input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity. In this embodiment, the flood prediction model is constructed based on a convolutional neural network (CNN).

[0051] Figure 2 It is a block diagram of a flood prediction model in an embodiment of the present invention.

[0052] like Figure 2 As shown, the flood prediction model 200 includes a convolution layer 21, a pooling layer 22, a fully connected layer 23 and an output layer 24.

[0053] The convolution layer 21 is used to perform multiple convolution operations on the input data to extract local features. In this embodiment, the convolution operation of the convolution layer 21 helps to capture the spatial patterns and local features in the input data, such as: terrain changes, identifying steep slopes and depressions in the terrain; rainfall distribution, analyzing the distribution of rainfall in different areas; water flow path, capturing the flow path of water on the terrain.

[0054] The pooling layer 22 is used to aggregate local features to obtain global features. The main steps of the pooling layer 22 in this embodiment include: feature aggregation, aggregating local features into more representative global features; calculation optimization, reducing the amount of calculation in subsequent layers, and improving the training and prediction efficiency of the model; preventing overfitting, reducing the complexity of the model through dimensionality reduction operations, and preventing overfitting.

[0055] The fully connected layer 23 is used to perform a fully connected operation on the local features and the global features to generate a feature vector.

[0056] The output layer 24 is used to process the feature vector to obtain the predicted flood location and the corresponding predicted severity.

[0057] In this embodiment, the output layer 24 generates a probability distribution through a Softmax function, or uses a linear activation function to output a continuous risk score. The output layer 24 generates a flood prediction level for each area in the city according to the feature vector, and according to a preset level threshold, the area exceeding the level threshold is used as a flood prediction location, and the corresponding flood prediction level is used as the predicted severity.

[0058] The waterlogging prediction module 15 is used to calculate each flood prediction location according to the corresponding characteristic data to obtain the waterlogging prediction range of the flood prediction location and the predicted waterlogging depth of each area as the waterlogging prediction result.

[0059] The waterlogging and ponding prediction module 15 includes a runoff simulation unit 151 , a confluence simulation unit 152 , and a waterlogging and ponding calculation unit 153 .

[0060] The runoff simulation unit 151 is used to calculate the surface runoff simulation data according to the meteorological data and the terrain data. In this embodiment, the runoff simulation unit 151 calculates the runoff per unit area through the rainfall and the surface characteristics, including the SCS-CN method, i.e., the Curve Number method, which calculates the runoff through the rainfall according to the land use and soil type, and the Green-Ampt method, which simulates the surface infiltration and runoff during the rainfall process based on the soil permeability.

[0061] The confluence simulation unit 152 stores an underground drainage model constructed according to underground drainage data, and is used to calculate the groundwater flow and drainage simulation data according to the surface runoff simulation data and the underground drainage model. In this embodiment, the confluence simulation unit 152 calculates the flow and convergence of runoff after rainfall in the urban drainage system, including pipe network simulation, that is, based on the topological structure of the drainage pipe, using the Manning equation or the dynamic wave equation to calculate the flow of runoff in the pipe, and water surface flow equations such as shallow water equations to simulate the diffusion and flow of surface water under different terrain conditions.

[0062] The waterlogging and ponding calculation unit 153 is used to calculate the groundwater flow and drainage simulation data and the surface runoff simulation data to obtain waterlogging prediction results. In this embodiment, the waterlogging prediction results include the ponding depth of each area.

[0063] The result positioning module 16 stores subway line map data, and is used to calculate each subway station affected by the flood as the affected station according to the waterlogging prediction result and the subway line map data.

[0064] The result positioning module 16 includes a data matching unit 161 , a positioning unit 162 and a disaster screening unit 163 .

[0065] The data matching unit 161 stores the subway line map data, and is used to coordinately match the waterlogging prediction result with the subway line map data to obtain a matching result. In this embodiment, the data matching unit 161 matches the waterlogging prediction result with the subway line map data so that the two have the same coordinate system such as WGS84 or UTM, and then superimposes the waterlogging range, water depth, etc. in the waterlogging prediction result on the subway line map through GIS software to obtain a matching result.

