Sponge city design optimization method and system based on rainfall calculation

Abstract

The present invention relates to a sponge city design optimization method and system based on rainfall measurement, comprising the following steps: predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtaining the probability distribution of future rainfall and the future measured rainfall; performing spatial analysis on the target sponge city through a preset geographic information system, and obtaining a distribution map of waterlogging points; using a Bayesian network algorithm, based on the distribution map of waterlogging points, the future measured rainfall and the probability distribution of future rainfall, evaluating the waterlogging risk level of each area in the target sponge city, and obtaining a waterlogging risk map; using a preset multi-objective optimization algorithm, performing layout optimization design on the target sponge city based on the waterlogging risk map, and obtaining an optimal configuration plan, which solves the problem of how to scientifically and reasonably predict rainfall patterns and impacts, and effectively alleviate urban waterlogging problems.

Description

Technical Field

[0001] The present invention relates to the technical field of sponge city design, and in particular to a sponge city design optimization method and system based on rainfall measurement. Background Art

[0002] With the acceleration of urbanization, urban areas are expanding, and the original natural surface is replaced by a large amount of hardened ground, which leads to a significant decrease in rainwater infiltration capacity and an increased burden on urban drainage systems. Under extreme weather conditions, such as heavy rains, urban waterlogging occurs frequently, causing great inconvenience to residents and even causing significant losses of life and property. In addition, the reduction in green space during urbanization further weakens the city's self-regulation ability, causing the degradation of urban ecosystem functions and a decline in environmental quality.

[0003] Faced with this series of challenges, the traditional urban drainage system can no longer meet the needs of modern urban development. Therefore, the concept of sponge city came into being. Sponge city aims to enhance the city's ability to absorb, store, infiltrate and purify rainwater by building a complete rainwater collection and utilization system, thereby effectively alleviating urban waterlogging and improving the urban water environment. However, in actual operation, sponge city construction faces many difficulties, such as how to scientifically and reasonably predict rainfall patterns and their impacts, and how to effectively plan urban spatial structures based on prediction results to achieve the best rainwater management effect. The existence of these problems limits the effective implementation and promotion of the sponge city concept.

[0004] To this end, a sponge city design optimization method based on rainfall measurement is proposed. This method combines advanced methods such as historical rainfall data analysis, climate data prediction, geographic information system spatial analysis and Bayesian network algorithm, which can more accurately assess the risk of urban waterlogging and conduct scientific and reasonable urban layout optimization design based on this. This method not only helps to improve the city's ability to cope with extreme weather, but also promotes the sustainable use of water resources, providing new ideas and technical support for solving urban waterlogging problems. However, despite the significant advantages of this method, it still needs to overcome obstacles such as technical costs and difficulty in data acquisition in the actual application process. At the same time, it also requires the support and cooperation of relevant policies to ensure the smooth implementation of the sponge city project. Summary of the invention

[0005] The main purpose of the present invention is to provide a sponge city design optimization method and system based on rainfall measurement, which solves the problem of how to scientifically and reasonably predict rainfall patterns and impacts, and effectively alleviate urban waterlogging problems.

[0006] To achieve the above object, the present invention provides a sponge city design optimization method based on rainfall measurement, comprising the following steps:

[0007] Obtain historical rainfall data and climate data of the target sponge city, and perform frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data;

[0008] Predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtaining the probability distribution of future rainfall and the future estimated rainfall;

[0009] Perform spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points;

[0010] Using a Bayesian network algorithm, based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, the waterlogging risk level of each area in the target sponge city is evaluated to obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas, and low-risk areas;

[0011] By using a preset multi-objective optimization algorithm, the layout of the target sponge city is optimized and designed based on the waterlogging risk map to obtain the optimal configuration solution.

[0012] Further, frequency distribution analysis is performed on the historical rainfall data to obtain rainfall analysis data, including:

[0013] Obtaining original historical rainfall data of multiple meteorological stations of the target sponge city, and cleaning the original historical rainfall data to remove outliers and missing values, to obtain historical rainfall data;

[0014] Performing rainfall trend analysis on the historical rainfall data to obtain rainfall trend data;

[0015] Performing multi-scale wavelet transform on the rainfall trend data to extract rainfall characteristics at different time scales to obtain multi-scale rainfall characteristic data;

[0016] Using extreme value theory, based on the rainfall trend data and multi-scale rainfall characteristic data, the probability distribution of extreme rainfall events is calculated to obtain the probability distribution of extreme rainfall events; wherein the probability distribution of extreme rainfall events is the probability distribution of the maximum rainfall amount and the longest duration;

[0017] Based on the probability distribution of the extreme rainfall event, the multi-scale rainfall characteristic data and the rainfall trend data, rainfall analysis data is obtained; wherein the rainfall analysis data includes rainfall intensity, rainfall duration and rainfall interval period.

[0018] Furthermore, the prediction of the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data to obtain the probability distribution of future rainfall and the future estimated rainfall includes:

[0019] Randomly sampling the rainfall intensity based on a Markov chain Monte Carlo algorithm to determine the transfer path probability of rainfall of different intensities;

[0020] Performing state hidden analysis and mining on the rainfall duration to obtain hidden duration state probability distribution;

[0021] The conditional random field algorithm is used to extract the correlation features of the rainfall interval period, so as to construct the conditional probability relationship between the rainfall interval period, rainfall intensity and duration, and obtain the conditional probability relationship between the interval period;

[0022] Combining the data of the transfer path probability, the hidden duration state probability distribution and the interval period conditional probability relationship to obtain rainfall combination data;

[0023] Constructing rainfall probability density data based on the rainfall combination data;

[0024] The probability distribution of the rainfall probability density data is adjusted by the maximum entropy principle to obtain adjusted probability density data;

[0025] Based on the adjusted probability density data and the climate data, the probability of occurrence of rainfall events in the target sponge city is predicted to obtain the probability distribution of future rainfall and the future estimated rainfall.

[0026] Furthermore, the target sponge city is spatially analyzed by a preset geographic information system to obtain a distribution map of waterlogging points, including:

[0027] Performing DEM analysis on the topographic data of the target sponge city through a preset geographic information system to obtain a topographic feature map; wherein the obtained topographic feature map includes slope, slope aspect and elevation;

[0028] Using a preset hydrological model, the surface runoff path in the topographic feature map is simulated to obtain a runoff simulation path map;

[0029] Searching the underground pipeline data in the target sponge city in the database, and performing network analysis on the underground pipeline data to identify the distribution and connection relationship of the underground pipelines, and obtaining underground pipeline distribution network data;

[0030] Using a network overlay analysis method, based on a runoff simulation path diagram and the underground pipeline distribution network data, the mutual influence between the surface runoff and the underground pipeline is evaluated to obtain a runoff influence diagram;

[0031] Classify and analyze the land use data of the target sponge city, identify the impact of different land use types on the surface runoff, and obtain a land use impact map;

[0032] A multi-criteria decision analysis method is used to obtain a distribution map of waterlogging points based on the runoff influence map and the land use influence map.

[0033] Furthermore, the Bayesian network algorithm is used to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall and the probability distribution of future rainfall, to obtain a waterlogging risk map, including:

[0034] Based on the Bayesian network structure learning algorithm, the characteristic analysis of the distribution map of water-prone points is performed to determine the dependency relationship between nodes and obtain the network structure of water-prone points;

[0035] Through the preset Monte Carlo simulation technology, multiple rainfall scenarios and the corresponding water accumulation conditions of each rainfall scenario are generated based on the network structure of the water-prone points, the future calculated rainfall, and the probability distribution of future rainfall;

[0036] Conducting waterlogging risk assessment on each rainfall scenario and the corresponding waterlogging situation to obtain risk indicator data; wherein the risk indicator data includes flooding depth and waterlogging time;

[0037] Based on the risk indicator data, the target sponge city area is divided into different risk level categories to obtain a risk level classification result; wherein the risk level classification result includes a high risk category, a medium risk category and a low risk category;

[0038] The risk level classification results are marked on the distribution map of waterlogging points to obtain a waterlogging risk map; wherein the waterlogging risk map is the specific location and range of high-risk areas, medium-risk areas and low-risk areas.

