A construction method and system for optimizing scheduling and resource allocation related to water conservancy and flood control

Abstract

The present invention relates to the field of heat map construction technology, and in particular to a construction method and system for optimizing scheduling and resource allocation related to water conservancy and flood control. The method comprises the following steps: acquiring regional remote sensing image data; performing data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; performing flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data. The present invention improves the accuracy, efficiency and intelligence level of the flood control resource configuration heat map system through systematic data integration, dynamic comprehensive analysis, model optimization and coupling, precise risk area identification and intelligent real-time updating.

Description

Technical Field

[0001] The present invention relates to the technical field of heat map construction, and in particular to a construction method and system for optimizing scheduling and resource allocation of water conservancy and flood control. Background Art

[0002] Initially, flood control resource management relied on traditional manual records and simple mapping. During this period, it mainly relied on paper maps and basic geographic information system (GIS) technology, with low requirements for the real-time and accuracy of data. With the introduction of GIS technology, flood control management began to be digitized. GIS technology can process geospatial data and provide more accurate maps and resource distribution analysis. At this stage, flood control resource allocation began to combine satellite images and digital maps, improving the timeliness and spatial accuracy of data. With the maturity of big data and artificial intelligence technology, the flood control resource allocation heat map system began to introduce machine learning algorithms for predictive analysis. At this stage, the system was able to process massive data, make accurate predictions and optimize resource allocation, improving the intelligence level of flood control work. At present, the application of intelligent cloud platforms and Internet of Things technologies has further promoted the development of flood control resource allocation systems. Through real-time sensor data and cloud computing platforms, the system can achieve more dynamic resource scheduling and emergency response, improving the real-time and flexibility of flood control work. However, the current traditional flood control system is limited to single data analysis and lacks comprehensive analysis. At the same time, it lacks accurate simulation and optimization in risk area identification and resource allocation, which leads to low comprehensiveness and accuracy of system construction. Summary of the invention

[0003] Based on this, it is necessary to provide a construction method and system for optimizing scheduling and resource allocation related to water conservancy and flood control to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a construction method for optimizing scheduling and resource allocation for water conservancy and flood control is provided, the method comprising the following steps:

[0005] Step S1: Acquire regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data;

[0006] Step S2: Based on the data of meteorological monitoring stations, the long-term and short-term rainfall extreme value changes of the standard regional remote sensing image data are analyzed to generate regional short-term heavy rainfall trend data and regional long-term heavy rainfall trend data; regional rainstorm convergence mechanism analysis is performed through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data to generate regional rainstorm convergence mechanism data; based on the data of flood monitoring stations, the regional flood mechanism analysis is performed on the standard regional remote sensing image data to generate regional flood mechanism data;

[0007] Step S3: Compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and the drainage network monitoring data to generate an urban flood model; perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model;

[0008] Step S4: regional flood simulation is performed on the standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; maximum flood depth is calculated for the regional flood simulation data to obtain regional flood flood depth simulation data; risk area annotation is performed on the regional geographic division data according to the regional flood flood depth simulation data to generate high-risk area annotation data and low-risk area annotation data; resource allocation simulation optimization is performed on the high-risk area annotation data and the low-risk area annotation data to generate flood control resource allocation optimization data;

[0009] Step S5: Perform three-dimensional heat map conversion on the resource allocation optimization simulation data to generate a three-dimensional flood control resource configuration heat map; perform real-time data stream update and fusion on the three-dimensional flood control resource configuration heat map to generate dynamic heat map update data; perform intelligent emergency decision-making on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0010] The present invention provides a high-resolution and comprehensive geographic information foundation by acquiring regional remote sensing image data, supporting subsequent analysis and decision-making. By cleaning, correcting and standardizing image data, the accuracy and consistency of the data are improved, and noise and errors are reduced. By screening key monitoring data (meteorology, floods, hydrology and drainage), the comprehensiveness and pertinence of flood control analysis are ensured, and a comprehensive data set containing different types of monitoring data is formed, which helps to accurately identify and evaluate flood control needs. The short-term and long-term rainfall trend data generated help to identify rainfall patterns and potential heavy rainfall risks, and improve the prediction ability of extreme rainfall events. By analyzing the rainstorm convergence mechanism, it is possible to understand the convergence and flow behavior of rainstorms in specific areas, which is helpful to formulate effective flood control strategies. Through the analysis of flood mechanism, the causes and laws of floods in the region are deeply understood, providing a scientific basis for formulating targeted flood prevention and control measures. The comparison of impervious surface changes reveals the impact of underlying surface changes in the region, helping to evaluate the impact of increased impervious surfaces on flood flow and water accumulation. The flood mechanism is optimized according to the underlying surface change data, the accuracy of the flood model is improved, and the prediction ability is enhanced. The urban flood model is constructed based on hydrological water level and drainage network data, making the simulation of urban flood conditions more accurate. The coupling of the urban flood model with the storm surge model improves the simulation capability of floods and storm surges under comprehensive meteorological and topographic conditions, providing support for the formulation of a comprehensive flood control plan. The regional flood situation is simulated by the urban flood coupling model, and the generated simulation data can help predict the impact of floods under different scenarios. Maximum inundation depth calculation: Flood inundation depth data for different locations in the region is provided to help assess the severity of the flood. High-risk and low-risk areas are marked according to the simulation data to help identify areas that need priority attention and optimize the allocation of flood control resources. Resource allocation simulation optimization is performed based on the marked data of the risk area to ensure that flood control resources can be effectively deployed to the areas most in need, improve resource utilization efficiency and flood control effects. The resource allocation optimization data is converted into a three-dimensional heat map to intuitively display the distribution of flood control resources and improve the visualization of the data. The dynamic update of the heat map ensures the real-time and accuracy of the data and can reflect the latest flood control resource demand and distribution. Intelligent emergency decision-making based on dynamic heat maps improves the flexibility and response capabilities of flood control resource allocation, and enhances the system's comprehensive flood control capabilities and decision-making support level. Therefore, the present invention improves the accuracy, efficiency and intelligence level of the flood control resource allocation heat map system through systematic data integration, dynamic comprehensive analysis, model optimization and coupling, precise risk area identification and intelligent real-time updating.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: using GIS to obtain regional remote sensing image data;

[0013] Step S12: performing data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0014] Step S13: extracting regional geographic features from the standard regional remote sensing image data to obtain regional geographic feature data; dividing the standard regional remote sensing image data into regions according to the regional geographic feature data to generate regional geographic division data;

[0015] Step S14: Screening flood control resource sites of the standard regional remote sensing image data through regional geographic division data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data.

[0016] The present invention ensures the consistency and integrity of data by cleaning, filling missing values ​​and standardizing remote sensing image data. This process reduces data noise and inconsistency and improves the reliability of subsequent analysis. Extracting regional geographic feature data from standardized remote sensing images can more accurately describe the geographical and environmental characteristics of the region. This helps to improve the accuracy of regional division, so that flood control resources can be configured more effectively. Regional division based on regional geographic feature data can divide the region into sub-regions with similar characteristics. This division helps to make a more detailed assessment of the risks in different regions, so as to optimize the deployment and management of flood control resources. Using regional geographic division data to screen flood control resource sites can ensure that the screened sites can cover key flood control demand areas. By including data from multiple aspects such as meteorological monitoring, flood monitoring, hydrological water level and drainage network, the comprehensiveness and effectiveness of flood control site selection are improved. The flood control site screening data covers a variety of monitoring types, so that flood control work can be monitored in real time from multiple dimensions. This comprehensive monitoring can more accurately predict and respond to potential flood risks and improve the early warning and emergency response capabilities of flood control work.

[0017] Preferably, step S21 includes the following steps:

[0018] Step S21: Screening the regional rainfall data of the remote sensing image data of the standard area based on the meteorological monitoring station data to obtain the regional rainfall data; analyzing the annual peak rainfall change trend of the regional rainfall data greater than the preset rainfall threshold to generate the regional short-duration heavy rainfall trend data;

[0019] Step S22: Mapping the regional short-duration heavy rainfall trend data to the standard regional remote sensing image data to perform rainfall interannual distribution annotation, and generate regional rainfall interannual distribution data; performing rainfall spatial variation analysis on the regional rainfall interannual distribution data, and generating regional rainfall distribution balance data;

[0020] Step S23: performing precipitation extreme value distribution calculation on regional rainfall data less than or equal to a preset rainfall threshold to generate long-duration regional rainfall extreme value distribution data; performing heavy rainfall change trend analysis on the long-duration regional rainfall extreme value distribution data in recent years to generate regional long-duration heavy rainfall trend data;

[0021] Step S24: performing regional rainstorm convergence mechanism analysis based on the regional short-duration heavy rainfall trend data, the regional rainfall distribution balance data and the regional long-duration heavy rainfall trend data to generate regional rainstorm convergence mechanism data;

[0022] Step S25: Perform regional flood mechanism analysis on the remote sensing image data of the standard area based on the flood monitoring station data to generate regional flood mechanism data.

