A flood simulation and prediction system based on GIS data

Abstract

The present invention relates to the field of geographic information system technology, and specifically to a flood simulation prediction system based on GIS data. The system includes: a data integration module collects climate and geographic information at the basin scale, regional scale and global scale, performs data verification and format standardization, integrates into a unified data set, extracts multi-regional climate trends and geographic features, constructs indexes, and generates a geographic climate database. In the present invention, a geographic climate database is constructed by integrating data of various scales and performing standardized processing, improving data consistency and availability, finely adjusting model parameters, optimizing model structure according to regional specific climate and geographic features, and enhancing the adaptability and accuracy of the prediction model. In addition, state transition data is used to calculate future flood risks, provide dynamic risk assessment, and update flood probability and intensity information in real time, making flood risk management more forward-looking and practical.

Description

Technical Field

[0001] The invention relates to the technical field of geographic information systems, and in particular to a flood simulation prediction system based on GIS data. Background Art

[0002] Geographic Information System (GIS) is an integrated technology for collecting, storing, querying, analyzing and displaying geospatial data. This technology involves the processing of geographic data to support spatial analysis and decision-making processes. GIS enables users to identify and analyze spatial patterns and relationships on the earth's surface. This technology is widely used in urban planning, environmental management, resource management, public safety, transportation and logistics. GIS technology not only provides map-making tools, but also strengthens the ability of model building and spatial data analysis, making it a key technical means to solve complex geographic problems.

[0003] Among them, the flood simulation and prediction system based on GIS data refers to a system that uses GIS technology to simulate and predict the possibility and impact of floods. This system integrates meteorological, topographic, hydrological and other relevant geographic data, and uses model algorithms to predict possible floods in specific areas and areas that may be affected. The main purpose of this system is to provide accurate flood prediction information to government departments, disaster response agencies and public safety organizations in order to formulate effective disaster prevention and mitigation measures and emergency response plans. Through such a prediction system, the efficiency and effectiveness of responding to flood disasters can be greatly improved, reducing casualties and economic losses.

[0004] Existing technologies are deficient in data integration and model adaptability. Common GIS systems are difficult to effectively integrate climate and geographic data of different scales and sources, resulting in insufficient data utilization and limited coverage and accuracy of prediction results. In addition, fixed model parameter settings cannot flexibly adapt to environmental changes in different regions, reducing the applicability of the model in a changing geographical environment and increasing the uncertainty of flood prediction and the difficulty of risk management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a flood simulation prediction system based on GIS data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A flood simulation prediction system based on GIS data includes:

[0007] The data integration module collects climate and geographic information at the basin, regional and global scales, performs data verification and format standardization, integrates them into a unified data set, extracts multi-regional climate trends and geographic features, builds indexes, and generates a geographic climate database;

[0008] The model self-matching module uses the data in the geographic climate database to adjust the model parameters, including the width of the kernel function and the number of layers of latent variables, configures the model structure according to the climate trend and geographic characteristics of the target area, and generates a flood probability distribution model;

[0009] The flood trend prediction module extracts state transition data from the flood probability distribution model, calculates the probability of occurrence of future states, analyzes the risks under differentiated flood-inducing conditions, predicts the possibility and intensity of future flood events, and generates future flood event prediction results;

[0010] The real-time response display module combines the prediction results of future flood events and performs data visualization on the GIS platform. It combines the prediction results with the existing geographic information system through map layer overlay, updates the flood probability and intensity information in real time, and generates a real-time flood risk map.

[0011] The geographic climate database specifically includes multi-regional climate trends, geographic features, and indexes; the flood probability distribution model includes model parameters and model structure; the future flood event prediction results specifically refer to flood occurrence probability and flood intensity prediction; the real-time flood risk map includes risk update display, probability layer, and intensity layer.

[0012] As a further solution of the present invention, the steps of acquiring the geographic climate database are specifically as follows:

[0013] Collect climate and geographic information at the basin, regional and global scales, integrate data from different geographical locations and climate systems, and obtain multi-source geographic climate datasets;

[0014] Verifying and formatting the multi-source geographic climate dataset, and generating a standardized geographic climate dataset through cleaning and conversion operations;

[0015] Key climate trends and geographic features are extracted from the standardized geoclimatic datasets to calculate climate change indicators at multiple scales using the formula:

[0016] ;

[0017] Generate climate change trend indices;

[0018] in, Represents the calculated climate change trend index, indicating the degree of climate change in the target area. Representative The climate or geographical characteristic value of each data point is expressed as the climate data of a certain area at a certain point in time, including temperature and rainfall. Representative The weight of a data point reflects the importance or influence of the data point in the overall analysis. is the total number of data points, indicating the number of geographical or climate data points involved in the calculation. is the normalization factor of the weight, used to adjust each weight size;

[0019] The climate change trend index is used to construct an index of climate and geographical features, and a geographical climate database is generated through association analysis and index construction processes.