[0039] Furthermore, the use of a preset multi-objective optimization algorithm to optimize the layout design of the sponge city based on the waterlogging risk map to obtain the optimal configuration solution includes:

[0040] Extracting and analyzing the hydrogeological characteristics of the waterlogging risk area of ​​the sponge city based on the waterlogging risk map to obtain waterlogging hydrogeological parameters; wherein the waterlogging hydrogeological parameters include groundwater level changes corresponding to the permeability coefficient;

[0041] Constructing a permeability coefficient-groundwater level change curve based on the groundwater level change corresponding to the permeability coefficient;

[0042] Through a preset multi-objective optimization algorithm, a multi-objective optimization calculation is performed on the sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions;

[0043] Perform spatial cluster analysis on the candidate layout schemes of sponge facilities and obtain the clustering results of the layout schemes;

[0044] Through the preset game theory algorithm, the strategic game analysis is performed on the representative solutions of each cluster in the layout solution clustering results to obtain the game equilibrium layout solution set;

[0045] Under various rainfall scenarios, a neural network algorithm is used to optimize the layout design of the sponge city based on the game equilibrium layout solution set to obtain the optimal configuration solution.

[0046] Furthermore, the preset multi-objective optimization algorithm is used to perform multi-objective optimization calculation on the target sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions, including:

[0047] Determine the variation law of the permeability coefficient and the groundwater level based on the permeability coefficient-groundwater level variation curve by using a preset multi-objective optimization algorithm;

[0048] Based on the above-mentioned variation law, a sensitivity analysis of the permeability coefficient was conducted to obtain the influence of the permeability coefficient on the groundwater level change under different rainfall scenarios;

[0049] Based on the impact degree and change law, the hydrological characteristics of the sponge city are analyzed to obtain the hydrological response mode and hydrological characteristic data in the waterlogging risk area;

[0050] Based on the hydrological response pattern and hydrological characteristic data, a multi-objective optimization calculation is performed on the sponge city to obtain a set of candidate sponge facility layout solutions.

[0051] The present invention also provides a sponge city design optimization system based on rainfall measurement, comprising:

[0052] The first analysis module is used to obtain historical rainfall data and climate data of the target sponge city, and perform frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data;

[0053] A prediction module, used to predict the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtain the probability distribution of future rainfall and the future estimated rainfall;

[0054] The second analysis module is used to perform spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points;

[0055] An evaluation module is used to use a Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, so as to obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas, and low-risk areas;

[0056] The design module is used to utilize a preset multi-objective optimization algorithm to optimize the layout design of the target sponge city based on the waterlogging risk map to obtain an optimal configuration solution.

[0057] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0058] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0059] The sponge city design optimization method based on rainfall calculation provided by the present invention comprises the following steps: obtaining historical rainfall data and climate data of a target sponge city, and performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data; predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data to obtain the probability distribution of future rainfall and the future measured rainfall; performing spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points; and adopting a Bayesian network algorithm to predict the probability distribution of future rainfall based on the distribution map of waterlogging points, the future measured rainfall and the probability distribution of future rainfall. The waterlogging risk level of each area in the target sponge city is evaluated to obtain a waterlogging risk map; the layout of the target sponge city is optimized and designed based on the waterlogging risk map using a preset multi-objective optimization algorithm to obtain the optimal configuration solution. The above-mentioned technical means solve the problem of how to scientifically and reasonably predict rainfall patterns and impacts, and effectively alleviate urban waterlogging problems. The Bayesian network algorithm is used to comprehensively consider factors such as the distribution of waterlogging points, future estimated rainfall, and rainfall probability distribution. This method can scientifically evaluate the waterlogging risk level of different areas, form a detailed waterlogging risk map, and provide beneficial effects of decision support for urban managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the steps of a sponge city design optimization method based on rainfall measurement in one embodiment of the present invention;

[0061] Figure 2 It is a structural block diagram of a sponge city design optimization system based on rainfall measurement in one embodiment of the present invention;

[0062] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0063] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of a sponge city design optimization method based on rainfall measurement in one embodiment of the present invention;

[0066] In one embodiment of the present invention, a sponge city design optimization method based on rainfall measurement is provided, comprising the following steps:

[0067] Step S1, obtaining historical rainfall data and climate data of the target sponge city, and performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data.

[0068] Specifically, in order to achieve the step of "obtaining historical rainfall data and climate data of the target sponge city, and performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data" mentioned above, it is first necessary to collect rainfall records and related climate data of the target sponge city over the years. These data can be obtained from the National Meteorological Administration or local meteorological stations, or through satellite remote sensing technology. For example, in a specific sponge city construction project, the project team can download daily rainfall data for the past ten years by visiting the official website of the local meteorological department, and collect climate information such as temperature, humidity, wind speed, etc. during the same period. Then, professional data analysis software, such as SPSS or Pandas library in Python programming language, is used to process the collected historical rainfall data, remove invalid values ​​and outliers, and ensure the accuracy and reliability of the data. After completing data cleaning, the next step is to perform frequency distribution analysis on the cleaned rainfall data, that is, to count the number or frequency of different rainfall amounts in a specific time period. For example, the proportion of days corresponding to the three intervals of daily rainfall less than 10 mm, between 10 and 50 mm, and greater than 50 mm can be calculated. By drawing histograms or cumulative frequency curves, the distribution of different rainfall intensities can be intuitively displayed, helping researchers understand the rainfall patterns and seasonal changes in the target sponge city. Such analysis results not only provide an important reference for subsequent rainfall event predictions, but also make the assessment of urban waterlogging risks more scientific and reasonable.

[0069] Step S2, predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtaining the probability distribution of future rainfall and the future estimated rainfall.

[0070] Specifically, after completing the collection and frequency distribution analysis of the historical rainfall data and climate data of the target sponge city, the next step is to predict the probability of future rainfall events based on these analysis results, and then obtain the probability distribution of future rainfall and the future rainfall. This process mainly relies on statistical models and machine learning algorithms to capture the relationship between rainfall patterns and climate factors by training models. For example, in specific application scenarios, the project team can use time series analysis methods, such as ARIMA models, or machine learning methods, such as random forests and support vector machines, to use existing rainfall analysis data and climate data as input variables to train models to learn the association rules between these variables and rainfall events. On this basis, the model can predict rainfall conditions in a certain period of time in the future, including the probability of occurrence of rainfall events of different intensities and the expected total rainfall. In order to ensure the accuracy of the prediction, it is also necessary to continuously adjust and optimize the model parameters, such as selecting the best model hyperparameter combination through cross-validation methods, or introducing more influencing factors, such as soil moisture, vegetation coverage, etc., to improve the generalization ability of the model. At the same time, considering the impact of climate change on rainfall patterns, the training data set can be updated regularly and the latest observation data can be added to enable the model to adapt to changes in environmental conditions and maintain the timeliness and accuracy of the prediction. For example, in a sponge city construction project, if the model predicts that there will be continuous moderate to heavy rain in the next few weeks, the drainage system maintenance work can be done in advance based on this prediction, the monitoring of waterlogging points can be strengthened, and timely measures can be taken to prevent possible waterlogging disasters. In this way, through scientific and reasonable rainfall prediction, strong data support and technical guarantee are provided for the construction and management of sponge cities.

[0071] Step S3, performing spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points.

[0072] Specifically, after analyzing the historical rainfall data and climate data of the target sponge city and predicting the probability of future rainfall events, the next important step is to conduct spatial analysis of the target sponge city through a preset geographic information system (GIS) to obtain a distribution map of waterlogging points. This process involves using the powerful spatial data analysis function of GIS, combined with multiple factors such as topography, underground pipeline layout, and building density, to accurately identify the locations where waterlogging may occur in the urban area. For example, in a specific sponge city construction project, the project team can first import the city's digital elevation model (DEM) on the GIS platform, and then overlay vector layers such as urban roads, rivers, lakes, and green parks on this basis to build a complete urban spatial database. Subsequently, by analyzing information such as terrain slope, water flow direction and speed, potential low-lying areas where water flows converge can be identified. These areas are often high-incidence areas of urban waterlogging. At the same time, the distribution of urban drainage pipe networks, especially the location information of key nodes such as inspection wells and pumping stations, can be combined to evaluate the carrying capacity and potential bottlenecks of the existing drainage system, and further screen out areas with poor drainage. After completing the above spatial data analysis, the GIS system can automatically generate a detailed distribution map of waterlogging points, clearly marking the specific location of each waterlogging point and its surrounding environmental characteristics. This distribution map not only provides an important basis for subsequent waterlogging risk assessment, but also provides intuitive guidance for urban planners and managers when renovating drainage facilities and building sponge cities. For example, based on the distribution map of waterlogging points, the project team can give priority to adding green infrastructure such as permeable pavement and rain gardens in high-risk areas to improve the surface rainwater infiltration capacity, reduce the pressure on the urban drainage system, and effectively reduce the risk of waterlogging.