[0066] The positioning unit 162 is used to calculate the distance between each waterlogging prediction range in the matching result and the nearest subway station through a nearest neighbor algorithm.

[0067] The disaster-affected screening unit 163 stores a distance threshold, and is used to select subway stations whose distance is less than the distance threshold as disaster-affected stations.

[0068] The display module 17 is used to display the disaster-affected sites.

[0069] In this embodiment, the display module 17 marks the location of the flood on the electronic map of the subway management system, and dynamically updates it to display the specific location of the abnormal event. In addition, in order to improve the user experience and the readability of information, the electronic map uses a variety of visualization effects. For example, marking points of different colors and shapes are used to indicate the severity and type of the flood, such as blue for mild waterlogging and red for severe waterlogging. For example, it supports the heat map function, which displays the distribution density and impact range of the flood through color gradients, so that managers can understand the flood situation more intuitively.

[0070] Users click on the marked point to view detailed information displayed in the information window, such as water depth, affected area, possible causes, etc. The information window is not only a display of static information, but also has certain interactive functions. Users can view more relevant information through the links or buttons in the window, such as viewing historical data, downloading detailed reports, or directly issuing emergency instructions through the system. This design improves the practicality and user experience of the system, enabling managers to make decisions and handle emergencies more efficiently.

[0071] The warning module 18 is used to generate warning information according to the disaster-affected sites and waterlogging prediction results, and send it to designated recipients.

[0072] In this embodiment, the early warning information includes the time, location, severity, estimated impact range and recommended response measures of the flood. The information sending method of the early warning module 18 includes SMS, email, APP push, etc. The designated recipients include subway management personnel, emergency rescue teams, and relevant government departments.

[0073] The processing module 19 is used to perform in-depth analysis on the data stored in the data storage module and generate an analysis report. The analysis report is used to optimize the emergency plan and understand the historical flood situation.

[0074] In this embodiment, the handling module 19 analyzes the frequency, seasonal changes, geographical distribution and effects of different response measures of floods, and generates analysis reports in the form of charts, reports and maps.

[0075] The control module 20 stores a control program for controlling the operation of each module.

[0076] The following describes the process of locating and displaying urban subway flood anomalies using the subway flood prediction system 100 in conjunction with the accompanying drawings.

[0077] Figure 3 It is a schematic diagram of the process of locating and displaying abnormalities of urban subway floods in an embodiment of the present invention.

[0078] like Figure 3As shown, the process of using the subway flood prediction system 100 to locate and display urban subway flood anomalies includes the following steps:

[0079] Step S1, using the data acquisition module 11 to collect rainfall and flood data, meteorological data and underground drainage data in real time.

[0080] Step S2, using the flood prediction module 14 to construct input data according to the data corresponding to each main factor of waterlogging in the characteristic data, and input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity.

[0081] Step S3, using the waterlogging prediction module 15 to calculate each flood prediction location according to the corresponding characteristic data, to obtain the waterlogging prediction range of the flood prediction location and the predicted waterlogging depth of each area as the waterlogging prediction result.

[0082] Step S4, using the result positioning module 16 to calculate the subway stations affected by the flood as the affected stations according to the waterlogging prediction results and the subway line map data.

[0083] Step S5: using the display module 17 to display the affected sites.

[0084] Functions and Effects of the Embodiments

[0085] According to the urban subway flood anomaly positioning and display system integrating multi-source data involved in this embodiment, first, the main factors of waterlogging and water accumulation closely related to waterlogging are extracted from terrain data, rain and flood data, meteorological data and underground drainage data through the factor analysis module for predicting floods; second, the data corresponding to each main factor of waterlogging and water accumulation are analyzed and processed through the flood prediction model to obtain accurate flood prediction locations; third, the waterlogging and water accumulation prediction module simulates the underground drainage system through a one-dimensional model and the surface runoff through a two-dimensional model for each flood prediction location, and uses numerical simulation to generate accurate waterlogging prediction results; fourth, the waterlogging prediction results are matched and screened with the subway station information through the result positioning module, and the subway stations that are prone to disasters are obtained as disaster-affected stations, and displayed through the display module. In short, this method can accurately predict urban waterlogging and mark and display the affected subway stations.