[0020] As a further solution of the present invention, the steps for obtaining the width of the kernel function and the number of layers of the latent variables are specifically as follows:

[0021] Analyze the climate data of the target area in the geographic climate database, identify key climate variables, including temperature and rainfall frequency, and generate climate variable analysis results for the target area;

[0022] Based on the analysis results of climate variables in the target area, the adjustment needs of kernel functions and latent variables are evaluated using the formula:

[0023] ;

[0024] Adjust the model parameters to obtain the width of the kernel function and the number of layers of hidden variables;

[0025] in, represents the width of the adjusted kernel function, reflecting the sensitivity of the model to climate change in the target area. represents the adjustment parameter of the kernel function width, which is used to reflect the volatility of climate variables in the target area. The influence factor representing the number of hidden variable layers is used to measure the impact of the differentiation level on the model. is the mathematical constant pi.

[0026] As a further solution of the present invention, the steps of obtaining the flood probability distribution model are specifically as follows:

[0027] Using the width of the kernel function and the number of layers of latent variables, the basic structure of the flood prediction model is configured to ensure that the model parameters match the geographical climate characteristics and generate a preliminary flood prediction model structure;

[0028] The preliminary flood prediction model structure is simulated and verified using the formula:

[0029] ;

[0030] Simulate the probability of flood occurrence under differentiated climate conditions and obtain a flood probability distribution model;

[0031] in, Represents the occurrence of flood events. Represents the input climate dataset, including key climate variables such as temperature and rainfall, It is the average occurrence condition of flood events predicted based on climate data, reflecting the climate state of flood occurrence at the average level. represents the standard deviation of the forecast data, which is used to quantify the variability and uncertainty of flood conditions. is a normalizing constant that ensures that the sum of the probability of flood occurrence in all cases is 1.

[0032] As a further solution of the present invention, the steps for obtaining the prediction results of future flood events are specifically as follows:

[0033] By analyzing the flood probability distribution model, key state variables are identified, including topography, climate change frequency and regional climate factors, and key state variable analysis results are obtained;

[0034] The key state variable analysis results are used to construct a conditional probability calculation model to calculate the probability of multiple future states occurring under given current conditions, using the formula:

[0035] ;

[0036] Generate multiple future state probability data;

[0037] in, Represents the state in the future time period, indicating multiple future situations under given current conditions. Represents the current state, which is the current state referenced when calculating conditional probability. Representation status The energy is used to evaluate the possibility of a state occurring. The lower the energy, the higher the possibility of the state occurring. The denominator of the formula It is to perform exponential decay summation on the energy of all states to normalize the probability value to ensure that the sum of the probabilities of all states is 1;

[0038] The plurality of future state probability data are evaluated, a risk level under each future state is determined, and a probability of occurrence of the future state is generated.

[0039] As a further solution of the present invention, the steps for obtaining the prediction results of future flood events are specifically as follows:

[0040] Comprehensively analyze the future state probability data and regional climate factors, identify the key influencing factors of rainfall intensity and river water level changes, and generate flood influencing factor analysis results;

[0041] Based on the analysis results of flood influencing factors, a composite mathematical model is used to calculate the possibility and intensity of flood events under multiple factors, using the formula:

[0042] ;

[0043] Obtain flood event probability and intensity calculation data;

[0044] in, It is The value of a condition, such as rainfall or river levels, affects the likelihood and severity of floods. is the weight of the condition, indicating the relative importance of the condition in the flood prediction model. The condition with a high weight has a greater impact on the prediction result. It is a condition The standard deviation is used to measure the degree of variation of conditional data and reflect the uncertainty under differentiated conditions. is a normalization factor, which is used to ensure that the sum of the flood probability under all conditions is 1, thus ensuring the normalization of the probability distribution;

[0045] The flood event probability and intensity calculation data are verified and the model is optimized to ensure that the model reflects the impact of actual climate change and geographical factors and to generate future flood event prediction results.