[0073] Step S4, using a Bayesian network algorithm, based on the distribution map of waterlogging points, the future calculated rainfall and the probability distribution of future rainfall, evaluates the waterlogging risk level of each area in the target sponge city to obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas and low-risk areas.

[0074] Specifically, after completing the production of the distribution map of waterlogging points in the target sponge city, the next step is to use the Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map, future measured rainfall and the probability distribution of future rainfall, and finally form a waterlogging risk map, which divides the area into high-risk areas, medium-risk areas and low-risk areas. Specifically, the Bayesian network algorithm is a probabilistic reasoning model that can handle uncertainty problems and is very suitable for assessing risks in complex environments. In this process, we first need to collect various factors related to waterlogging, such as the location of waterlogging points, historical rainfall records, topographic characteristics, and the efficiency of the drainage system, and then use these factors as nodes of the Bayesian network. Each node represents a variable, and the connection between nodes represents the causal relationship or correlation between variables. For example, in the application scenario of sponge cities, if the terrain of a certain area is low-lying and surrounded by a large amount of hard ground, then even if the drainage system is relatively complete, the area may still become a waterlogging point in heavy rainfall events. Next, we also incorporate the future estimated rainfall and the probability distribution of future rainfall into the Bayesian network model. This step is to more accurately predict the possibility of waterlogging in various regions under different rainfall scenarios. For example, for a city that is expected to experience continuous heavy rain in the next few days, we can use meteorological forecast data to adjust the node weights of the rainfall intensity and duration in the Bayesian network, so as to calculate the probability of each waterlogging point being converted into an actual waterlogging point under different rainfall levels. In this way, the Bayesian network can comprehensively consider the influence of multiple factors, assign a waterlogging risk level to each area, and then generate a complete waterlogging risk map. Finally, based on the generated waterlogging risk map, urban managers can take more targeted measures to reduce the impact of waterlogging. For example, in high-risk areas, drainage facilities can be strengthened to improve emergency response capabilities; in medium-risk areas, greening design can be optimized to increase rainwater absorption capacity; and in low-risk areas, resource investment can be appropriately reduced, and more attention can be paid to daily maintenance and management. In this way, not only can the probability of waterlogging disasters be effectively reduced, but also limited urban construction funds can be reasonably allocated to maximize resource utilization.

[0075] Step S5, using a preset multi-objective optimization algorithm, optimizing the layout design of the target sponge city based on the waterlogging risk map to obtain an optimal configuration solution.

[0076] Specifically, after obtaining the waterlogging risk map, the next key step is to use the preset multi-objective optimization algorithm to optimize the layout design of the target sponge city based on this waterlogging risk map in order to obtain the optimal configuration plan. This process involves the balance and optimization of multiple objectives, including but not limited to reducing waterlogging risk, improving rainwater utilization, and controlling construction costs. The multi-objective optimization algorithm can find one or more Pareto optimal solutions among many possible design solutions, that is, solutions that cannot further improve other objectives without sacrificing a certain goal. For example, in the construction of sponge cities, minimizing waterlogging risk, maximizing rainwater recycling efficiency, and minimizing construction costs can be set as three main optimization goals. In specific implementation, it is necessary to first define the quantitative indicators of these goals. For example, waterlogging risk can be measured by the product of waterlogging probability and impact range, rainwater recycling efficiency can be determined based on the ratio of rainwater collection to total precipitation, and construction cost is directly calculated based on actual expenses such as material costs and construction costs. Next, these quantitative indicators are input into multi-objective optimization algorithms, such as genetic algorithms and particle swarm optimization algorithms, which can search for optimal solutions by simulating the evolutionary process or group behavior in nature. During the optimization process, the algorithm will continuously generate new design solutions, evaluate the pros and cons of each solution according to the preset objective function, and gradually converge to the optimal solution. Taking a specific sponge city construction project as an example, assuming that the project is located in an old urban area prone to waterlogging, the project team has obtained a detailed waterlogging risk map through the previous steps, showing which areas belong to high-risk areas, medium-risk areas, and low-risk areas. Based on this map, the team can use a multi-objective optimization algorithm to explore different design solutions, such as increasing the proportion of permeable pavement and rain gardens in high-risk areas to enhance the surface rainwater infiltration capacity; setting up more rainwater collection pools and artificial wetlands in medium-risk areas to improve the storage and purification capacity of rainwater; and mainly carrying out greening transformation in low-risk areas to improve the ecological environment quality of the city. After multiple rounds of iterative optimization, an optimal configuration solution that can effectively reduce the risk of waterlogging and take into account both economic and social benefits is finally selected, thus providing strong technical support for the scientific planning and construction of sponge cities.

[0077] In a specific embodiment, frequency distribution analysis is performed on the historical rainfall data to obtain rainfall analysis data, including:

[0078] Obtaining original historical rainfall data of multiple meteorological stations of the target sponge city, and cleaning the original historical rainfall data to remove outliers and missing values, to obtain historical rainfall data;

[0079] Performing rainfall trend analysis on the historical rainfall data to obtain rainfall trend data;

[0080] Performing multi-scale wavelet transform on the rainfall trend data to extract rainfall characteristics at different time scales to obtain multi-scale rainfall characteristic data;

[0081] Using extreme value theory, based on the rainfall trend data and multi-scale rainfall characteristic data, the probability distribution of extreme rainfall events is calculated to obtain the probability distribution of extreme rainfall events; wherein the probability distribution of extreme rainfall events is the probability distribution of the maximum rainfall amount and the longest duration;

[0082] Based on the probability distribution of the extreme rainfall event, the multi-scale rainfall characteristic data and the rainfall trend data, rainfall analysis data is obtained; wherein the rainfall analysis data includes rainfall intensity, rainfall duration and rainfall interval period.

[0083] Specifically, the process of performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data is a complex and delicate task, which involves multiple links such as data acquisition, cleaning, trend analysis, feature extraction, and probability distribution calculation. The purpose of this process is to fully understand the rainfall characteristics of the target sponge city and provide a solid foundation for subsequent rainfall event prediction and waterlogging risk management. Specifically, it is necessary to first obtain the original historical rainfall data from multiple meteorological stations in the target sponge city. These data usually contain daily rainfall records for many years, which may be stored in the form of spreadsheets or in the form of databases. In order to ensure the quality of the data, these raw data must be cleaned to remove outliers and missing values, so as to obtain historical rainfall data that can be used for analysis. For example, in a specific sponge city construction project, the project team can obtain daily rainfall data for the past twenty years from the local meteorological bureau, and then use Python or R language to write scripts to automatically detect and delete those obviously wrong data points, such as negative rainfall or extremely high values ​​beyond a reasonable range, and fill in the data of missing dates to ensure the integrity of the data series. After completing the data cleaning, the next step is to perform rainfall trend analysis on the historical rainfall data to reveal the changing patterns of rainfall patterns over time. This phase of work usually uses statistical methods, such as linear regression analysis or moving average method, to identify long-term rainfall trends. For example, the project team can use SPSS software to perform linear regression analysis on the cleaned rainfall data to find the trend line of rainfall changes over time. This trend line can help us determine whether there is a trend of increasing or decreasing rainfall in the region year by year. This trend analysis is crucial to understanding the impact of climate change on rainfall patterns and also provides important background information for subsequent rainfall forecasts. On the basis of obtaining rainfall trend data, these data are further subjected to multi-scale wavelet transform to extract rainfall characteristics at different time scales. Wavelet transform is a time-frequency analysis tool that is particularly suitable for processing non-stationary signals. It can decompose rainfall data into components on multiple time scales, thereby revealing rainfall characteristics at different time scales. For example, in the application scenario of sponge city, the project team can use the wavelet transform function in MATLAB to convert daily rainfall data into coefficients on different time scales. These coefficients reflect various rainfall characteristics from short-term fluctuations to long-term trends. By comparing the changes in coefficients at different time scales, it can be found that rainfall activities at certain specific time scales are more active. These characteristics are very useful for understanding the occurrence mechanism of rainfall events. With the multi-scale rainfall characteristic data, the next step is to use extreme value theory to calculate the probability distribution of extreme rainfall events based on rainfall trend data and multi-scale rainfall characteristic data. Extreme value theory is a branch of statistics that is specifically used to analyze the probability distribution of extreme events. It can help us estimate the possibility of extreme rainfall events occurring within a certain period of time.For example, in a sponge city construction project, the project team can use the Gumbel distribution or Weibull distribution model in extreme value theory, combined with rainfall trend data and multi-scale rainfall characteristic data, to calculate the probability distribution of maximum rainfall and longest duration. This means that the team can predict the probability that the maximum daily rainfall at a specific location exceeds a certain threshold in the next year, or the probability that the longest continuous rainfall days exceed a certain threshold. The probability distribution of these extreme rainfall events provides a scientific basis for the planning and design of urban drainage systems, helping decision makers to rationally allocate resources and improve the city's flood resistance. Finally, based on the probability distribution of extreme rainfall events, multi-scale rainfall characteristic data and rainfall trend data, rainfall analysis data is comprehensively obtained, including key parameters such as rainfall intensity, rainfall duration and rainfall interval period. These parameters not only describe the basic characteristics of rainfall events, but also reflect the distribution patterns of rainfall events in time and space. For example, in the application of sponge cities, the project team can use rainfall analysis data to identify which months are more likely to have high-intensity short-term rainfall, and which areas are more likely to become hotspots for long-term continuous rainfall due to terrain reasons. This information is crucial for developing effective flood control strategies, and can help urban managers make adequate preparations before the rainy season arrives and reduce the impact of flood disasters on urban life. In summary, the process of obtaining rainfall analysis data by frequency distribution analysis of historical rainfall data is a multi-step, multi-technical integration process that requires interdisciplinary knowledge and skills. From data acquisition to cleaning, to trend analysis, feature extraction, and probability distribution calculation, each step is crucial and together constitutes a complete rainfall characteristic analysis framework. This framework not only provides scientific data support for the construction and management of sponge cities, but also provides valuable references for hydrological and meteorological research in other fields.