[0023] The present invention can more accurately identify rainfall intensity and frequency by screening regional rainfall data through meteorological monitoring station data. This precise screening helps to identify areas with excessive rainfall and provide basic data for subsequent risk assessment and protective measures. Analysis of the changing trend of annual peak rainfall can reveal the changing trend of short-duration heavy rainfall in the region. This trend analysis helps to identify potential heavy rainfall risks in advance and take corresponding early warning and response measures. By mapping short-duration heavy rainfall trend data to remote sensing image data for interannual distribution annotation, regional rainfall interannual distribution data can be generated. This annotation helps to understand the spatiotemporal distribution characteristics of rainfall, thereby optimizing the configuration of flood control resources. Spatial change analysis of rainfall interannual distribution data can generate rainfall distribution balance data. This helps to evaluate the degree of balance of rainfall distribution in the region and identify the existing rainfall abnormal areas. Extreme value distribution calculation of rainfall data less than or equal to the rainfall threshold can generate long-duration rainfall extreme value distribution data. This helps to understand the distribution characteristics of long-term rainfall extremes, thereby formulating more effective flood control measures. Heavy rainfall change trend analysis of long-duration rainfall extreme value distribution data can generate regional long-duration heavy rainfall trend data. This analysis helps to identify long-term rainfall trends and provide a basis for long-term flood control planning. Comprehensive regional short-duration heavy rainfall trend, rainfall distribution balance and long-duration heavy rainfall trend data are used to analyze the rainstorm runoff mechanism, and regional rainstorm runoff mechanism data can be generated. This helps to deeply understand the water flow convergence and propagation mechanism caused by heavy rain, thereby improving flood control design and emergency response. Flood mechanism analysis of remote sensing image data is performed through flood monitoring station data to generate regional flood mechanism data. This helps to identify the mechanism and law of flood occurrence, thereby enhancing regional flood prevention capabilities.

[0024] Preferably, step S25 comprises the following steps:

[0025] Step S251: screening the standard regional remote sensing image data for river channels to obtain regional river channel data; connecting the regional river channel data for river channels to generate regional river network data;

[0026] Step S252: Analyze the river network tide characteristics of the regional river network data according to the flood monitoring station data to generate river network tide characteristic data; calculate the flood and tide encounter frequency of the regional river network data according to the river network tide characteristic data to obtain the river network flood and tide encounter frequency data;

[0027] Step S253: Utilizing the river network flood and tide encounter frequency data and the river network tidal level characteristic data, the regional river network data is subjected to regional flood and tide mechanism analysis to generate regional flood and tide mechanism data.

[0028] The present invention can generate regional river network data by screening and connecting the river channels of the standard regional remote sensing image data, and can depict the river channel network in the region in detail. This provides an accurate geographical basis for subsequent flood analysis and ensures the reliability of the data. Detailed river network tide level characteristic data can be generated by analyzing the tide level characteristics of the river network. This helps to understand the behavior and changes of the river network at different tide levels, thereby providing key information for assessing flood risks. The river network flood level encounter frequency data can be obtained by calculating the flood level encounter frequency data through the river network tide level characteristic data. This calculation helps to identify the frequency and distribution of flood events, and provides an important basis for flood risk assessment and management. Regional flood level mechanism analysis can be performed using the river network flood level encounter frequency data and the river network tide level characteristic data, and regional flood level mechanism data can be generated. This analysis can provide an in-depth understanding of the mechanism and law of flood level occurrence, and help formulate more effective flood control strategies and emergency response measures. The data on the comprehensive river network tide level characteristics and the flood level encounter frequency can provide a scientific basis for the design and deployment of flood control facilities, thereby improving the regional defense and emergency response capabilities against floods. Regional flood mechanism data provides important information support for the government and relevant departments in flood control planning, risk management and post-disaster recovery, helping to formulate more scientific and reasonable flood control policies and measures.

[0029] Preferably, step S3 comprises the following steps:

[0030] Step S31: converting the standard area remote sensing image data into geographic elevation data to generate regional geographic elevation data; performing regional impervious surface change comparison on the standard area remote sensing image data based on the regional geographic elevation data to generate regional underlying surface change data; optimizing the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data;

[0031] Step S32: Calculate the rainwater flow rate of the pipe network based on the hydrological water level station data and the drainage pipe network monitoring data to generate rainwater surface runoff simulation data and rainwater surface convergence dynamics data; construct an urban flood model based on the rainwater surface runoff simulation data and rainwater surface convergence dynamics data to generate an urban flood model;

[0032] Step S33: extracting storm surge characteristics from the meteorological monitoring station data to obtain storm surge characteristic data; constructing a storm surge model for the storm surge characteristic data based on the hydrodynamic equation to generate a storm surge model;

[0033] Step S34: Based on the regional rainstorm runoff mechanism data and the regional flood tide mechanism optimization data, the urban flood model and the storm surge model are coupled to generate an urban flood coupling model.

[0034] The present invention can generate detailed regional geographic elevation data by converting the geographic elevation of standard regional remote sensing image data. This process provides basic data for analyzing terrain changes and surface features. By comparing the changes in impervious surfaces with regional geographic elevation data, the regional underlying surface change data generated can reflect the dynamics of surface changes in the region. This helps to understand the impact of urbanization on flood discharge and water accumulation. The regional flood mechanism data is optimized according to the regional underlying surface change data, thereby improving the accuracy and practicality of the flood mechanism analysis and providing more accurate information for the formulation of flood control measures. The hydrological water level station data and the drainage network monitoring data are calculated, and the generated rainwater surface flow simulation data and rainwater surface convergence dynamics data can help predict rainwater flow and convergence behavior. This is crucial for the design and optimization of urban drainage systems. The urban flood model constructed based on the calculation data provides the ability to simulate and predict the occurrence of floods in the city. This helps to identify potential waterlogging areas and formulate corresponding flood emergency measures. Storm surge feature extraction of meteorological monitoring station data can obtain detailed storm surge data. This provides a basis for the prediction and response of storm surges. The storm surge model constructed based on storm surge characteristic data and hydrodynamic equations can simulate the behavior and impact of storm surges, which is helpful for early warning and prevention of disasters caused by storm surges. The regional rainstorm runoff mechanism data and regional flood mechanism optimization data are applied to the coupling of urban flood model and storm surge model to generate an urban flood coupling model. This coupling model comprehensively considers the interactive effects of rainstorm and storm surge, and can provide a more comprehensive flood risk assessment. Through the coupling model, the urban flood risk under complex weather conditions can be predicted more accurately, and the effect of disaster prevention and mitigation can be improved.

[0035] Preferably, calculating the network rainwater flow rate based on the hydrological water level station data and the drainage network monitoring data includes:

[0036] Perform time series spectrum analysis on hydrological water level station data to generate hydrological flow spectrum time series data; perform high-precision flow modeling on drainage network monitoring data to generate network fine flow model data;

[0037] Perform multi-scale flow synthesis processing on the hydrological flow spectrum time series data and the pipe network fine flow model data to generate comprehensive flow distribution data; perform terrain-based rainfall runoff simulation on the comprehensive flow distribution data to generate rainwater surface runoff simulation data;

[0038] Dynamically optimize the runoff path of rainwater surface runoff simulation data to generate rainwater surface runoff path optimization data; perform three-dimensional hydrodynamic runoff calculation on the rainwater surface runoff path optimization data to generate rainwater surface runoff dynamics data.