[0046] As a further solution of the present invention, the steps of obtaining the real-time flood risk map are specifically as follows:

[0047] Integrate the forecast results of future flood events into the geographic information system to ensure the spatial location of each data point, associate the flood risk data with geographic coordinates, and generate a GIS data layer;

[0048] The GIS data layer is used on the GIS platform through layer overlay technology, combined with the existing functions of map services, to overlay the flood prediction results on the actual map using the formula:

[0049] ;

[0050] Generate preliminary risk map views;

[0051] in, Represented in geographic coordinates The flood risk value on Representative The transparency of the layer, adjusts the visibility of the layer in the visual display, Indicates Layer at coordinates The flood risk data value provides information on the flood intensity of the location. is the total number of map layers;

[0052] The preliminary risk map view is linked to the real-time meteorological update system to automatically update the flood risk level to reflect the current flood probability and intensity and publish a real-time flood risk map.

[0053] Compared with the prior art, the advantages and positive effects of the present invention are:

[0054] In the present invention, a geographic climate database is constructed by integrating data of various scales and performing standardized processing to improve data consistency and availability. The model parameters are finely adjusted, and the model structure is optimized according to the specific climate and geographical characteristics of the region to enhance the adaptability and accuracy of the prediction model. In addition, the state transition data is used to calculate future flood risks, provide dynamic risk assessment, and update flood probability and intensity information in real time, making flood risk management more forward-looking and practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a system flow chart of the present invention;

[0056] Figure 2 A flow chart of the steps for obtaining the geographic climate database of the present invention;

[0057] Figure 3 A flowchart of the steps for obtaining the width of the kernel function and the number of layers of latent variables of the present invention;

[0058] Figure 4 A flow chart of the steps for obtaining the flood probability distribution model of the present invention;

[0059] Figure 5 A flow chart of the steps for obtaining the probability of occurrence of the future state of the present invention;

[0060] Figure 6 A flow chart of the steps for obtaining the prediction results of future flood events of the present invention;

[0061] Figure 7 This is a flow chart of the steps for obtaining a real-time flood risk map according to the present invention. DETAILED DESCRIPTION

[0062] 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.

[0063] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0064] Embodiment 1

[0065] See also Figure 1 , a flood simulation and prediction system based on GIS data includes:

[0066] The data integration module collects climate and geographic information at the basin, regional and global scales, performs data verification and format standardization, integrates them into a unified data set, extracts multi-regional climate trends and geographic features, builds indexes, and generates a geographic climate database;

[0067] The model self-matching module uses data from the geographic climate database to adjust model parameters, including the width of the kernel function and the number of layers of latent variables, configures the model structure according to the climate trends and geographic characteristics of the target area, and generates a flood probability distribution model;

[0068] The flood trend prediction module extracts state transition data from the flood probability distribution model, calculates the probability of future state occurrence, analyzes the risks under differentiated flood-inducing conditions, predicts the possibility and intensity of future flood events, and generates future flood event prediction results;

[0069] The real-time response display module combines the prediction results of future flood events to visualize the data on the GIS platform, combines the prediction results with the existing geographic information system through map layer overlay, updates the flood probability and intensity information in real time, and generates a real-time flood risk map.

[0070] The geographic climate database specifically includes multi-regional climate trends, geographic features, and indexes. The flood probability distribution model includes model parameters and model structure. The prediction results of future flood events specifically refer to the probability of flood occurrence and flood intensity prediction. The real-time flood risk map includes risk update display, probability layer, and intensity layer.

[0071] See also Figure 2 , the specific steps for obtaining the geographic climate database are:

[0072] Collect climate and geographic information at the basin, regional and global scales, integrate data from different geographical locations and climate systems, and obtain multi-source geographic climate datasets;

[0073] Collecting climate and geographic information at the basin scale, regional scale, and global scale is a key step in the diversification of data collection. Integrating climate and geographic data from multiple locations is the basis for building a comprehensive database. The temperature, humidity, wind speed, and rainfall data provided by multiple observation stations are standardized in a unified format, including synchronization of timestamps and normalization of values, to ensure information consistency and data availability. Spatial and temporal data alignment is performed through geographic information system technology and climate models, and a preliminary data set including all necessary geographic tags and climate characteristics is integrated. The data set will support subsequent trend analysis and feature extraction to obtain a multi-source geographic climate data set.

[0074] Verify and standardize the formats of multi-source geographic climate datasets, and generate standardized geographic climate datasets through cleaning and conversion operations;

[0075] Data validation and format standardization are performed to ensure the accuracy and availability of the data. Through the data quality control process, including outlier detection, missing value processing, and data type conversion, statistical analysis methods are used to evaluate the completeness and representativeness of the data set. Batch data are automatically processed through programming scripts to ensure that each data meets the predetermined quality standards. Regular expressions are used for format verification, and machine learning algorithms are used to detect sample anomalies to ensure the consistency and accuracy of the data set, generating a standardized geographic climate data set that meets research needs and is easy to analyze.