[0084] In a specific embodiment, the prediction of the probability of occurrence of a rainfall event in the target sponge city based on the rainfall analysis data and the climate data to obtain the probability distribution of future rainfall and the future estimated rainfall includes:

[0085] Randomly sampling the rainfall intensity based on a Markov chain Monte Carlo algorithm to determine the transfer path probability of rainfall of different intensities;

[0086] Performing state hidden analysis and mining on the rainfall duration to obtain hidden duration state probability distribution;

[0087] The conditional random field algorithm is used to extract the correlation features of the rainfall interval period, so as to construct the conditional probability relationship between the rainfall interval period, rainfall intensity and duration, and obtain the conditional probability relationship between the interval period;

[0088] Combining the data of the transfer path probability, the hidden duration state probability distribution and the interval period conditional probability relationship to obtain rainfall combination data;

[0089] Constructing rainfall probability density data based on the rainfall combination data;

[0090] The probability distribution of the rainfall probability density data is adjusted by the maximum entropy principle to obtain adjusted probability density data;

[0091] Based on the adjusted probability density data and the climate data, the probability of occurrence of rainfall events in the target sponge city is predicted to obtain the probability distribution of future rainfall and the future estimated rainfall.

[0092] Specifically, the process of predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, obtaining the probability distribution of future rainfall and the future rainfall measurement is a highly comprehensive task involving knowledge in multiple fields such as statistics, machine learning and probability theory. The main purpose of this process is to accurately predict rainfall events through advanced algorithms and models, and provide a scientific basis for urban waterlogging risk management. Specifically, it is first necessary to use the Markov Chain Monte Carlo (MCMC) algorithm to randomly sample the rainfall intensity to determine the probability of the transfer path of rainfall of different intensities. The MCMC algorithm is an iterative method for extracting samples from complex probability distributions, which is particularly suitable for dealing with problems in high-dimensional parameter space. For example, in a sponge city construction project, the project team can use the MCMC algorithm to generate a series of random samples based on the rainfall intensity sequence in the historical rainfall data, which represent the transition paths between different rainfall intensities. By analyzing these samples, the probability of transferring from one rainfall intensity to another can be calculated, thereby constructing a transfer matrix of rainfall intensity. After obtaining the transfer path probability of rainfall intensity, the next step is to perform state hidden analysis and mining on the rainfall duration to obtain the hidden duration state probability distribution. A method similar to the Hidden Markov Model (HMM) is used here, which assumes that there are some unobserved states behind the observed rainfall duration, which affect the distribution of rainfall duration. For example, the project team can divide the rainfall duration into several states, such as "short", "medium" and "long", and then use the EM algorithm (expectation maximization algorithm) to estimate the probability distribution of rainfall duration in each state. In this way, not only can the internal structure of rainfall duration be revealed, but also which factors may lead to the extension or shortening of rainfall duration can be identified. Next, the conditional random field (CRF) algorithm is used to extract the associated features of the rainfall interval period to construct the conditional probability relationship between the rainfall interval period, rainfall intensity and duration, and obtain the interval period conditional probability relationship. CRF is a statistical modeling method for sequence labeling and structured prediction, which is particularly suitable for processing dependencies in time series data. In the application scenario of sponge city, the project team can regard the rainfall interval period, rainfall intensity and duration as multiple features on a time series, and then use the CRF model to learn the interaction between these features. By training the CRF model, the conditional probability of each feature at different time points can be obtained, thereby establishing the connection between the rainfall interval period and the other two features. After completing the above steps, it is necessary to combine the data of the transfer path probability, the hidden duration state probability distribution and the interval period conditional probability relationship to obtain rainfall combination data. This process actually integrates the information obtained from different angles to form a complete description of the rainfall event.For example, the project team can combine the transition probability of rainfall intensity, the state probability distribution of rainfall duration, and the conditional probability relationship of rainfall interval period into a unified data structure for subsequent processing. This data combination not only improves the integrity of information, but also lays the foundation for subsequent rainfall forecasting. Constructing rainfall probability density data based on the rainfall combination data is the key step in the next step. This step aims to convert the combined data into the form of probability density function, which is convenient for the calculation and adjustment of probability distribution. For example, the project team can use the kernel density estimation (KDE) method to map each feature in the rainfall combination data to a continuous probability density function, so as to obtain the probability density distribution of rainfall events under different conditions. By constructing rainfall probability density data, the possibility of different combinations of rainfall features can be more intuitively seen, providing richer information for prediction. The rainfall probability density data is adjusted by the maximum entropy principle to obtain adjusted probability density data. The maximum entropy principle is a method to find the most uncertain (i.e., the maximum entropy) probability distribution under given constraints, which can ensure that the prediction results are as close to the actual situation as possible while avoiding overfitting. In the application of sponge cities, the project team can set some prior knowledge as constraints, such as the average rainfall intensity and duration in historical rainfall data, and then use the maximum entropy model to readjust the rainfall probability density data. The advantage of doing so is that the prediction results can be more robust and the errors caused by data noise can be reduced. Finally, the probability of occurrence of rainfall events in the target sponge city is predicted based on the adjusted probability density data and the climate data, and the probability distribution of future rainfall and the future measured rainfall are obtained. The work at this stage is to combine all the data obtained from the previous processing with the current and future climate data, and estimate the probability of occurrence of future rainfall events by building a suitable prediction model. For example, the project team can use a Bayesian network or a deep learning model, take the adjusted rainfall probability density data and the latest climate forecast data as input, and output the joint probability distribution of different rainfall intensities, durations, and interval periods in the future. In this way, not only can the probability of occurrence of future rainfall events be predicted, but also the corresponding rainfall can be estimated, providing scientific decision-making support for the construction and management of sponge cities. In summary, the process of predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, obtaining the probability distribution of future rainfall and the future rainfall measurement is a multi-step, multi-level complex task. From the application of the Markov chain Monte Carlo algorithm to the adjustment of the maximum entropy principle, each step is constantly optimizing and refining the prediction model, with the ultimate goal of providing more accurate and reliable rainfall prediction results to help cities better cope with waterlogging risks and achieve sustainable development.

[0093] In a specific embodiment, the target sponge city is spatially analyzed by a preset geographic information system to obtain a distribution map of waterlogging points, including:

[0094] Performing DEM analysis on the topographic data of the target sponge city through a preset geographic information system to obtain a topographic feature map; wherein the obtained topographic feature map includes slope, slope aspect and elevation;

[0095] Using a preset hydrological model, the surface runoff path in the topographic feature map is simulated to obtain a runoff simulation path map;

[0096] Searching the underground pipeline data in the target sponge city in the database, and performing network analysis on the underground pipeline data to identify the distribution and connection relationship of the underground pipelines, and obtaining underground pipeline distribution network data;

[0097] Using a network overlay analysis method, based on a runoff simulation path diagram and the underground pipeline distribution network data, the mutual influence between the surface runoff and the underground pipeline is evaluated to obtain a runoff influence diagram;

[0098] Classify and analyze the land use data of the target sponge city, identify the impact of different land use types on the surface runoff, and obtain a land use impact map;

[0099] A multi-criteria decision analysis method is used to obtain a distribution map of waterlogging points based on the runoff influence map and the land use influence map.