[0039] The present invention can reveal the periodicity and frequency characteristics of flow by performing time series spectrum analysis on hydrological and water level station data. This helps to identify flow change patterns on different time scales and provides an important data basis for prediction and analysis. High-precision flow modeling of drainage network monitoring data can create a detailed network flow model. This model can accurately reflect the flow characteristics of the drainage system and help optimize the design and operation of the drainage system. Multi-scale synthesis processing of hydrological flow spectrum time series data and network fine flow model data can obtain comprehensive comprehensive flow distribution data. This comprehensive data helps to understand the changes in flow at different scales and improve the accuracy of flow prediction. Based on the comprehensive flow distribution data, the terrain rainfall runoff simulation is performed, and the generated rainwater surface runoff simulation data can reveal how rainfall generates runoff on the surface. This helps to identify high-risk waterlogging areas and design reasonable flood control measures. Dynamic convergence path optimization of rainwater surface runoff simulation data can generate optimized convergence path data. This process ensures that rainwater flows to the optimal path and reduces the risk of waterlogging and flooding. Through three-dimensional hydrodynamic confluence routing, the dynamic characteristics of rainwater flow can be simulated and detailed confluence dynamic data can be generated. This helps to deeply understand the dynamic process of rainwater flow, so as to more accurately predict and manage floods. Through time-series spectrum analysis and fine modeling of flow data, flow changes can be more accurately predicted, and the accuracy of flood warning and response can be improved. High-precision flow models and dynamic confluence path optimization help optimize drainage system design and reduce flood and waterlogging risks. Multi-scale flow synthesis and rainfall runoff simulation provide a comprehensive analysis of flow, which helps to formulate scientific flood control measures. Three-dimensional hydrodynamic confluence routing provides an in-depth understanding of rainwater flow characteristics and provides accurate data support for flood response and management.

[0040] Preferably, step S4 comprises the following steps:

[0041] Step S41: performing regional flood simulation on standard regional remote sensing image data through an urban flood coupling model to generate regional flood simulation data;

[0042] Step S42: Calculate the maximum inundation depth of the regional flood simulation data to obtain regional flood inundation depth simulation data; compare the regional flood inundation depth simulation data with a preset standard water depth threshold, and when the regional flood inundation depth simulation data is greater than or equal to the preset standard water depth threshold, mark the regional geographic division data as a high-risk area based on the regional flood inundation depth simulation data to generate high-risk area marking data;

[0043] Step S43: when the regional flood water depth simulation data is less than a preset standard water depth threshold, the regional geographic division data is marked as a low-risk area based on the regional flood water depth simulation data to generate low-risk area marking data;

[0044] Step S44: forecast the demand for flood control resources for the high-risk area labeled data and the low-risk area labeled data to generate regional flood control resource demand forecast data; perform resource allocation simulation optimization on the high-risk area labeled data and the low-risk area labeled data based on the regional flood control resource demand forecast data to generate flood control resource allocation optimization data.

[0045] The present invention can accurately divide high-risk and low-risk areas through comparative analysis of regional flood simulation and water depth threshold, providing a scientific basis for disaster prevention and mitigation. Through the prediction and simulation optimization of flood control resource demand, the allocation efficiency of flood control resources is effectively improved, ensuring that high-risk areas can obtain sufficient protection resources first, thereby minimizing the impact of flood disasters. The method can dynamically adjust flood control strategies and resource allocation plans based on real-time flood simulation data and regional changes, enhancing the flexibility and effectiveness of responding to flood disasters. Through comprehensive analysis of regional flood simulation data and high-precision regional division combined with geographic information system (GIS), data-driven flood control decision support is realized, and the scientificity and accuracy of decision-making are improved. The whole process management from flood simulation to resource optimization is integrated, which significantly improves the overall efficiency of flood control management and reduces the blindness and waste of resources in disaster response.

[0046] Preferably, step S44 includes the following steps:

[0047] Step S441: extracting spatiotemporal risk features from the high-risk area annotated data and the low-risk area annotated data to obtain the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data; performing joint risk assessment on the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data to generate comprehensive risk assessment data;

[0048] Step S442: Divide the comprehensive risk assessment data into data sets to generate a model training set and a model test set; perform model training on the model training set using a time series prediction network algorithm to generate a flood control demand prediction pre-model; perform model optimization iteration on the flood control demand prediction pre-model using the model test set to generate a flood control resource demand prediction model;

[0049] Step S443: Importing the comprehensive risk assessment data into the flood control resource demand prediction model to perform flood control resource demand prediction, and generate regional flood control resource demand prediction data; based on the regional flood control resource demand prediction data, geospatial mapping is performed on the high-risk area annotation data and the low-risk area annotation data to generate a high-risk area resource demand distribution prediction map and a low-risk area resource distribution prediction map;

[0050] Step S444: Perform resource demand intensity analysis on the resource demand distribution forecast map of the high-risk area to generate resource demand intensity data for the high-risk area; optimize resource priority allocation of the high-risk area annotation data according to the resource demand intensity data of the high-risk area to generate flood control resource allocation optimization data for the high-risk area; confirm the basic configuration amount of flood control resources on the resource distribution forecast map of the low-risk area to obtain the basic configuration amount of flood control resources in the low-risk area;

[0051] Step S445: Optimize the resource balance allocation of the low-risk area marked data according to the basic configuration of flood control resources in the low-risk area, and generate the low-risk area flood control resource allocation optimization data; integrate the high-risk area flood control resource allocation optimization data and the low-risk area flood control resource allocation optimization data to generate the flood control resource allocation optimization data.

[0052] The present invention analyzes the spatiotemporal characteristics of high-risk and low-risk areas in detail through spatiotemporal feature extraction and joint risk assessment, making risk assessment more comprehensive and accurate, and helping to formulate more effective flood control strategies. Model training and optimization are carried out through the time series prediction network algorithm, and the generated flood control resource demand prediction model can accurately predict the resource demand of different regions, ensuring that flood control resources can be reasonably allocated to the most needed places. Based on the resource demand data generated by the prediction model, the resource allocation of high-risk areas and low-risk areas is optimized through resource demand intensity analysis and geographic space mapping, making resource allocation more scientific and reasonable. Resource allocation optimization is performed for high-risk areas and low-risk areas respectively, and through resource balance allocation optimization, the dynamic configuration of flood control resources is ensured, and changes in actual flood control needs can be flexibly responded to. The method significantly improves the efficiency and effect of flood control response through model-driven resource allocation optimization, reduces resource waste, and ensures that key areas can obtain sufficient resource support. Through the integration of allocation optimization data of high- and low-risk areas, a unified flood control resource allocation optimization scheme is formed, which enhances the overall coordination of resource management and effectively improves the regional flood control and disaster resistance capabilities.

[0053] Preferably, step S5 comprises the following steps:

[0054] Step S51: performing multi-dimensional data slicing processing on the resource allocation optimization simulation data to generate multi-dimensional resource distribution slice data; performing high-precision spatial interpolation on the multi-dimensional resource distribution slice data to generate continuous resource distribution grid data;

[0055] Step S52: performing advanced color mapping conversion on the continuous resource distribution grid data to generate two-dimensional color mapping matrix data; performing three-dimensional data visualization processing on the two-dimensional color mapping matrix data to generate a three-dimensional flood control resource configuration heat map;

[0056] Step S53: Update and merge the three-dimensional flood control resource configuration heat map in real time to generate dynamic heat map update data; make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0057] The present invention uses multidimensional data slicing and high-precision spatial interpolation technology to generate continuous resource distribution grid data that can accurately present the distribution of resources in different regions, ensuring the accuracy and rationality of resource allocation. Through advanced color mapping conversion and three-dimensional data visualization processing, the generated three-dimensional flood control resource configuration heat map provides an intuitive resource allocation display method, allowing managers to quickly and accurately understand the resource allocation situation and facilitate decision-making. Through advanced color mapping conversion and three-dimensional data visualization processing, the generated three-dimensional flood control resource configuration heat map provides an intuitive resource allocation display method, allowing managers to quickly and accurately understand the resource allocation situation and facilitate decision-making. Through the intelligent emergency decision-making function, the flood control resource configuration heat map system can automatically analyze and dynamically update data, provide optimized emergency decision-making suggestions, help managers quickly make scientific decisions in emergency situations, and improve emergency management efficiency. The constructed flood control resource configuration heat map system integrates data processing, visualization display and emergency decision support functions, provides all-round and systematic technical support for flood control resource management, and effectively improves the overall level of flood control resource management. This method effectively improves the efficiency and accuracy of flood control resource management through multi-dimensional data processing and intelligent decision support, ensuring that resources can be allocated to key areas in a timely and accurate manner, thereby significantly improving flood control response capabilities.