[0076] Extract key climate trends and geographic features from standardized geographic climate datasets and calculate climate change indicators at multiple scales using the formula:

[0077] ;

[0078] Generate climate change trend indices;

[0079] in, Represents the calculated climate change trend index, indicating the degree of climate change in the target area. Representative The climate or geographical characteristic value of each data point is expressed as the climate data of a certain area at a certain point in time, including temperature and rainfall. Representative The weight of a data point reflects the importance or influence of the data point in the overall analysis. is the total number of data points, indicating the number of geographical or climate data points involved in the calculation. is the normalization factor of the weight, used to adjust each weight size;

[0080] formula:

[0081] ;

[0082] The benefit of the formula is that it strengthens the impact of individual data points in the overall trend through weight adjustment, reflects the criticality of differentiated data points in geographic climate analysis, and improves the accuracy and usefulness of the results.

[0083] Detailed explanation of the formula and the process of formula calculation and derivation:

[0084] Refer to a simplified example to set the climate characteristic values ​​with three data points They are 15°C, 20°C, and 25°C, and the corresponding weights is 0.5, 1.0, 0.5. First, calculate the square root of the sum of the squares of the weights, that is

[0085] ;

[0086] Then, calculate the weighted average, that is,

[0087] ;

[0088] So, for this set of data, It is about 24.49, which means that after referring to the weight, the average temperature of the overall trend is about 24.49°C.

[0089] The results show that through this weighted approach, a comprehensive climate indicator that refers to the key values ​​of multiple data points can be obtained, providing a quantitative method for climate change trend analysis.

[0090] The climate change trend index is used to construct an index of climate and geographical characteristics, and a geographic climate database is generated through association analysis and index construction process.

[0091] Use the Climate Change Trend Index to construct an index of climate and geographical characteristics. Through multidimensional data analysis technology, integrate climate change data at multiple scales. Use time series analysis and pattern recognition methods to identify long-term and short-term climate change trends. Use geographic information systems to map and visualize data to make the geographical and climate relationships between data clearer. Through data clustering and regression analysis, establish a comprehensive database of a wide range of climate variables to provide support for climate research and environmental policy making, and generate a geographic climate database.

[0092] See also Figure 3 , the steps to obtain the width of the kernel function and the number of layers of hidden variables are as follows:

[0093] Analyze climate data of the target area in the geographic climate database, identify key climate variables, including temperature and rainfall frequency, and generate analysis results of climate variables in the target area;

[0094] In analyzing the climate data of the target area, by obtaining the key climate variables of temperature and rainfall frequency extracted from the geographic climate database, the data is first verified and cleaned to ensure that the data set used reflects the current climate patterns and geographical changes. This process includes data outlier detection and missing value processing. The techniques used include time series analysis and multivariate regression analysis to ensure that each data point is highly accurate and representative. Subsequently, the data is used in the model to evaluate and adjust the kernel function width and the number of layers of latent variables in the flood prediction model. By comparing the output of the model under differentiated parameter settings, the model configuration with the most current climate trend is found. This process ensures that the model parameters can match the climate characteristics of the target area and can effectively predict potential climate risks.

[0095] Based on the analysis results of climate variables in the target area, the adjustment needs of kernel functions and latent variables are evaluated using the formula:

[0096] ;

[0097] Adjust the model parameters to obtain the width of the kernel function and the number of layers of hidden variables;

[0098] in, represents the width of the adjusted kernel function, reflecting the sensitivity of the model to climate change in the target area. represents the adjustment parameter of the kernel function width, which is used to reflect the volatility of climate variables in the target area. The influence factor representing the number of hidden variable layers is used to measure the impact of the differentiation level on the model. is the mathematical constant pi.

[0099] formula:

[0100] ;

[0101] The benefit of the formula is that by adjusting the width of the kernel function and the number of hidden variable layers The impact of climate change can be flexibly adjusted to match the model with different regions, thus enhancing the adaptability and prediction accuracy of the model.

[0102] Detailed explanation of the formula and the process of formula calculation: Setting the width of the kernel function , the influence of the number of hidden variable layers , substitute these values ​​into the formula to calculate:

[0103] 1. Calculate the denominator ;

[0104] 2. Calculate the exponential part ;

[0105] 3. Calculate exponential function (almost zero);

[0106] 4. Calculate the entire formula ;

[0107] The results show that for a given and The increase in kernel function width makes the function value almost zero, which reflects that the kernel function tends to zero at a larger number of layers or width, indicating that the kernel function is very sensitive and needs to be adjusted according to the actual data. and value to achieve the best model effect.