[0100] Specifically, the process of spatially analyzing the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points is a complex and delicate task, which involves multiple steps such as topographic analysis, hydrological simulation, underground pipeline network analysis, land use classification analysis, and multi-criteria decision analysis. This process aims to comprehensively evaluate the hydrological characteristics and infrastructure conditions within the city, so as to identify waterlogging points and provide a scientific basis for urban waterlogging risk management and sponge city construction. Specifically, it is first necessary to perform DEM (digital elevation model) analysis on the topographic data of the target sponge city through a preset geographic information system to obtain a terrain feature map. The terrain feature map here includes information such as slope, aspect, and elevation, which are the basis for evaluating the path of surface runoff and the direction of water flow. For example, in a specific sponge city construction project, the project team can use ArcGIS software to load the DEM data of the target city, and then run the terrain analysis tool to generate a terrain feature map including slope, aspect, and elevation. This map can clearly show the ups and downs and terrain direction of the city, providing an important geographical background for subsequent hydrological simulation. After obtaining the topographic feature map, the preset hydrological model is used to simulate the surface runoff path in the topographic feature map to obtain the runoff simulation path map. The choice of hydrological model depends on the characteristics of the study area and the available data types. Common models include SWAT (Soil and Water Assessment Tool), HEC-HMS (Hydrologic Engineering Center'sHydrologic Modeling System), etc. These models can simulate the surface runoff path and flow changes after rainfall based on factors such as topographic characteristics, soil type, and vegetation cover. For example, the project team can use the HEC-HMS model, input the slope and aspect data in the topographic feature map, as well as soil and vegetation information, set different rainfall scenarios, and run the model to obtain the surface runoff path map under different rainfall conditions. These path maps not only show the direction of the water flow, but also reflect the speed and flow of the water flow, which helps to identify potential waterlogging areas. At the same time, it is necessary to consult the underground pipeline data in the target sponge city in the database, and perform network analysis on these underground pipeline data to identify the distribution and connection relationship of the underground pipelines and obtain the underground pipeline distribution network data. Underground pipelines include rainwater pipes, sewage pipes, water supply pipes and other types. Their distribution and connection directly affect the discharge of surface runoff and the change of groundwater level. For example, the project team can access the city's municipal engineering database, export the GIS layer of underground pipelines, and then use the network analysis tools in ArcGIS to build a network model of underground pipelines.By analyzing the length, diameter, material and other properties of the pipelines, as well as the connection relationship between the pipelines, the key nodes and bottleneck sections in the pipeline network can be identified. This information is crucial for evaluating the drainage capacity of underground pipelines. Using the network overlay analysis method, the mutual influence of surface runoff and underground pipelines is evaluated based on the runoff simulation path map and the underground pipeline distribution network data, and the runoff impact map is obtained. Network overlay analysis refers to the overlay of different types of geographic information layers for spatial analysis to reveal the interaction between different elements. For example, the project team can overlay the runoff simulation path map with the underground pipeline distribution network data to analyze the intersection and adjacent areas of the surface runoff path and the underground pipeline. Through this analysis, it is possible to identify which underground pipelines may be damaged by the impact of surface runoff and which areas have insufficient drainage capacity for underground pipelines, resulting in ground waterlogging. This information will help prioritize the repair and transformation of underground pipelines and improve the drainage efficiency of the city. Classify and analyze the land use data of the target sponge city, identify the impact of different land use types on surface runoff, and obtain a land use impact map. Land use types include residential areas, commercial areas, industrial areas, green areas, water areas, etc. Different land use types have different effects on the generation and flow of surface runoff. For example, the project team can use remote sensing images and urban planning maps to classify land use types, and then use GIS software to calculate the area proportion and distribution characteristics of each land use type. Then, the impact of different land use types on surface runoff is evaluated by combining parameters such as the permeability of surface cover and surface roughness. For example, hardened ground (such as concrete and asphalt) will cause a rapid increase in surface runoff, while green land and wetlands can slow down surface runoff and increase the infiltration and evaporation of rainwater. Through this analysis, it is possible to identify which areas are prone to waterlogging due to unreasonable land use. Finally, based on the runoff influence map and land use influence map, the multi-criteria decision analysis method is used to comprehensively consider the mutual influence of surface runoff and underground pipelines and the influence of different land use types on surface runoff, and obtain a distribution map of waterlogging points. Multi-criteria decision analysis is a comprehensive evaluation method that can weigh multiple evaluation criteria to select the optimal solution. For example, the project team can set a series of evaluation indicators, such as surface runoff velocity, underground pipeline drainage capacity, land use type, etc., and then assign weights to each indicator, using methods such as the analytic hierarchy process (AHP) or fuzzy comprehensive evaluation method to calculate the comprehensive score of each area. According to the score, the city is divided into high-risk areas, medium-risk areas, and low-risk areas, and finally a distribution map of waterlogging points is generated. This map can intuitively show which areas in the city are most prone to waterlogging, providing clear guidance for urban planning and management. In summary, the process of spatially analyzing the target sponge city through a preset geographic information system and obtaining a distribution map of waterlogging points is a multi-step, multi-technical integrated process.From topographic analysis to hydrological simulation, to underground pipeline network analysis and land use classification analysis, each step is crucial and together constitutes a comprehensive urban waterlogging risk assessment framework. This framework not only provides scientific data support for the construction and management of sponge cities, but also provides valuable references for urban planning and environmental protection in other fields.

[0101] In a specific embodiment, the Bayesian network algorithm is used to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall to obtain a waterlogging risk map, including:

[0102] Based on the Bayesian network structure learning algorithm, the characteristic analysis of the distribution map of water-prone points is performed to determine the dependency relationship between nodes and obtain the network structure of water-prone points;

[0103] Through the preset Monte Carlo simulation technology, multiple rainfall scenarios and the corresponding water accumulation conditions of each rainfall scenario are generated based on the network structure of the water-prone points, the future calculated rainfall, and the probability distribution of future rainfall;

[0104] Conducting waterlogging risk assessment on each rainfall scenario and the corresponding waterlogging situation to obtain risk indicator data; wherein the risk indicator data includes flooding depth and waterlogging time;

[0105] Based on the risk indicator data, the target sponge city area is divided into different risk level categories to obtain a risk level classification result; wherein the risk level classification result includes a high risk category, a medium risk category and a low risk category;

[0106] The risk level classification results are marked on the distribution map of waterlogging points to obtain a waterlogging risk map; wherein the waterlogging risk map is the specific location and range of high-risk areas, medium-risk areas and low-risk areas.