[0058] In this specification, a construction system for optimizing scheduling and resource allocation for water conservancy and flood control is provided, which is used to execute the above-mentioned construction method for optimizing scheduling and resource allocation for water conservancy and flood control. The construction system for optimizing scheduling and resource allocation for water conservancy and flood control includes:

[0059] The flood control site acquisition module is used to obtain regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data;

[0060] The rainstorm and flood mechanism analysis module is used to analyze the extreme changes of long-term and short-term rainfall on the remote sensing image data of the standard area based on the data of the meteorological monitoring station, and generate the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data; to analyze the regional rainstorm convergence mechanism through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data, and generate the regional rainstorm convergence mechanism data; to analyze the regional flood mechanism of the standard area remote sensing image data based on the flood monitoring station data, and generate the regional flood mechanism data;

[0061] The model coupling module is used to compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and drainage network monitoring data to generate an urban flood model; and perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model.

[0062] The regional risk labeling module is used to simulate regional floods on standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; calculate the maximum flood depth of the regional flood simulation data to obtain regional flood depth simulation data; label the risk areas of regional geographic division data based on the regional flood depth simulation data to generate high-risk area labeling data and low-risk area labeling data; perform resource allocation simulation optimization on the high-risk area labeling data and the low-risk area labeling data to generate flood control resource allocation optimization data;

[0063] The heat map configuration module is used to convert the resource allocation optimization simulation data into a three-dimensional heat map to generate a three-dimensional flood control resource configuration heat map; to update and fuse the three-dimensional flood control resource configuration heat map with real-time data streams to generate dynamic heat map update data; to make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0064] The beneficial effect of the present invention is that by acquiring regional remote sensing image data and preprocessing, a variety of monitoring data related to flood control are screened out, making the data more comprehensive and reliable, and laying a solid foundation for subsequent analysis. By analyzing the changes in long and short-term rainfall extremes, the regional rainfall pattern can be accurately captured, and short-term and long-term heavy rainfall trend data are generated, providing a basis for flood mechanism analysis, and regional flood mechanism analysis is performed based on flood monitoring station data, providing a scientific basis for subsequent flood control work. By analyzing the regional underlying surface change data and optimizing the regional flood mechanism, optimized flood mechanism data is generated. At the same time, an urban flood model is constructed and regional model coupling is performed, which improves the simulation accuracy of flood phenomena and makes flood control work more accurate and scientific. The maximum flood depth is calculated by flood simulation data, the risk area is marked in the region, and resource allocation simulation optimization is performed to ensure that flood control resources can be effectively allocated to high-risk areas and low-risk areas, thereby improving the efficiency and pertinence of resource allocation. The resource allocation optimization simulation data is converted into a three-dimensional flood control resource configuration heat map, and real-time data streams are updated and fused, so that the distribution of flood control resources can be presented intuitively and updated at any time, which improves the real-time and accuracy of emergency management. Through the intelligent emergency decision-making function, a flood control resource configuration heat map system is constructed, which can analyze dynamic data in real time, provide decision support, and help managers make scientific decisions quickly in emergency situations, thereby improving flood control response capabilities. The overall method provides comprehensive technical support for flood control management through precise data processing, optimized models, scientific resource allocation and real-time visualization, and significantly improves the scientificity, efficiency and emergency response capabilities of flood control work. Therefore, the present invention improves the accuracy, efficiency and intelligence level of the flood control resource configuration heat map system through systematic data integration, dynamic comprehensive analysis, model optimization and coupling, precise risk area identification and intelligent real-time updating. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of a construction method for optimizing scheduling and resource allocation for water conservancy and flood control;

[0066] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0067] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 3 , a construction method for optimizing scheduling and resource allocation for water conservancy and flood control, the method comprising the following steps:

[0073] Step S1: Acquire regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data;

[0074] Step S2: Based on the data of meteorological monitoring stations, the long-term and short-term rainfall extreme value changes of the standard regional remote sensing image data are analyzed to generate regional short-term heavy rainfall trend data and regional long-term heavy rainfall trend data; regional rainstorm convergence mechanism analysis is performed through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data to generate regional rainstorm convergence mechanism data; based on the data of flood monitoring stations, the regional flood mechanism analysis is performed on the standard regional remote sensing image data to generate regional flood mechanism data;

[0075] Step S3: Compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and the drainage network monitoring data to generate an urban flood model; perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model;

[0076] Step S4: regional flood simulation is performed on the standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; maximum flood depth is calculated for the regional flood simulation data to obtain regional flood flood depth simulation data; risk area annotation is performed on the regional geographic division data according to the regional flood flood depth simulation data to generate high-risk area annotation data and low-risk area annotation data; resource allocation simulation optimization is performed on the high-risk area annotation data and the low-risk area annotation data to generate flood control resource allocation optimization data;

[0077] Step S5: Perform three-dimensional heat map conversion on the resource allocation optimization simulation data to generate a three-dimensional flood control resource configuration heat map; perform real-time data stream update and fusion on the three-dimensional flood control resource configuration heat map to generate dynamic heat map update data; perform intelligent emergency decision-making on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0078] The present invention provides a high-resolution and comprehensive geographic information foundation by acquiring regional remote sensing image data, supporting subsequent analysis and decision-making. By cleaning, correcting and standardizing image data, the accuracy and consistency of the data are improved, and noise and errors are reduced. By screening key monitoring data (meteorology, floods, hydrology and drainage), the comprehensiveness and pertinence of flood control analysis are ensured, and a comprehensive data set containing different types of monitoring data is formed, which helps to accurately identify and evaluate flood control needs. The short-term and long-term rainfall trend data generated help to identify rainfall patterns and potential heavy rainfall risks, and improve the prediction ability of extreme rainfall events. By analyzing the rainstorm convergence mechanism, it is possible to understand the convergence and flow behavior of rainstorms in specific areas, which is helpful to formulate effective flood control strategies. Through the analysis of flood mechanism, the causes and laws of floods in the region are deeply understood, providing a scientific basis for formulating targeted flood prevention and control measures. The comparison of impervious surface changes reveals the impact of underlying surface changes in the region, helping to evaluate the impact of increased impervious surfaces on flood flow and water accumulation. The flood mechanism is optimized according to the underlying surface change data, the accuracy of the flood model is improved, and the prediction ability is enhanced. The urban flood model is constructed based on hydrological water level and drainage network data, making the simulation of urban flood conditions more accurate. The coupling of the urban flood model with the storm surge model improves the simulation capability of floods and storm surges under comprehensive meteorological and topographic conditions, providing support for the formulation of a comprehensive flood control plan. The regional flood situation is simulated by the urban flood coupling model, and the generated simulation data can help predict the impact of floods under different scenarios. Maximum inundation depth calculation: Flood inundation depth data for different locations in the region is provided to help assess the severity of the flood. High-risk and low-risk areas are marked according to the simulation data to help identify areas that need priority attention and optimize the allocation of flood control resources. Resource allocation simulation optimization is performed based on the marked data of the risk area to ensure that flood control resources can be effectively deployed to the areas most in need, improve resource utilization efficiency and flood control effects. The resource allocation optimization data is converted into a three-dimensional heat map to intuitively display the distribution of flood control resources and improve the visualization of the data. The dynamic update of the heat map ensures the real-time and accuracy of the data and can reflect the latest flood control resource demand and distribution. Intelligent emergency decision-making based on dynamic heat maps improves the flexibility and response capabilities of flood control resource allocation, and enhances the system's comprehensive flood control capabilities and decision-making support level. Therefore, the present invention improves the accuracy, efficiency and intelligence level of the flood control resource allocation heat map system through systematic data integration, dynamic comprehensive analysis, model optimization and coupling, precise risk area identification and intelligent real-time updating.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a construction method for optimizing scheduling and resource allocation for water conservancy and flood control according to the present invention. In this example, the construction method for optimizing scheduling and resource allocation for water conservancy and flood control includes the following steps:

[0080] Step S1: Acquire regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data;

[0081] In an embodiment of the present invention, regional remote sensing image data is obtained by using remote sensing satellites or drones. Common remote sensing satellites include Landsat and Sentinel series, or drones are used for high-resolution regional photography. The required image data is downloaded through platforms such as EarthExplorer and Sentinel Hub. The regional image is photographed using a camera carried by a drone and exported to common image formats such as TIFF or JPEG. Image processing technology (such as OpenCV or Python Imaging Library) is used to remove noise and artifacts in the image. Interpolation algorithms (such as Kriging interpolation and spline interpolation) are used to repair missing areas in the image. Missing values ​​are filled using linear interpolation, polynomial interpolation, mean filling and other methods. The image data is standardized to a uniform scale, such as a range of 0-1, and data normalization is performed. Meteorological monitoring data, such as temperature, precipitation and other information, are obtained from meteorological departments or related data platforms. Data is obtained from flood monitoring systems, including historical flood data, real-time water level monitoring data, etc. Hydrological data, including river water levels, lake water levels, etc., are obtained. Monitoring data of drainage pipe networks are obtained from urban drainage systems. Integrate monitoring data from different sources, including meteorological stations, flood monitoring stations, hydrological stations, and drainage networks. Spatially match the acquired monitoring data with remote sensing image data to determine the location of flood control monitoring stations. Use GIS analysis tools to perform spatial analysis and screen out qualified flood control monitoring stations.