[0108] See also Figure 4 , the specific steps for obtaining the flood probability distribution model are:

[0109] The basic structure of the flood prediction model is configured using the width of the kernel function and the number of layers of latent variables to ensure that the model parameters match the geographical and climatic characteristics and generate a preliminary flood prediction model structure;

[0110] Before using the width of the kernel function and the number of layers of latent variables for model configuration, it is first necessary to analyze the climate data of the target area, including rainfall and temperature fluctuation data. The data is provided by the meteorological station. After standardization, it can be used to evaluate and adjust the kernel function width and the number of layers of latent variables of the model. The parameters directly affect the accuracy and sensitivity of the model in flood probability prediction. Through a systematic analysis of key climate variables, the model parameters that need to be adjusted are determined. The adjustment of the parameters is based on the coefficient of variation and distribution characteristics of the actual climate data to ensure that the prediction model can reflect the actual climate conditions. The generated preliminary flood prediction model structure will be used for simulation and verification.

[0111] The preliminary flood forecast model structure was simulated and verified using the formula:

[0112] ;

[0113] Simulate the probability of flood occurrence under differentiated climate conditions and obtain a flood probability distribution model;

[0114] in, Represents the occurrence of flood events. Represents the input climate dataset, including key climate variables such as temperature and rainfall, It is the average occurrence condition of flood events predicted based on climate data, reflecting the climate state of flood occurrence at the average level. represents the standard deviation of the forecast data, which is used to quantify the variability and uncertainty of flood conditions. is a normalizing constant that ensures that the sum of the probability of flood occurrence in all cases is 1.

[0115] formula:

[0116] ;

[0117] The benefit of the formula is that the model parameters are adjusted by matching and , which can flexibly match the climate characteristics of differentiated regions, thereby improving the accuracy and reliability of flood forecasting.

[0118] Detailed explanation of the formula and the process of formula calculation and derivation:

[0119] The average annual precipitation in a region is 1000 mm, and the standard deviation is 250 mm, that is, , . Set the probability of flood occurrence to be calculated when the precipitation is 1200mm, and substitute it into the formula to get:

[0120]

[0121]

[0122]

[0123]

[0124]

[0125] The results show that under given climatic conditions, the probability of a flood with a precipitation of 1200 mm is about 0.2048%. This numerical result shows that the model can provide flood risk assessment for the region based on current climate data.

[0126] See also Figure 5 , the steps to obtain the probability of future state occurrence are as follows:

[0127] By analyzing the flood probability distribution model, key state variables are identified, including topography, climate change frequency and regional climate factors, and key state variable analysis results are obtained;

[0128] By analyzing the flood probability distribution model, key state variables are identified, including topography, climate change frequency and regional climate factors. This process requires first obtaining preliminary data through climate models and terrain databases, and then using R or Python for data processing, including data cleaning, sorting and preliminary trend analysis. Through these steps, it is possible to determine which factors have a significant impact on the occurrence of floods, which is crucial for subsequent model adjustments. Then, multivariate analysis of the data is performed, using regression analysis or machine learning methods to find out the interactions and influence of multiple factors. This process not only provides direct information on key state variables, but also reveals how these variables jointly affect the mechanism of flood occurrence, thereby generating key state variable analysis results. This result provides the necessary input variables for the flood prediction model, enhancing the model's predictive ability and adaptability.

[0129] The key state variable analysis results are used to construct a conditional probability calculation model to calculate the probability of a state occurring under given current conditions using the formula:

[0130] ;

[0131] Generate state probability data;

[0132] in, Represents the state in the future time period, indicating multiple future situations under given current conditions. Represents the current state, which is the current state referenced when calculating conditional probability. Representation status The energy is used to evaluate the possibility of a state occurring. The lower the energy, the higher the possibility of the state occurring. The denominator of the formula It is to perform exponential decay summation on the energy of all states to normalize the probability value to ensure that the sum of the probabilities of all states is 1;

[0133] formula:

[0134] ;

[0135] The benefit of the formula is that it can predict the probability of multiple future states based on the current state, which has practical application value for flood prevention and preparedness, including providing data support in formulating emergency evacuation plans or insurance pricing.

[0136] Detailed explanation of the formula and the process of formula calculation and derivation:

[0137] Set current state The energy is (Based on the results of the measured data analysis), future state Energy The range is 1.0 to 2.0 (calculated by the energy assessment model). Refer to three future states, the energies are 1.0, 1.5, and 2.0 respectively.