[0086] Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A system for locating and displaying urban subway flood anomalies by integrating multi-source data, characterized in that: include: Data collection module, used to collect rainfall and flood data, meteorological data and underground drainage data in real time; A data storage module, used to store existing terrain data, as well as the rain and flood data, the meteorological data and the subway drainage data as feature data; A factor analysis module is used to analyze the characteristic data to obtain a plurality of main factors of waterlogging; A flood prediction module stores a flood prediction model, which is used to construct input data according to the data corresponding to each of the main factors of waterlogging in the characteristic data, and input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity; A waterlogging prediction module is used to calculate each of the flood prediction locations according to the corresponding characteristic data to obtain the waterlogging prediction range of the flood prediction location and the predicted waterlogging depth of each area as the waterlogging prediction result; A result positioning module stores subway line map data and is used to calculate each subway station affected by the flood as a disaster-affected station based on the waterlogging prediction result and the subway line map data; A display module is used to display the disaster-affected site.

2. According to the system for locating and displaying urban subway flood anomalies by integrating multi-source data in claim 1, Features: Wherein, the factor analysis module includes: A correlation analysis unit, used to perform a correlation analysis of waterlogging events on the corresponding factors in the characteristic data to obtain a plurality of correlation factors; The collinearity test unit is used to perform a multicollinearity test on all the related factors, and screen out a plurality of the related factors as the main factors of the waterlogging.

3. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 2 is characterized by: in, The waterlogging event correlation analysis is a statistical method or a tree model-based method. The statistical methods include linear correlation calculation and chi-square test, The tree model-based method is to calculate the importance scores corresponding to each of the factors according to the trained random forest model or XGBoost model, and select the factors corresponding to the large importance scores as the relevant factors.

4. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1, Features: Wherein, the flood prediction module includes: An input data generating unit, used for sequentially performing preprocessing, standardization and data conversion on the data to generate an input matrix as the input data; The first prediction unit stores the flood prediction model and is used to input the input data into the flood prediction model to obtain the flood prediction location and the corresponding predicted severity.

5. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1, Features: Wherein, the flood prediction model includes: A convolution layer, used to perform multiple convolution operations on the input data to extract local features; A pooling layer, used to aggregate the local features to obtain global features; A fully connected layer, used for performing a fully connected operation on the local features and the global features to generate a feature vector; The output layer is used to process the feature vector to obtain the predicted flood location and the corresponding predicted severity.

6. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1, Features: Among them, the waterlogging prediction module includes: A runoff simulation unit, used for calculating surface runoff simulation data according to the meteorological data and the terrain data; A confluence simulation unit storing an underground drainage model constructed according to the underground drainage data, and used for calculating the groundwater flow and drainage simulation data according to the surface flow simulation data and the underground drainage model; The waterlogging and ponding calculation unit is used to calculate the groundwater flow and drainage simulation data and the surface runoff simulation data to obtain the waterlogging prediction result.

7. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1, Features: Wherein, the result positioning module includes: A data matching unit storing subway line map data, used for performing coordinate matching between the waterlogging prediction result and the subway line map data to obtain a matching result; A positioning unit, used to calculate the distance between each of the waterlogging prediction ranges in the matching result and the nearest subway station by using a nearest neighbor algorithm; The disaster-affected screening unit stores a distance threshold, and is used to select the subway stations whose distances are less than the distance threshold as the disaster-affected stations.

8. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1 is characterized in that: Also includes: The early warning module is used to generate early warning information according to the disaster-stricken sites and the waterlogging prediction results, and send it to a designated recipient.

9. The urban subway flood anomaly positioning and display system integrating multi-source data according to claim 1 is characterized in that: Also includes: Disposal module, The data storage module is also used to store the disaster-affected sites, the waterlogging prediction results, flood response measures and processing results. The processing module is used to perform in-depth analysis on the data stored in the data storage module and generate an analysis report. The analysis report is used to optimize emergency response plans and understand historical flood situations.

Images