[0082] Step S2: Based on the data of meteorological monitoring stations, the long-term and short-term rainfall extreme value changes of the standard regional remote sensing image data are analyzed to generate regional short-term heavy rainfall trend data and regional long-term heavy rainfall trend data; regional rainstorm convergence mechanism analysis is performed through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data to generate regional rainstorm convergence mechanism data; based on the data of flood monitoring stations, the regional flood mechanism analysis is performed on the standard regional remote sensing image data to generate regional flood mechanism data;

[0083] In the embodiment of the present invention, data such as rainfall, rainfall intensity, and rainfall duration are collected from meteorological monitoring sites. These data can be obtained through meteorological monitoring equipment to ensure that the temporal and spatial resolution of the data are suitable for analysis needs. Remote sensing image data covering the standard area is obtained. The image data should cover a sufficiently long period of time to analyze the changes in long and short-term rainfall. Water level data, waterlogging area and other information from flood monitoring sites are collected. Rainfall data in a short period of time are analyzed, such as hourly or daily rainfall extremes. Statistical methods (such as extreme value distribution analysis) are used to identify short-duration heavy rainfall extremes. These extremes are synchronized with the remote sensing image data of the standard area in time, and their spatial distribution trends are analyzed to generate regional short-duration heavy rainfall trend data to describe the spatial distribution and change trends of short-duration heavy rainfall. Rainfall data in a longer period of time (such as monthly or annual rainfall extremes) are analyzed. Extreme values ​​of long-duration rainfall are identified and their change trends are analyzed. These data are combined with remote sensing image data to analyze the long-term impact of rainfall on the regional surface, generate regional long-duration heavy rainfall trend data, and describe the spatial distribution and trend of long-term heavy rainfall. The regional short-duration and long-duration heavy rainfall trend data are integrated, combined with information such as terrain, soil type, and vegetation cover, to analyze the convergence mechanism of heavy rain in the region. Hydrological models (such as watershed models) are used to simulate the heavy rain convergence process, identify the convergence path and convergence point of heavy rain, generate regional heavy rain convergence mechanism data, and describe how heavy rain converges, accumulates water, and drains in the region. Standard regional remote sensing image data are analyzed using flood monitoring station data (such as water level changes, changes in waterlogging areas) to identify the patterns and mechanisms of flood occurrence. Flood monitoring data are combined with rainfall data to analyze the conditions and mechanisms of flood occurrence, generate regional flood mechanism data, and describe the causes, processes, and impacts of flood occurrence on the region. The generated regional short-duration heavy rainfall trend data, regional long-duration heavy rainfall trend data, regional heavy rain convergence mechanism data, and regional flood mechanism data are comprehensively analyzed to verify their consistency and accuracy, and compared with actual heavy rainfall and flood events to verify the accuracy of the model and analysis results.

[0084] Step S3: Compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and the drainage network monitoring data to generate an urban flood model; perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model;

[0085] In an embodiment of the present invention, multi-temporal remote sensing image data of a standard area is collected. These images should cover a sufficiently long period of time to detect changes in the underlying surface. The image data should be preprocessed, including geometric correction, radiation correction, cloud removal and defogging processing. Use remote sensing image classification algorithms (such as supervised classification, unsupervised classification or deep learning methods) to extract impervious surfaces (such as buildings, roads, etc.). Classify images at different time points to generate a spatial distribution map of the impervious surface. Compare the impervious surface data extracted at different time points to identify the changed area. Use change detection technology (such as difference image analysis, change matrix) to calculate the amount of impervious surface change, generate regional underlying surface change data, and describe the spatial distribution and change trend of impervious surface changes. Combine the regional underlying surface change data with flood and tide mechanism data to analyze the impact of underlying surface changes on flood and tide mechanisms. Use hydrological models (such as water flow simulation models, flood and tide models) for optimization analysis, consider the impact of underlying surface changes on flood and tide processes, generate regional flood and tide mechanism optimization data, and describe the optimized flood and tide mechanism and its influencing factors. Collect hydrological and water level station data, including real-time water level, rainfall, flow, etc. Collect drainage network monitoring data, including network flow, pipeline status, rainfall infiltration, etc. Construct an urban flood model based on hydrological and water level station data and drainage network monitoring data. Numerical simulation methods (such as finite element method and finite difference method) can be used to construct the model. Divide the model into a rainfall-runoff model and a drainage network model, comprehensively consider urban topography, land use and pipe network structure, generate an urban flood model, and describe the flood risk and drainage capacity of the urban area. Collect regional stormwater confluence mechanism data and regional flood tide mechanism optimization data. Adjust the parameters of the urban flood model and storm surge model to adapt to the characteristics of regional stormwater confluence and flood tide. Couple the urban flood model with the storm surge model to consider the impact of stormwater confluence mechanism and flood tide mechanism on urban flooding. When implementing model coupling, ensure the accuracy of data transmission and feedback mechanism between models. Conduct joint simulation to analyze the comprehensive impact of stormwater and storm surge on urban flooding. The simulation results of the coupling model are compared with actual flood events to verify the accuracy of the model. According to the verification results, the model parameters and coupling mechanism are adjusted to optimize the urban flood coupling model and generate the output data of the urban flood coupling model, including flood risk areas, flood depth, flow distribution, etc.

[0086] Step S4: regional flood simulation is performed on the standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; maximum flood depth is calculated for the regional flood simulation data to obtain regional flood flood depth simulation data; risk area annotation is performed on the regional geographic division data according to the regional flood flood depth simulation data to generate high-risk area annotation data and low-risk area annotation data; resource allocation simulation optimization is performed on the high-risk area annotation data and the low-risk area annotation data to generate flood control resource allocation optimization data;

[0087] In the embodiment of the present invention, by using the urban flood coupling model and standard regional remote sensing image data, it is ensured that the remote sensing data covers complete terrain, land use and impervious surface information. Ensure that the parameters and input data of the flood model are accurate, covering rainfall intensity, watershed characteristics and drainage system status. Input remote sensing image data to the urban flood coupling model, and perform simulation to predict the performance of floods in different scenarios. The simulation should include rainfall and storm surge conditions of different intensities to cover various possible flood scenarios, generate regional flood simulation data, and record information such as water depth, flow rate, and flood range of each area. Extract the water depth data of each grid unit or area from the regional flood simulation data. Use statistical methods (such as maximum extraction and extreme value analysis) to calculate the maximum flooding depth of each area. Visualize the maximum flooding depth data and generate a regional flood flooding depth simulation data map to describe the water depth distribution of different areas. Set a risk threshold based on the regional flood flooding depth simulation data. For example, mark an area with a water depth greater than a specific value as a high-risk area. Mark an area with a water depth less than the threshold but still presenting a flood risk as a low-risk area. According to the set threshold, the regional geographic division data is labeled with risk areas, and high-risk area labeling data and low-risk area labeling data are generated. Risk maps are made to identify areas of different risk levels. Based on the labeled data of high-risk and low-risk areas, the flood control resource needs of each area, such as sandbags, pumping stations, personnel and equipment, are evaluated. Combined with historical flood event data and resource supply, the resource demand priority of each area is determined. Optimization algorithms (such as linear programming, integer programming or genetic algorithms) are used to simulate resource allocation to minimize risks and optimize resource utilization. The effects of different resource allocation strategies are simulated, their flood control capabilities for high-risk areas are evaluated, and flood control resource allocation optimization data is generated, providing specific resource allocation plans and strategies. Including resource allocation plans, priority ranking and resource scheduling suggestions. Summarize regional flood simulation data, maximum flooding depth data, high-risk area labeling data and flood control resource allocation optimization data. Make a comprehensive report describing the simulation results, risk areas and resource allocation strategies.