[0138] Compute the exponential term for each state:

[0139] - ,

[0140] - ,

[0141] - ,

[0142] Summing these values ​​gives us the denominator:

[0143] ;

[0144] Then, the probability of each state is:

[0145] - ,

[0146] - ,

[0147] - ,

[0148] The results show that the state is , that is, in the current state, the system evolves to the state with the lowest energy. This result helps to analyze the tendency of the system to evolve toward a stable state, which is crucial for the formulation of disaster prevention and mitigation strategies.

[0149] Evaluate state probability data, determine the risk level under each future state, and generate the probability of future states occurring.

[0150] After obtaining the state probability data, the probability data is applied to the risk assessment model to simulate differentiated climate scenarios and evaluate the possibility and expected intensity of floods under differentiated scenarios. This requires combining the output results of the climate model with flood data, comparing data and model predictions, and adjusting model parameters to improve prediction accuracy. Then, probabilistic statistical methods, such as Monte Carlo simulation, are used to conduct risk assessment and calculate the possibility of floods under differentiated climate change scenarios. This process involves batch data processing and statistical analysis, using Python's Pandas library for data processing and Matplotlib library for visual display of results. Through these analyses and calculations, the probability of future state occurrence is generated, providing a scientific basis for flood risk management and the formulation of response strategies.

[0151] See also Figure 6 , the specific steps for obtaining the prediction results of future flood events are:

[0152] Comprehensively analyze future state probability data and regional climate factors, identify key influencing factors of rainfall intensity and river water level changes, and generate flood influencing factor analysis results;

[0153] By comprehensively analyzing the output data of the flood probability distribution model and the climate influencing factors of regional targets, the factors that most significantly affect floods can be identified, including rainfall intensity and river water level changes. This involves the collection and analysis of a variety of climate data, including precipitation records, river monitoring data, and capacity assessment of urban drainage systems. Through the data, regression analysis and variance analysis are used to determine the contribution of multiple factors to flood risk. This process includes not only data collection, but also strict review of data quality to ensure the accuracy and relevance of the data used. Through these analyses, more accurate predictions of flood risks can be made, providing a scientific basis for urban planning and emergency response.

[0154] Based on the analysis results of flood influencing factors, a composite mathematical model is used to calculate the possibility and intensity of flood events under multiple factors, using the formula:

[0155] ;

[0156] Obtain flood event probability and intensity calculation data;

[0157] in, It is The value of a condition, such as rainfall or river levels, affects the likelihood and severity of floods. is the weight of the condition, indicating the relative importance of the condition in the flood prediction model. The condition with a high weight has a greater impact on the prediction result. It is a condition The standard deviation is used to measure the degree of variation of conditional data and reflect the uncertainty under differentiated conditions. is a normalization factor, which is used to ensure that the sum of the flood probability under all conditions is 1, thus ensuring the normalization of the probability distribution;

[0158] formula:

[0159] ;

[0160] The formula is useful in that by introducing the standard deviation of multiple conditions , the formula can refer to the impact of each condition on flood risk, enhancing the accuracy and adaptability of the prediction.

[0161] Detailed explanation of the formula and the process of formula calculation and derivation:

[0162] There are three conditions: rainfall ( ), river level ( ), urban drainage system capacity ( The corresponding weight is , , , and their standard deviations are , , . Normalization factor is a constant that makes the sum of probabilities equal to 1, and the formula is:

[0163] ;

[0164] ;

[0165] if ,but , indicating that under given conditions, the probability of flood occurrence is 100%. This result shows that under given rainfall, river water level and urban drainage system capacity, the probability of flood events is extremely high, which helps to formulate more targeted flood prevention and control measures.

[0166] The calculation data of flood event probability and intensity are verified and the model is optimized to ensure that the model reflects the impact of actual climate change and geographical factors and to generate prediction results of future flood events.

[0167] The probability and intensity calculation data of flood events are systematically verified and the model is optimized to ensure that the model reflects the impact of actual climate change and geographical factors, thereby generating prediction results of future flood events and providing a scientific basis for response strategies and resource allocation. This process includes multiple iterative tests of the model and comparative analysis with data to verify the reliability and practicality of the prediction results. In addition, the model parameters need to be adjusted to reflect current climate change data.