[0107] Specifically, the process of using the Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future measured rainfall and the probability distribution of future rainfall to obtain the waterlogging risk map is a highly comprehensive and technical task, which involves multiple steps such as Bayesian network structure learning, Monte Carlo simulation, waterlogging risk assessment and risk level classification. The main purpose of this process is to comprehensively evaluate the urban waterlogging risk through advanced algorithms and models, and provide a scientific basis for urban waterlogging management and sponge city construction. Specifically, it is first necessary to perform feature analysis on the distribution map of waterlogging points based on the Bayesian network structure learning algorithm to determine the dependency relationship between nodes and obtain the network structure of waterlogging points. Bayesian network is a probabilistic graph model that can express the causal relationship and dependency relationship between variables and is particularly suitable for dealing with uncertainty problems. For example, in a sponge city construction project, the project team can use a structure learning algorithm, such as the K2 algorithm or the TAN (Tree Augmented Naive Bayes) algorithm, to perform feature analysis on each point in the distribution map of waterlogging points and identify which points have significant dependencies. In this way, a network structure that reflects the mutual influence between waterlogging points can be constructed, providing a basis for subsequent risk assessment. After obtaining the network structure of waterlogging points, the preset Monte Carlo simulation technology is used to generate multiple rainfall scenarios and the corresponding waterlogging conditions of each rainfall scenario based on the network structure of waterlogging points, the future measured rainfall, and the probability distribution of future rainfall. Monte Carlo simulation is a method of solving problems through random sampling, which is particularly suitable for dealing with complex probability distribution and uncertainty problems. For example, the project team can generate a series of random rainfall scenarios based on the network structure of waterlogging points, combined with the future measured rainfall and the probability distribution of future rainfall. Each rainfall scenario includes parameters such as the time, intensity, and duration of rainfall. Then, the hydrological model is used to simulate each rainfall scenario to calculate the waterlogging depth and waterlogging time of each waterlogging point under different rainfall scenarios. In this way, a large number of possible waterlogging conditions can be generated, providing rich data support for waterlogging risk assessment. Waterlogging risk assessment is performed on each rainfall scenario and the corresponding waterlogging conditions to obtain risk indicator data, which is one of the core steps in assessing urban waterlogging risks. Risk indicator data include flooding depth and waterlogging time, which can fully reflect the impact of urban flooding on the city. For example, the project team can set different risk thresholds, such as waterlogging depth exceeding 30 cm or waterlogging time exceeding 6 hours is considered high risk. Then, according to the waterlogging depth and waterlogging time under each rainfall scenario, the risk value of each waterlogging point is calculated. In this way, the risk indicator data of each waterlogging point under different rainfall scenarios can be obtained, providing a basis for the subsequent risk level classification.Based on the risk indicator data, the target sponge city area is divided into different risk level categories to obtain the risk level classification results. This process requires setting reasonable risk level classification standards to ensure the scientificity and practicality of the assessment results. For example, the project team can divide the risk level into high risk category, medium risk category and low risk category. The specific classification standard can be based on the statistical distribution of the risk indicator data, such as dividing the top 20% of the areas with the highest risk values ​​into high risk categories, the middle 60% of the areas into medium risk categories, and the remaining 20% ​​of the areas into low risk categories. In this way, the urban area can be divided into different risk levels to provide clear risk zoning information for urban managers. Finally, the risk level classification results are marked on the distribution map of waterlogging points to obtain a waterlogging risk map. The waterlogging risk map not only shows the specific location and range of high-risk areas, medium-risk areas and low-risk areas in the city, but also can intuitively reflect the overall distribution of urban waterlogging risks. For example, the project team can use different colors or symbols to mark the areas of each risk level on the waterlogging point distribution map, such as red for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. In this way, a detailed waterlogging risk map can be generated, providing intuitive data support for urban waterlogging management and sponge city construction. In summary, the process of using the Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, future measured rainfall, and the probability distribution of future rainfall to obtain a waterlogging risk map is a multi-step, multi-level complex task. From Bayesian network structure learning to Monte Carlo simulation, to waterlogging risk assessment and risk level classification, each step is constantly optimizing and refining the assessment model. The ultimate goal is to provide more accurate and reliable waterlogging risk assessment results to help cities better cope with waterlogging risks and achieve sustainable development.

[0108] In a specific embodiment, the layout optimization design of the sponge city is performed based on the waterlogging risk map using a preset multi-objective optimization algorithm to obtain an optimal configuration solution, including:

[0109] Extracting and analyzing the hydrogeological characteristics of the waterlogging risk area of ​​the sponge city based on the waterlogging risk map to obtain waterlogging hydrogeological parameters; wherein the waterlogging hydrogeological parameters include groundwater level changes corresponding to the permeability coefficient;

[0110] Constructing a permeability coefficient-groundwater level change curve based on the groundwater level change corresponding to the permeability coefficient;

[0111] Through a preset multi-objective optimization algorithm, a multi-objective optimization calculation is performed on the sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions;

[0112] Perform spatial cluster analysis on the candidate layout schemes of sponge facilities and obtain the clustering results of the layout schemes;

[0113] Through the preset game theory algorithm, the strategic game analysis is performed on the representative solutions of each cluster in the layout solution clustering results to obtain the game equilibrium layout solution set;

[0114] Under various rainfall scenarios, a neural network algorithm is used to optimize the layout design of the sponge city based on the game equilibrium layout solution set to obtain the optimal configuration solution.

[0115] Specifically, the process of optimizing the layout of the sponge city based on the waterlogging risk map using a preset multi-objective optimization algorithm to obtain the optimal configuration solution is a highly comprehensive and technical task, involving multiple steps such as hydrogeological feature extraction and analysis, multi-objective optimization calculation, spatial clustering analysis, strategy game analysis, and neural network optimization. The main purpose of this process is to optimize the layout of the sponge city through scientific methods and advanced algorithms to minimize the risk of waterlogging and improve the city's rainwater management capabilities. Specifically, it is first necessary to extract and analyze the hydrogeological features of the waterlogging risk area of ​​the sponge city based on the waterlogging risk map to obtain waterlogging hydrogeological parameters. These parameters include the change in groundwater level corresponding to the permeability coefficient, which are important indicators for evaluating the interaction between surface water and groundwater. For example, in a sponge city construction project, the project team can use GIS software, combined with the waterlogging risk map and geological survey data, to extract the geological profile and soil type distribution map of each waterlogging risk area. By analyzing these data, the permeability coefficient of different areas can be calculated, and the change in groundwater level can be monitored, so as to obtain detailed waterlogging hydrogeological parameters. After obtaining the hydrogeological parameters of waterlogging, a permeability coefficient-groundwater level change curve is constructed based on the groundwater level change corresponding to the permeability coefficient. This curve can intuitively show the relationship between the permeability coefficient and the groundwater level, providing important reference information for subsequent optimization design. For example, the project team can use statistical software, such as R language or Python, to perform regression analysis on the extracted permeability coefficient and groundwater level data to draw a permeability coefficient-groundwater level change curve. By analyzing this curve, it is possible to identify which areas have a greater impact on the permeability coefficient due to groundwater level changes. These areas may be areas with a higher risk of waterlogging and need to be optimized. Through a preset multi-objective optimization algorithm, a multi-objective optimization calculation is performed on the sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions. The multi-objective optimization algorithm can balance multiple objectives and find the optimal solution or Pareto frontier. For example, the project team can use multi-objective optimization algorithms such as NSGA-II (Non-dominated Sorting Genetic Algorithm II) or MOEA / D (Multiobjective Evolutionary Algorithm based on Decomposition), taking the permeability coefficient-groundwater level change curve as input, and considering other factors such as construction cost and environmental impact, to perform multi-objective optimization calculations. Through multiple iterations, the algorithm can generate a set of candidate solutions for sponge facility layout, which achieve a good balance between multiple objectives. Spatial clustering analysis is performed on the set of candidate solutions for sponge facility layout to obtain the clustering results of the layout solutions.Spatial clustering analysis can classify similar layout solutions into one category, thereby reducing the complexity of subsequent analysis. For example, the project team can use the K-means clustering algorithm or the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to perform clustering analysis on the candidate solutions generated by multi-objective optimization. By setting reasonable clustering parameters, the candidate solutions can be divided into several clusters, and the solutions in each cluster have similar layout characteristics. These clustering results provide a basis for subsequent strategic game analysis. Through the preset game theory algorithm, the representative solutions of each cluster in the layout solution clustering results are analyzed by strategic game analysis to obtain a set of game equilibrium layout solutions. Game theory is a mathematical method for analyzing the interaction and strategy selection between decision makers, and is particularly suitable for dealing with multi-agent optimization problems. For example, the project team can use game theory methods such as Nash Equilibrium or Multi-Agent Reinforcement Learning to perform strategic game analysis on the representative solutions in each cluster. By simulating the interaction between different subjects (such as urban management departments, residents, enterprises, etc.), one or more balanced layout schemes can be found, which achieve the optimal balance between the interests of various subjects. Finally, under the various rainfall scenarios, the neural network algorithm is used to optimize the layout design of the sponge city based on the game equilibrium layout scheme set to obtain the optimal configuration scheme. The neural network algorithm can handle complex nonlinear relationships and is particularly suitable for prediction and optimization tasks. For example, the project team can use a deep learning framework such as TensorFlow or PyTorch to build a neural network model, and the input data includes rainfall scenarios, game equilibrium layout scheme sets, and waterlogging risk maps. By training the model, the effects of various layout schemes under different rainfall scenarios can be predicted, so as to select a layout scheme that performs best under multiple rainfall scenarios. The optimal configuration scheme generated in the end can not only effectively reduce the risk of waterlogging, but also take into account economic and environmental friendliness, providing a scientific basis for the construction and management of sponge cities. In summary, the process of optimizing the layout design of sponge cities based on waterlogging risk maps using a preset multi-objective optimization algorithm to obtain the optimal configuration scheme is a multi-step, multi-level complex task. From the extraction of hydrogeological characteristics to multi-objective optimization calculations, and then to spatial clustering analysis and strategy game analysis, each step is constantly optimizing and refining the layout plan. The ultimate goal is to provide a more scientific and practical sponge city layout optimization plan to help cities better cope with urban flooding risks and achieve sustainable development.