[0088] Step S5: Perform three-dimensional heat map conversion on the resource allocation optimization simulation data to generate a three-dimensional flood control resource configuration heat map; perform real-time data stream update and fusion on the three-dimensional flood control resource configuration heat map to generate dynamic heat map update data; perform intelligent emergency decision-making on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0089] In an embodiment of the present invention, by using flood control resource allocation optimization data, including resource type, distribution, quantity and priority. Ensure that the data contains three-dimensional spatial coordinate information so as to generate a three-dimensional heat map. Select appropriate visualization tools or software (such as ParaView, MATLAB, Python's Matplotlib and Plotly library) to generate a three-dimensional heat map. Convert resource configuration data into three-dimensional grid or voxel data, set the color and intensity of the heat map according to resource density or priority, generate a three-dimensional flood control resource configuration heat map, and intuitively display the resource distribution and configuration density of different regions. Integrate real-time data sources, such as meteorological monitoring, sensor data, emergency response data, etc., to ensure the timeliness and accuracy of data flow. Set up a data receiving and processing interface to transmit real-time data to the system. Develop a real-time data processing module to update and merge data streams in real time. Stream processing frameworks (such as Apache Kafka and Apache Flink) can be used for real-time data processing. Preprocess real-time data (such as data cleaning, format conversion) and merge (such as integration with existing data). Update the three-dimensional flood control resource configuration heat map to reflect the latest resource allocation and emergency situation. Generate a dynamic heat map in real time to reflect changes in resource configuration and dynamic data. Ensure that the heat map can be updated in real time and display the latest status. Provide a user interface that allows viewing dynamic heat map update data at different time points or events. Based on the dynamic heat map update data, develop an intelligent decision support system and use artificial intelligence and machine learning algorithms for emergency decision analysis. The system should include decision algorithms such as resource priority sorting, optimal scheduling, demand forecasting, etc. Analyze the current coverage and configuration of flood control resources based on dynamic heat map data. Provide real-time suggestions and solutions through the intelligent decision system, including resource scheduling, emergency response priority, resource replenishment strategy, etc. Implement the suggestions provided by the intelligent decision system for resource scheduling and emergency response. Continuously monitor the execution effect and collect feedback data to optimize the decision support system and resource allocation strategy. Integrate the three-dimensional flood control resource configuration heat map, real-time data flow update module, and intelligent emergency decision system into a unified platform. Ensure data flow and functional coordination between various parts of the system. Maintain the system regularly to ensure the accuracy of the data source and the stability of the system. Update system functions and adjust and optimize according to actual needs.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: using GIS to obtain regional remote sensing image data;

[0092] Step S12: performing data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0093] Step S13: extracting regional geographic features from the standard regional remote sensing image data to obtain regional geographic feature data; dividing the standard regional remote sensing image data into regions according to the regional geographic feature data to generate regional geographic division data;

[0094] Step S14: Screening flood control resource sites of the standard regional remote sensing image data through regional geographic division data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data.

[0095] In an embodiment of the present invention, remote sensing image data of a target area is obtained from a satellite, a drone or other remote sensing equipment by using a geographic information system (GIS). These data include multispectral, thermal infrared, high-resolution images of the region, etc., which can fully reflect the geographical and environmental characteristics of the region. Noise and outliers in remote sensing image data are removed to improve the accuracy and reliability of the data. For missing data in remote sensing image data, missing values ​​are filled by interpolation, prediction or use of other data sources to ensure the integrity of the data. Remote sensing image data from different sources and in different formats are standardized to make them consistent in terms of spatial resolution, spectral range, time span, etc., for subsequent analysis and processing. After data preprocessing, the generated standard area remote sensing image data will be used as the basic data for subsequent steps. By analyzing the standardized remote sensing image data, the geographical feature data of the region is extracted. These features include terrain, land use type, water distribution, vegetation coverage, etc. The extracted geographical feature data will be used to further divide the region. Based on these geographical feature data, the standard area remote sensing image data is divided into regions. Through spatial clustering, classification algorithms or expert knowledge, the region is divided into several sub-regions with similar geographical characteristics to generate regional geographic division data. Select appropriate flood control sites in different regions. According to the regional geographic division data, combined with relevant indicators such as meteorology, flooding, hydrological water level and drainage network, comprehensive evaluation and screening are carried out to generate flood control resource site screening data. The screened data includes: identifying and locating locations suitable for installing meteorological monitoring equipment to monitor meteorological parameters such as rainfall, wind speed, and humidity. Select suitable sites to monitor water level changes and flood warnings in flood risk areas. Determine the site selection of hydrological stations to monitor water level changes in rivers, lakes and other water bodies. Screen and determine the key monitoring points of the drainage network to evaluate the operation status of the urban drainage system. The final output is a screening data set containing multiple key flood control sites.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: Screening the regional rainfall data of the remote sensing image data of the standard area based on the meteorological monitoring station data to obtain the regional rainfall data; analyzing the annual peak rainfall change trend of the regional rainfall data greater than the preset rainfall threshold to generate the regional short-duration heavy rainfall trend data;

[0098] Step S22: Mapping the regional short-duration heavy rainfall trend data to the standard regional remote sensing image data to perform rainfall interannual distribution annotation, and generate regional rainfall interannual distribution data; performing rainfall spatial variation analysis on the regional rainfall interannual distribution data, and generating regional rainfall distribution balance data;

[0099] Step S23: performing precipitation extreme value distribution calculation on regional rainfall data less than or equal to a preset rainfall threshold to generate long-duration regional rainfall extreme value distribution data; performing heavy rainfall change trend analysis on the long-duration regional rainfall extreme value distribution data in recent years to generate regional long-duration heavy rainfall trend data;

[0100] Step S24: performing regional rainstorm convergence mechanism analysis based on the regional short-duration heavy rainfall trend data, the regional rainfall distribution balance data and the regional long-duration heavy rainfall trend data to generate regional rainstorm convergence mechanism data;

[0101] Step S25: Perform regional flood mechanism analysis on the remote sensing image data of the standard area based on the flood monitoring station data to generate regional flood mechanism data.

[0102] In an embodiment of the present invention, by using the meteorological monitoring station data screened out in the previous step, the standard regional remote sensing image data is analyzed to screen out regional rainfall data related to rainfall. The screening process includes spatial interpolation and matching of the rainfall observation data of the meteorological station to generate a detailed regional rainfall distribution. After obtaining the regional rainfall data, the annual peak rainfall change trend analysis is performed on those areas with a rainfall threshold greater than the preset rainfall threshold. This analysis will focus on short-duration heavy rainfall events in these areas, evaluate their inter-annual changes, and generate regional short-duration heavy rainfall trend data. The data reflects the frequency, intensity and time trends of heavy rainfall events in these areas. The regional short-duration heavy rainfall trend data is mapped to the standard regional remote sensing image data. This mapping process combines the spatial and temporal distribution characteristics so that the heavy rainfall change trend in each geographical location is visually marked on the remote sensing image. This process will generate regional rainfall inter-annual distribution data. Based on the rainfall inter-annual distribution data, a spatial variation analysis of rainfall is performed. By analyzing whether the rainfall is evenly distributed in different regions, the regions with uneven rainfall are identified, and regional rainfall distribution balance data is generated. These data are used to identify potential flood risk areas, especially in areas with concentrated or sparse rainfall. For those areas where rainfall is less than or equal to the preset threshold, precipitation extreme value distribution calculations are performed. This calculation aims to identify extreme rainfall events that occur in these areas over a long period of time and generate long-duration regional rainfall extreme value distribution data. Even areas with less rainfall may experience extreme rainfall in certain periods of time. Next, these long-duration regional rainfall extreme value distribution data are analyzed, focusing on the changing trends of heavy rainfall events in these areas in recent years. Through this step, regional long-duration heavy rainfall trend data are generated, which reflects the evolution of heavy rainfall events in these areas on a long time scale. The regional short-duration heavy rainfall trend data, regional rainfall distribution balance data and regional long-duration heavy rainfall trend data obtained in steps S21 to S23 are comprehensively analyzed to perform regional rainstorm convergence mechanism analysis. This analysis aims to understand how water gathers and flows in the region during rainstorms, as well as potential flood risks. Through this analysis, regional rainstorm convergence mechanism data are generated. This data reflects key factors such as the flow path, speed, and waterlogging points of water under heavy rain conditions in different regions, and is an important reference for flood control measures and flood risk assessment. Using data from flood monitoring stations, regional flood mechanism analysis is performed on standard regional remote sensing image data. This process combines data from flood stations with remote sensing images to analyze the flood formation mechanism in the region in detail, determine waterlogging points, flood propagation paths, and their time characteristics, and generate regional flood mechanism data.