[0168] See also Figure 7 ,The specific steps for obtaining real-time flood risk maps are:

[0169] Integrate the prediction results of future flood events into the geographic information system to ensure the spatial location of each data point, associate the flood risk data with geographic coordinates, and generate a GIS data layer;

[0170] In order to integrate the prediction results of future flood events with the existing geographic information system and ensure the spatial alignment of the data, it is necessary to first match the flood risk data with the geographic coordinate system through the data import function of GIS. This process includes coordinate conversion and projection adjustment to ensure that each data point can be located on the map. Such integration not only improves the accuracy of the data, but also provides the necessary foundation for subsequent layer overlay. Subsequently, through the layer control function of the GIS platform, the data is set as an independent layer so that its display and hiding can be flexibly adjusted when the layer is overlaid, thereby providing users with customizable view options.

[0171] Using GIS data layers on the GIS platform through layer overlay technology, combined with the existing functions of map services, the flood prediction results are overlaid on the actual map using the formula:

[0172] ;

[0173] Generate preliminary risk map views;

[0174] in, Represented in geographic coordinates The flood risk value on Representative The transparency of the layer, adjusts the visibility of the layer in the visual display, Indicates Layer at coordinates The flood risk data value provides information on the flood intensity of the location. is the total number of map layers;

[0175] formula:

[0176] ;

[0177] The formula is useful in that by adjusting the transparency parameter of each layer and layer data , can flexibly display the information of differentiated data layers, enhance the information richness and visual effects of the map, and enable users to view the data focus of the target as needed.

[0178] Detailed explanation of the formula and the process of formula calculation and derivation:

[0179] Set the transparency of layer 1 , the transparency of layer 2 , at coordinate (100,100), the data value of layer 1 , data value of layer 2 , calculate the superimposed data value at the coordinate:

[0180] ;

[0181] The results show that on the map at coordinate (100,100), the superimposed data value is 25, which reflects the flood risk assessment result after integrating the data of the two layers and provides risk data for decision makers.

[0182] Link preliminary risk map views with real-time weather update systems to automatically update flood risk levels to reflect current flood probability and intensity, and publish real-time flood risk maps.

[0183] Realizing the function of real-time update system involves docking with the data interface of meteorological station and hydrological monitoring station, and obtaining current meteorological and hydrological data through API. Each data point needs to include timestamp, geographic coordinates, rainfall, and water level information. The data is transmitted to the GIS system in real time through the network and triggers the update event of the database. The GIS system then recalculates the flood risk level and reflects it in real time on the risk map. In addition, the system also includes the function of users setting warning thresholds. When the flood risk reaches or exceeds the threshold, the system automatically sends an alert to related departments and the public.

[0184] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A flood simulation and prediction system based on GIS data, characterized in that: The system comprises: The data integration module collects climate and geographic information at the basin, regional and global scales, performs data verification and format standardization, integrates them into a unified data set, extracts multi-regional climate trends and geographic features, builds indexes, and generates a geographic climate database; The model self-matching module uses the data in the geographic climate database to adjust the flood prediction model parameters, including the width of the kernel function and the number of layers of hidden variables, configures the flood prediction model structure according to the climate trend and geographical characteristics of the target area, and generates a flood probability distribution model; The steps of obtaining the width of the kernel function and the number of layers of the latent variables specifically include: Analyze the climate data of the target area in the geographic climate database, identify key climate variables, including temperature and rainfall frequency, and generate climate variable analysis results for the target area; Based on the analysis results of climate variables in the target area, the adjustment needs of kernel functions and latent variables are evaluated using the formula: ； Adjust the flood prediction model parameters to obtain the width of the kernel function; in, represents the width of the adjusted kernel function, reflecting the sensitivity of the flood prediction model to climate change in the target area. represents the adjustment parameter of the kernel function width, which is used to reflect the volatility of climate variables in the target area. The influence factor representing the number of hidden variable layers is used to measure the impact of the differentiation level on the flood prediction model. is the mathematical constant pi; The steps of obtaining the flood probability distribution model specifically include: Using the width of the kernel function and the number of layers of latent variables, the basic structure of the flood prediction model is configured to ensure that the flood prediction model parameters match the geographical climate characteristics and generate a preliminary flood prediction model structure; The preliminary flood prediction model structure is simulated and verified using the formula: ； Simulate the probability of flood occurrence under differentiated climate conditions and obtain a flood probability distribution model; in, Represents the occurrence of flood events. Represents the input climate dataset, including key climate variables such as temperature and rainfall, It is the average occurrence condition of flood events predicted based on climate data, reflecting the climate state of flood occurrence at the average level. represents the standard deviation of the forecast data, which is used to quantify the variability and uncertainty of flood conditions. is a normalization constant that ensures that the sum of the probability of flood occurrence in all cases is 1; The flood trend prediction module extracts state transition data from the flood probability distribution model, calculates the probability of occurrence of future states, analyzes the risks under differentiated flood-inducing conditions, predicts the possibility and intensity of future flood events, and generates future flood event prediction results; The real-time response display module combines the prediction results of future flood events and performs data visualization on the GIS platform. It combines the prediction results with the existing geographic information system through map layer overlay, updates the flood probability and intensity information in real time, and generates a real-time flood risk map.