[0116] In a specific embodiment, the preset multi-objective optimization algorithm is used to perform multi-objective optimization calculation on the target sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions, including:

[0117] Determine the variation law of the permeability coefficient and the groundwater level based on the permeability coefficient-groundwater level variation curve by using a preset multi-objective optimization algorithm;

[0118] Based on the above-mentioned variation law, a sensitivity analysis of the permeability coefficient was conducted to obtain the influence of the permeability coefficient on the groundwater level change under different rainfall scenarios;

[0119] Based on the impact degree and change law, the hydrological characteristics of the sponge city are analyzed to obtain the hydrological response mode and hydrological characteristic data in the waterlogging risk area;

[0120] Based on the hydrological response pattern and hydrological characteristic data, a multi-objective optimization calculation is performed on the sponge city to obtain a set of candidate sponge facility layout solutions.

[0121] Specifically, the process of performing multi-objective optimization calculation on the target sponge city based on the permeability coefficient-groundwater level change curve by using a preset multi-objective optimization algorithm to obtain a set of candidate sponge facility layout solutions is a highly comprehensive and technical task, which involves multiple steps such as determination of the permeability coefficient and groundwater level change law, sensitivity analysis, hydrological characteristics analysis, and multi-objective optimization calculation. The main purpose of this process is to optimize the layout of the sponge city through scientific methods and advanced algorithms to minimize the risk of waterlogging and improve the city's rainwater management capabilities. Specifically, first, it is necessary to determine the change law of the permeability coefficient and the groundwater level based on the permeability coefficient-groundwater level change curve by using a preset multi-objective optimization algorithm. The purpose of this step is to establish a mathematical relationship between the permeability coefficient and the groundwater level to provide a basis for subsequent analysis. For example, in a sponge city construction project, the project team can use statistical software, such as R language or Python, to perform regression analysis on historical data of the permeability coefficient and groundwater level, and fit a curve reflecting the relationship between the two. This curve can intuitively show how the permeability coefficient affects the change of the groundwater level, providing a basis for subsequent sensitivity analysis. After determining the variation law of permeability coefficient and groundwater level, a sensitivity analysis of permeability coefficient is conducted based on the variation law to obtain the degree of influence of permeability coefficient on groundwater level change under different rainfall scenarios. Sensitivity analysis is a method to evaluate the impact of different parameter changes on system output, which is particularly suitable for dealing with multivariate problems. For example, the project team can set different rainfall scenarios, such as light rain, moderate rain and heavy rain, and then observe the change of groundwater level by adjusting the value of permeability coefficient in each rainfall scenario. In this way, the sensitivity of permeability coefficient under different rainfall scenarios can be quantitatively evaluated, and the areas where the change of permeability coefficient has the most significant impact on groundwater level can be identified. These sensitivity analysis results provide important reference information for subsequent hydrological characteristic analysis. Based on the degree of influence and variation law, the hydrological characteristics of sponge city are analyzed to obtain the hydrological response pattern and hydrological characteristic data in the waterlogging risk area. Hydrological characteristic analysis refers to the identification of hydrological response patterns and characteristic parameters in different regions through comprehensive analysis of hydrological data. For example, the project team can use hydrological models, such as SWAT (Soil and Water Assessment Tool) or MIKE SHE (Integrated Hydrological Modelling System), combined with the results of sensitivity analysis, to conduct a detailed analysis of the hydrological characteristics of the waterlogging risk areas. By simulating surface runoff, groundwater flow, and soil moisture dynamics under different rainfall scenarios, the hydrological response patterns of various regions can be identified, such as fast response type, slow response type, etc.At the same time, key hydrological characteristic data such as runoff coefficient, groundwater recharge rate and soil saturation can also be extracted. These hydrological response patterns and characteristic data provide important input information for subsequent multi-objective optimization calculations. Based on the hydrological response pattern and hydrological characteristic data, the sponge city is multi-objective optimized to obtain a set of candidate sponge facility layout solutions. Multi-objective optimization algorithms can balance multiple objectives and find the optimal solution or Pareto front. For example, the project team can use multi-objective optimization algorithms such as NSGA-II (Non-dominated Sorting Genetic Algorithm II) or MOEA / D (Multiobjective Evolutionary Algorithm based on Decomposition) to take hydrological response patterns and characteristic data as input, and consider other factors such as construction cost, environmental impact and community acceptance to perform multi-objective optimization calculations. Through multiple iterations, the algorithm can generate a set of candidate sponge facility layout solutions that achieve a good balance between multiple objectives. Each candidate solution can not only effectively reduce the risk of waterlogging, but also take into account economic and environmental friendliness, providing urban managers with a variety of options. In summary, the process of obtaining a set of candidate sponge facility layout solutions by performing multi-objective optimization calculations on the target sponge city based on the permeability coefficient-groundwater level change curve through a preset multi-objective optimization algorithm is a multi-step, multi-level complex task. From determining the variation law of permeability coefficient and groundwater level to sensitivity analysis, and then to hydrological characteristics analysis and multi-objective optimization calculations, each step is constantly optimizing and refining the layout plan. The ultimate goal is to provide a more scientific and practical sponge city layout optimization plan to help cities better cope with waterlogging risks and achieve sustainable development. Through this process, the project team can provide strong technical support and decision-making basis for the construction and management of sponge cities.

[0122] The above describes the sponge city design optimization method based on rainfall measurement in the embodiment of the present invention. The following describes the sponge city design optimization system based on rainfall measurement in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a sponge city design optimization system based on rainfall measurement includes:

[0123] The first analysis module 21 is used to obtain historical rainfall data and climate data of the target sponge city, and perform frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data;

[0124] A prediction module 22 is used to predict the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtain the probability distribution of future rainfall and the future estimated rainfall;

[0125] The second analysis module 23 is used to perform spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points;

[0126] The evaluation module 24 is used to use a Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, and obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas, and low-risk areas;

[0127] The design module 25 is used to utilize a preset multi-objective optimization algorithm to optimize the layout design of the target sponge city based on the waterlogging risk map to obtain an optimal configuration solution.

[0128] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0129] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0130] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0131] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0132] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0133] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0134] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A sponge city design optimization method based on rainfall measurement, characterized in that: The following steps are involved: Obtain historical rainfall data and climate data of the target sponge city, and perform frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data; Predicting the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtaining the probability distribution of future rainfall and the future estimated rainfall; Perform spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points; Using a Bayesian network algorithm, based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, the waterlogging risk level of each area in the target sponge city is evaluated to obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas, and low-risk areas; Using a preset multi-objective optimization algorithm, the target sponge city is optimized and designed based on the waterlogging risk map to obtain an optimal configuration solution; Performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data includes: Obtaining original historical rainfall data of multiple meteorological stations of the target sponge city, and cleaning the original historical rainfall data to remove outliers and missing values, to obtain historical rainfall data; Performing rainfall trend analysis on the historical rainfall data to obtain rainfall trend data; Performing multi-scale wavelet transform on the rainfall trend data to extract rainfall characteristics at different time scales to obtain multi-scale rainfall characteristic data; Using extreme value theory, based on the rainfall trend data and multi-scale rainfall characteristic data, the probability distribution of extreme rainfall events is calculated to obtain the probability distribution of extreme rainfall events; wherein the probability distribution of extreme rainfall events is the probability distribution of the maximum rainfall amount and the longest duration; Obtaining rainfall analysis data based on the probability distribution of the extreme rainfall event, the multi-scale rainfall characteristic data and the rainfall trend data; wherein the rainfall analysis data includes rainfall intensity, rainfall duration and rainfall interval period; The prediction of the probability of occurrence of a rainfall event in the target sponge city based on the rainfall analysis data and the climate data to obtain the probability distribution of future rainfall and the future estimated rainfall includes: Randomly sampling the rainfall intensity based on a Markov chain Monte Carlo algorithm to determine the transfer path probability of rainfall of different intensities; Performing state hidden analysis and mining on the rainfall duration to obtain hidden duration state probability distribution; The conditional random field algorithm is used to extract the correlation features of the rainfall interval period, so as to construct the conditional probability relationship between the rainfall interval period, rainfall intensity and duration, and obtain the conditional probability relationship between the interval period; Combining the data of the transfer path probability, the hidden duration state probability distribution and the interval period conditional probability relationship to obtain rainfall combination data; Constructing rainfall probability density data based on the rainfall combination data; The probability distribution of the rainfall probability density data is adjusted by the maximum entropy principle to obtain adjusted probability density data; Predicting the probability of occurrence of a rainfall event in the target sponge city based on the adjusted probability density data and the climate data, and obtaining a probability distribution of future rainfall and a future estimated rainfall; The target sponge city is spatially analyzed by a preset geographic information system to obtain a distribution map of waterlogging points, including: Performing DEM analysis on the topographic data of the target sponge city through a preset geographic information system to obtain a topographic feature map; wherein the obtained topographic feature map includes slope, slope aspect and elevation; Using a preset hydrological model, the surface runoff path in the topographic feature map is simulated to obtain a runoff simulation path map; Searching the underground pipeline data in the target sponge city in the database, and performing network analysis on the underground pipeline data to identify the distribution and connection relationship of the underground pipelines, and obtaining underground pipeline distribution network data; Using a network overlay analysis method, based on a runoff simulation path diagram and the underground pipeline distribution network data, the mutual influence between the surface runoff and the underground pipeline is evaluated to obtain a runoff influence diagram; Classify and analyze the land use data of the target sponge city, identify the impact of different land use types on the surface runoff, and obtain a land use impact map; A multi-criteria decision analysis method is used to obtain a distribution map of waterlogging points based on the runoff influence map and the land use influence map.