[0103] Preferably, step S25 comprises the following steps:

[0104] Step S251: screening the standard regional remote sensing image data for river channels to obtain regional river channel data; connecting the regional river channel data for river channels to generate regional river network data;

[0105] Step S252: Analyze the river network tide characteristics of the regional river network data according to the flood monitoring station data to generate river network tide characteristic data; calculate the flood and tide encounter frequency of the regional river network data according to the river network tide characteristic data to obtain the river network flood and tide encounter frequency data;

[0106] Step S253: Utilizing the river network flood and tide encounter frequency data and the river network tidal level characteristic data, the regional river network data is subjected to regional flood and tide mechanism analysis to generate regional flood and tide mechanism data.

[0107] In an embodiment of the present invention, by utilizing remote sensing image processing technology, river channel and water body information is automatically extracted from standard regional remote sensing image data through methods such as image classification, edge detection and morphological operations. These methods may include multispectral image classification, deep learning-based water body detection algorithms (such as U-Net models), or using terrain elevation data (such as DEM) combined with water flow simulation algorithms to accurately identify and segment river channel areas and generate regional river channel data, which is the distribution information of the river channel in the remote sensing image. Adjacent river channel data are connected using graph theory algorithms (such as shortest path algorithms, network flow analysis, etc.) or terrain-based river channel network generation algorithms to generate coherent regional river network data. This process can be completed using river network generation tools in geographic information systems (GIS) (such as the Hydrology toolset in ArcGIS). Statistical analysis and tidal simulation techniques are used to analyze the tidal characteristics of data from flood monitoring sites. This can include tidal time series analysis, frequency analysis, and hydrological modeling (such as SWMM, HEC-RAS) to simulate tidal changes in the river network. Through these analyses, river network tidal characteristics data are generated, which include tidal height, change rate and fluctuation pattern of different river sections under different time conditions. Through joint probability analysis of flood and tidal events (for example, using Copula function or joint probability distribution model), the frequency of simultaneous occurrence of flood and tide in a specific time period is calculated. This process can be combined with Monte Carlo simulation method or extreme value theory to evaluate the probability of flood encounter under different scenarios, and finally generate river network flood encounter frequency data. Combined with the previously generated river network flood encounter frequency data and river network tidal characteristics data, regional flood mechanism analysis is carried out. Numerical simulation (such as two-dimensional or three-dimensional hydrodynamic model), multi-factor regression analysis or machine learning model (such as random forest, support vector machine) can be used to simulate the propagation process of flood in the river network, the formation of waterlogging points, and potential flood risk areas, and generate regional flood mechanism data. These data describe in detail the behavioral characteristics of the river network system in the region when encountering floods, such as water level rise rate, flow rate change, embankment pressure, etc., providing a comprehensive understanding of flood risks.

[0108] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0109] Step S31: converting the standard area remote sensing image data into geographic elevation data to generate regional geographic elevation data; performing regional impervious surface change comparison on the standard area remote sensing image data based on the regional geographic elevation data to generate regional underlying surface change data; optimizing the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data;

[0110] Step S32: Calculate the rainwater flow rate of the pipe network based on the hydrological water level station data and the drainage pipe network monitoring data to generate rainwater surface runoff simulation data and rainwater surface convergence dynamics data; construct an urban flood model based on the rainwater surface runoff simulation data and rainwater surface convergence dynamics data to generate an urban flood model;

[0111] Step S33: extracting storm surge characteristics from the meteorological monitoring station data to obtain storm surge characteristic data; constructing a storm surge model for the storm surge characteristic data based on the hydrodynamic equation to generate a storm surge model;

[0112] Step S34: Based on the regional rainstorm runoff mechanism data and the regional flood tide mechanism optimization data, the urban flood model and the storm surge model are coupled to generate an urban flood coupling model.

[0113] In an embodiment of the present invention, the standard regional remote sensing image data is converted into three-dimensional geographic elevation data by using the digital elevation model (DEM) technology. This step is usually processed using geographic information system (GIS) software, and the geographic coordinates of the remote sensing image are combined with the elevation data for conversion. Image classification technology, such as support vector machine (SVM) or random forest, is used to classify the surface features in the remote sensing image to distinguish between impervious surfaces (such as buildings, roads) and permeable surfaces (such as grasslands, soil). Then, the image data of different periods are compared to identify the changes in the impervious surface of the region. Based on the change data of the impervious surface, numerical simulation methods, such as geostatistics or spatial analysis, are used to optimize the flood mechanism, including re-evaluating the flood risk area, optimizing the water flow path, etc. Hydrological models, such as SWMM (Storm Water Management Model) or HEC-RAS, are used to combine hydrological water level station data and drainage network monitoring data to calculate the flow of rainwater in the pipe network. Simulate the accumulation and flow of rainwater on the surface after rainfall to generate rainwater surface runoff and convergence dynamics data. Use fluid dynamics equations (such as the Saint-Venant equation) combined with previous rainwater flow data to establish an urban flood model. This step can use finite element analysis (FEA) or computational fluid dynamics (CFD) methods to simulate water flow distribution and water accumulation in urban environments. Extract storm surge characteristic information from meteorological monitoring data, such as tide level, wind speed, and air pressure. Time series analysis technology or spectrum analysis can be used to extract these features. Based on the extracted characteristic data, use hydrodynamic equations (such as the Navier-Stokes equation) to build a storm surge model. Commonly used tools include professional software such as MIKE 21 and Delft3D to simulate storm surge behavior in oceans and coastal areas. Based on the regional rainstorm convergence mechanism and flood tide mechanism optimization data, multi-model coupling technology is used to combine the urban flood model and the storm surge model to generate a more comprehensive urban flood coupling model. This can be achieved through integrated model platforms such as OpenMI or CoupModel, which enable seamless connection of data and dynamic processes between different models.

[0114] Preferably, calculating the network rainwater flow rate based on the hydrological water level station data and the drainage network monitoring data includes:

[0115] Perform time series spectrum analysis on hydrological water level station data to generate hydrological flow spectrum time series data; perform high-precision flow modeling on drainage network monitoring data to generate network fine flow model data;

[0116] Perform multi-scale flow synthesis processing on the hydrological flow spectrum time series data and the pipe network fine flow model data to generate comprehensive flow distribution data; perform terrain-based rainfall runoff simulation on the comprehensive flow distribution data to generate rainwater surface runoff simulation data;

[0117] Dynamically optimize the runoff path of rainwater surface runoff simulation data to generate rainwater surface runoff path optimization data; perform three-dimensional hydrodynamic runoff calculation on the rainwater surface runoff path optimization data to generate rainwater surface runoff dynamics data.

[0118] In the embodiment of the present invention, data from hydrological water level stations are obtained. Time series spectrum analysis is performed on these data. This process generates hydrological flow spectrum time series data by analyzing the frequency characteristics of hydrological data in the time dimension. The data reflects the change pattern and periodicity of hydrological flow in different time periods, which is convenient for further flow model processing. The monitoring data of the drainage network is collected, and a high-precision flow model is established based on these data. The model generates fine flow model data of the network through precise algorithm processing. The model can simulate the flow changes of different nodes and regions in the drainage network, taking into account various influencing factors such as the size of the pipe, the slope and the speed of the water flow. Combined with the hydrological flow spectrum time series data and the fine flow model data of the network, multi-scale flow synthesis processing is performed. The purpose of this processing step is to integrate flow information of different scales to generate comprehensive flow distribution data. The data not only reflects the flow distribution of large scales (such as the entire urban area), but also captures the flow changes of small scales (such as specific drainage network areas). The comprehensive flow distribution data is used in combination with regional terrain information to simulate the flow generation of rainfall runoff. The simulation aims to predict the amount of surface runoff and its distribution under specific rainfall conditions. Through the simulation, rainwater surface runoff simulation data is generated, which provides a basis for the subsequent runoff path optimization. The rainwater surface runoff simulation data is further analyzed to implement dynamic confluence path optimization. This optimization process determines the optimal confluence path by considering the dynamic changes of real-time rainfall and surface flow, and generates rainwater surface confluence path optimization data. This data reflects the optimal path for how rainwater converges and flows on the surface under specific terrain conditions. Based on the optimized rainwater surface confluence path data, three-dimensional hydrodynamic confluence calculations are performed. This step uses a complex hydrodynamic model to simulate the flow of rainwater in three-dimensional space and generate rainwater surface confluence dynamic data.