2. The flood simulation prediction system based on GIS data according to claim 1 is characterized in that: The geographic climate database specifically includes multi-regional climate trends, geographic features, and indexes; the future flood event prediction results specifically refer to flood occurrence probability and flood intensity prediction; and the real-time flood risk map includes risk update display, probability layer, and intensity layer.

3. The flood simulation prediction system based on GIS data according to claim 2 is characterized in that: The steps of obtaining the geographic climate database specifically include: Collect climate and geographic information at the basin, regional and global scales, integrate data from different geographical locations and climate systems, and obtain multi-source geographic climate datasets; Verifying and formatting the multi-source geographic climate dataset, and generating a standardized geographic climate dataset through cleaning and conversion operations; Key climate trends and geographic features are extracted from the standardized geoclimatic datasets to calculate climate change indicators at multiple scales using the formula: ； Generate climate change trend indices; in, Represents the calculated climate change trend index, indicating the degree of climate change in the target area. Representative The climate or geographical characteristic value of a data point. The climate data of a region at a certain point in time includes temperature, rainfall, Representative The weight of a data point reflects the importance or influence of the data point in the overall analysis. is the total number of data points, indicating the number of geographical or climate data points involved in the calculation. is the normalization factor of the weight, used to adjust each weight size; The climate change trend index is used to construct an index of climate and geographical features, and a geographical climate database is generated through association analysis and index construction processes.

4. The flood simulation prediction system based on GIS data according to claim 1 is characterized in that: The steps of obtaining the prediction results of future flood events specifically include: By analyzing the flood probability distribution model, key state variables are identified, including topography, climate change frequency and regional climate factors, and key state variable analysis results are obtained; The key state variable analysis results are used to construct a conditional probability calculation model to calculate the probability of multiple future states occurring under given current conditions, using the formula: ； Generate multiple future state probability data; in, Represents the state in the future time period, indicating multiple future situations under given current conditions. Represents the current state, which is the current state referenced when calculating conditional probability. Representation status The energy is used to evaluate the possibility of a state occurring. The lower the energy, the higher the possibility of the state occurring. The denominator of the formula It is to perform exponential decay summation on the energy of all states to normalize the probability value to ensure that the sum of the probabilities of all states is 1; The plurality of future state probability data are evaluated, a risk level under each future state is determined, and a probability of occurrence of the future state is generated.

5. The flood simulation prediction system based on GIS data according to claim 4 is characterized in that: The steps of obtaining the prediction results of future flood events specifically include: Comprehensively analyze the future state probability data and regional climate factors, identify the key influencing factors of rainfall intensity and river water level changes, and generate flood influencing factor analysis results; Based on the analysis results of flood influencing factors, a composite mathematical model is used to calculate the possibility of flood events under multiple factors, using the formula: ； Get the probability of flood events; in, It is The value of a condition, such as rainfall or river levels, affects the likelihood and severity of floods. is the weight of the condition, indicating the relative importance of the condition in the flood prediction model. The condition with a high weight has a greater impact on the prediction result. It is a condition The standard deviation is used to measure the degree of variation of conditional data and reflect the uncertainty under differentiated conditions. is a normalization factor, which is used to ensure that the sum of the flood probability under all conditions is 1, thus ensuring the normalization of the probability distribution; The flood event probability and intensity calculation data are verified and the model is optimized to ensure that the model reflects the impact of actual climate change and geographical factors and to generate future flood event prediction results.

6. The flood simulation prediction system based on GIS data according to claim 5 is characterized in that: The steps for obtaining the real-time flood risk map are specifically as follows: Integrate the forecast results of future flood events into the geographic information system to ensure the spatial location of each data point, associate the flood risk data with geographic coordinates, and generate a GIS data layer; The GIS data layer is used on the GIS platform through layer overlay technology, combined with the existing functions of map services, to overlay the flood prediction results on the actual map using the formula: ； Generate preliminary risk map views; in, Represented in geographic coordinates The flood risk value on Representative The transparency of the layer, adjusts the visibility of the layer in the visual display, Indicates Layer at coordinates The flood risk data value provides information on the flood intensity of the location. is the total number of map layers; The preliminary risk map view is linked to the real-time meteorological update system to automatically update the flood risk level to reflect the current flood probability and intensity and publish a real-time flood risk map.

Images