2. The sponge city design optimization method based on rainfall calculation according to claim 1 is characterized in that: The Bayesian network algorithm is used to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, to obtain a waterlogging risk map, including: Based on the Bayesian network structure learning algorithm, the characteristic analysis of the distribution map of water-prone points is performed to determine the dependency relationship between nodes and obtain the network structure of water-prone points; Through the preset Monte Carlo simulation technology, multiple rainfall scenarios and the corresponding water accumulation conditions of each rainfall scenario are generated based on the network structure of the water-prone points, the future calculated rainfall, and the probability distribution of future rainfall; Conducting waterlogging risk assessment on each rainfall scenario and the corresponding waterlogging situation to obtain risk indicator data; wherein the risk indicator data includes flooding depth and waterlogging time; Based on the risk indicator data, the target sponge city area is divided into different risk level categories to obtain a risk level classification result; wherein the risk level classification result includes a high risk category, a medium risk category and a low risk category; The risk level classification results are marked on the distribution map of waterlogging points to obtain a waterlogging risk map; wherein the waterlogging risk map is the specific location and range of high-risk areas, medium-risk areas and low-risk areas.

3. The sponge city design optimization method based on rainfall calculation according to claim 2 is characterized in that: The method of using a preset multi-objective optimization algorithm to optimize the layout of the sponge city based on the waterlogging risk map to obtain an optimal configuration solution includes: Extracting and analyzing the hydrogeological characteristics of the waterlogging risk area of ​​the sponge city based on the waterlogging risk map to obtain waterlogging hydrogeological parameters; wherein the waterlogging hydrogeological parameters include groundwater level changes corresponding to the permeability coefficient; Constructing a permeability coefficient-groundwater level change curve based on the groundwater level change corresponding to the permeability coefficient; Through a preset multi-objective optimization algorithm, a multi-objective optimization calculation is performed on the sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions; Perform spatial cluster analysis on the candidate layout schemes of sponge facilities and obtain the clustering results of the layout schemes; Through the preset game theory algorithm, the strategic game analysis is performed on the representative solutions of each cluster in the layout solution clustering results to obtain the game equilibrium layout solution set; Under various rainfall scenarios, a neural network algorithm is used to optimize the layout design of the sponge city based on the game equilibrium layout solution set to obtain the optimal configuration solution.

4. The sponge city design optimization method based on rainfall calculation according to claim 3 is characterized in that: The preset multi-objective optimization algorithm is used to perform multi-objective optimization calculation on the target sponge city based on the permeability coefficient-groundwater level change curve to obtain a set of candidate sponge facility layout solutions, including: Determine the variation law of the permeability coefficient and the groundwater level based on the permeability coefficient-groundwater level variation curve by using a preset multi-objective optimization algorithm; Based on the above-mentioned variation law, a sensitivity analysis of the permeability coefficient was conducted to obtain the influence of the permeability coefficient on the groundwater level change under different rainfall scenarios; Based on the impact degree and change law, the hydrological characteristics of the sponge city are analyzed to obtain the hydrological response mode and hydrological characteristic data in the waterlogging risk area; Based on the hydrological response pattern and hydrological characteristic data, a multi-objective optimization calculation is performed on the sponge city to obtain a set of candidate sponge facility layout solutions.

5. A sponge city design optimization system based on rainfall measurement, characterized in that: include: The first analysis module is used to obtain historical rainfall data and climate data of the target sponge city, and perform frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data; A prediction module, used to predict the probability of occurrence of rainfall events in the target sponge city based on the rainfall analysis data and the climate data, and obtain the probability distribution of future rainfall and the future estimated rainfall; The second analysis module is used to perform spatial analysis on the target sponge city through a preset geographic information system to obtain a distribution map of waterlogging points; An evaluation module is used to use a Bayesian network algorithm to evaluate the waterlogging risk level of each area in the target sponge city based on the distribution map of waterlogging points, the future calculated rainfall, and the probability distribution of future rainfall, so as to obtain a waterlogging risk map; wherein the waterlogging risk map includes high-risk areas, medium-risk areas, and low-risk areas; A design module, for optimizing the layout of the target sponge city based on the waterlogging risk map using a preset multi-objective optimization algorithm to obtain an optimal configuration solution; Performing frequency distribution analysis on the historical rainfall data to obtain rainfall analysis data includes: Obtaining original historical rainfall data of multiple meteorological stations of the target sponge city, and cleaning the original historical rainfall data to remove outliers and missing values, to obtain historical rainfall data; Performing rainfall trend analysis on the historical rainfall data to obtain rainfall trend data; Performing multi-scale wavelet transform on the rainfall trend data to extract rainfall characteristics at different time scales to obtain multi-scale rainfall characteristic data; Using extreme value theory, based on the rainfall trend data and multi-scale rainfall characteristic data, the probability distribution of extreme rainfall events is calculated to obtain the probability distribution of extreme rainfall events; wherein the probability distribution of extreme rainfall events is the probability distribution of the maximum rainfall amount and the longest duration; Obtaining rainfall analysis data based on the probability distribution of the extreme rainfall event, the multi-scale rainfall characteristic data and the rainfall trend data; wherein the rainfall analysis data includes rainfall intensity, rainfall duration and rainfall interval period; The prediction of the probability of occurrence of a rainfall event in the target sponge city based on the rainfall analysis data and the climate data to obtain the probability distribution of future rainfall and the future estimated rainfall includes: Randomly sampling the rainfall intensity based on a Markov chain Monte Carlo algorithm to determine the transfer path probability of rainfall of different intensities; Performing state hidden analysis and mining on the rainfall duration to obtain hidden duration state probability distribution; The conditional random field algorithm is used to extract the correlation features of the rainfall interval period, so as to construct the conditional probability relationship between the rainfall interval period, rainfall intensity and duration, and obtain the conditional probability relationship between the interval period; Combining the data of the transfer path probability, the hidden duration state probability distribution and the interval period conditional probability relationship to obtain rainfall combination data; Constructing rainfall probability density data based on the rainfall combination data; The probability distribution of the rainfall probability density data is adjusted by the maximum entropy principle to obtain adjusted probability density data; Predicting the probability of occurrence of a rainfall event in the target sponge city based on the adjusted probability density data and the climate data, and obtaining a probability distribution of future rainfall and a future estimated rainfall; The target sponge city is spatially analyzed by a preset geographic information system to obtain a distribution map of waterlogging points, including: Performing DEM analysis on the topographic data of the target sponge city through a preset geographic information system to obtain a topographic feature map; wherein the obtained topographic feature map includes slope, slope aspect and elevation; Using a preset hydrological model, the surface runoff path in the topographic feature map is simulated to obtain a runoff simulation path map; Searching the underground pipeline data in the target sponge city in the database, and performing network analysis on the underground pipeline data to identify the distribution and connection relationship of the underground pipelines, and obtaining underground pipeline distribution network data; Using a network overlay analysis method, based on a runoff simulation path diagram and the underground pipeline distribution network data, the mutual influence between the surface runoff and the underground pipeline is evaluated to obtain a runoff influence diagram; Classify and analyze the land use data of the target sponge city, identify the impact of different land use types on the surface runoff, and obtain a land use impact map; A multi-criteria decision analysis method is used to obtain a distribution map of waterlogging points based on the runoff influence map and the land use influence map.

6. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images