[0119] Preferably, step S4 comprises the following steps:

[0120] Step S41: performing regional flood simulation on standard regional remote sensing image data through an urban flood coupling model to generate regional flood simulation data;

[0121] Step S42: Calculate the maximum inundation depth of the regional flood simulation data to obtain regional flood inundation depth simulation data; compare the regional flood inundation depth simulation data with a preset standard water depth threshold, and when the regional flood inundation depth simulation data is greater than or equal to the preset standard water depth threshold, mark the regional geographic division data as a high-risk area based on the regional flood inundation depth simulation data to generate high-risk area marking data;

[0122] Step S43: when the regional flood water depth simulation data is less than a preset standard water depth threshold, the regional geographic division data is marked as a low-risk area based on the regional flood water depth simulation data to generate low-risk area marking data;

[0123] Step S44: forecast the demand for flood control resources for the high-risk area labeled data and the low-risk area labeled data to generate regional flood control resource demand forecast data; perform resource allocation simulation optimization on the high-risk area labeled data and the low-risk area labeled data based on the regional flood control resource demand forecast data to generate flood control resource allocation optimization data.

[0124] In an embodiment of the present invention, the standard regional remote sensing image data is simulated by using an urban flood coupling model. This model combines rainwater flow simulation, terrain elevation data, drainage system characteristics, etc., and is simulated by finite difference method or finite element method. Common tools include SWMM (Storm Water Management Model), HEC-RAS (Hydrologic Engineering Center's River Analysis System) and MIKE 11 / 21. Standard regional remote sensing image data, rainfall data, terrain elevation data and drainage system data are input for simulation to generate regional flood simulation data, including simulated flood depth, flow rate and affected area. Flood depth information is extracted from the regional flood simulation data, statistical analysis is performed, and the maximum flooding depth is calculated. These calculations can be performed using spatial analysis tools in GIS software (such as ArcGIS or QGIS). The maximum flooding depth data is compared with a preset standard water depth threshold. If the maximum flooding depth is greater than or equal to the preset standard, it is marked as a high-risk area in the regional geographic division data. The marking is completed using threshold classification technology and spatial analysis tools (such as the raster calculator in ArcGIS). When the simulated data of regional flood inundation depth is less than the preset standard water depth threshold, the regional geographic division data is marked as a low-risk area. Similar to high-risk marking, threshold classification technology and GIS spatial analysis tools are used for marking. Based on the high-risk and low-risk area marking data, statistical models or machine learning models (such as regression analysis, time series analysis) are used to predict the flood control resource needs in different regions. The model includes statistical data of historical flood events, regional population density, and infrastructure loss data. Linear programming or integer programming techniques are used to optimize the allocation of flood control resources. Considering the resource needs of high-risk and low-risk areas, simulation optimization techniques (such as simulated annealing and genetic algorithms) are applied to allocate resources to ensure the effective use of resources.

[0125] Preferably, step S44 includes the following steps:

[0126] Step S441: extracting spatiotemporal risk features from the high-risk area annotated data and the low-risk area annotated data to obtain the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data; performing joint risk assessment on the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data to generate comprehensive risk assessment data;

[0127] Step S442: Divide the comprehensive risk assessment data into data sets to generate a model training set and a model test set; perform model training on the model training set using a time series prediction network algorithm to generate a flood control demand prediction pre-model; perform model optimization iteration on the flood control demand prediction pre-model using the model test set to generate a flood control resource demand prediction model;

[0128] Step S443: Importing the comprehensive risk assessment data into the flood control resource demand prediction model to perform flood control resource demand prediction, and generate regional flood control resource demand prediction data; based on the regional flood control resource demand prediction data, geospatial mapping is performed on the high-risk area annotation data and the low-risk area annotation data to generate a high-risk area resource demand distribution prediction map and a low-risk area resource distribution prediction map;

[0129] Step S444: Perform resource demand intensity analysis on the resource demand distribution forecast map of the high-risk area to generate resource demand intensity data for the high-risk area; optimize resource priority allocation of the high-risk area annotation data according to the resource demand intensity data of the high-risk area to generate flood control resource allocation optimization data for the high-risk area; confirm the basic configuration amount of flood control resources on the resource distribution forecast map of the low-risk area to obtain the basic configuration amount of flood control resources in the low-risk area;

[0130] Step S445: Optimize the resource balance allocation of the low-risk area marked data according to the basic configuration of flood control resources in the low-risk area, and generate the low-risk area flood control resource allocation optimization data; integrate the high-risk area flood control resource allocation optimization data and the low-risk area flood control resource allocation optimization data to generate the flood control resource allocation optimization data.

[0131] In an embodiment of the present invention, spatiotemporal features are extracted from the labeled data of high-risk areas and the labeled data of low-risk areas by using spatiotemporal data analysis technology. These features can be extracted using time series analysis and spatial statistical analysis (such as spatial autocorrelation analysis). Combined with the spatiotemporal feature data of high-risk and low-risk areas, multivariate analysis techniques such as principal component analysis (PCA) and factor analysis are used to perform joint risk assessment. Machine learning models (such as random forests and gradient boosting trees) can also be used for comprehensive risk assessment. The comprehensive risk assessment data is divided into a training set and a test set. An 80 / 20 split ratio is usually used to divide the data into a model training set and a test set. A time series prediction network algorithm (such as a long short-term memory network (LSTM) or a gated recurrent unit (GRU)) is applied to train the model training set to generate a flood control demand forecast pre-model. The pre-model is optimized and iterated using the model test set, and the hyperparameters are adjusted to improve the model performance. Grid search or random search can be used for optimization. The comprehensive risk assessment data is input into the flood control resource demand forecast model to generate regional flood control resource demand forecast data. Map the forecast data in geospatial space to generate resource demand distribution forecast maps for high-risk areas and low-risk areas. Mapping can be done using GIS tools (such as mapping tools in ArcGIS). Analyze the resource demand distribution forecast map for high-risk areas and calculate the resource demand intensity. This can be achieved through methods such as heat map analysis and density analysis. Based on the resource demand intensity data, optimize the resource priority allocation for high-risk areas. Optimization can be performed using linear programming or integer programming techniques. Confirm the basic resource allocation amount for low-risk areas and determine the basic allocation amount based on the data from the resource demand distribution map. Optimize resource balance allocation based on the basic allocation amount of flood control resources in low-risk areas. This can be achieved through optimization algorithms (such as genetic algorithms and simulated annealing). Integrate the flood control resource allocation optimization data for high-risk areas and low-risk areas to generate comprehensive flood control resource allocation optimization data.

[0132] Preferably, step S5 comprises the following steps:

[0133] Step S51: performing multi-dimensional data slicing processing on the resource allocation optimization simulation data to generate multi-dimensional resource distribution slice data; performing high-precision spatial interpolation on the multi-dimensional resource distribution slice data to generate continuous resource distribution grid data;

[0134] Step S52: performing advanced color mapping conversion on the continuous resource distribution grid data to generate two-dimensional color mapping matrix data; performing three-dimensional data visualization processing on the two-dimensional color mapping matrix data to generate a three-dimensional flood control resource configuration heat map;

[0135] Step S53: Update and merge the three-dimensional flood control resource configuration heat map in real time to generate dynamic heat map update data; make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0136] In an embodiment of the present invention, multi-dimensional data slicing processing is performed on the resource allocation optimization simulation data. This can be achieved through data slicing technology or the Numpy library in Python, and the data is sliced ​​to extract information of different dimensions. High-precision spatial interpolation is performed on the multi-dimensional resource distribution slice data. This can be performed using methods such as Kriging interpolation, spline interpolation, or inverse distance weighting (IDW) for high-precision interpolation. Advanced color mapping conversion is performed on the continuous resource distribution grid data to generate two-dimensional color mapping matrix data. Color mapping algorithms such as gradient color mapping can be applied. The two-dimensional color mapping matrix data is subjected to three-dimensional data visualization processing to generate a three-dimensional flood control resource configuration heat map. This can be achieved through three-dimensional visualization tools and virtual reality technology. Real-time data stream update and fusion of the three-dimensional flood control resource configuration heat map. This can be achieved through a data stream processing framework and real-time data update technology. Intelligent emergency decision-making is performed based on dynamic heat map update data to build a flood control resource configuration heat map system. Artificial intelligence and machine learning algorithms (such as decision trees and reinforcement learning) can be used for intelligent decision-making.

[0137] In this specification, a construction system for optimizing scheduling and resource allocation for water conservancy and flood control is provided, which is used to execute the above-mentioned construction method for optimizing scheduling and resource allocation for water conservancy and flood control. The construction system for optimizing scheduling and resource allocation for water conservancy and flood control includes:

[0138] The flood control site acquisition module is used to obtain regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data;

[0139] The rainstorm and flood mechanism analysis module is used to analyze the extreme changes of long-term and short-term rainfall on the remote sensing image data of the standard area based on the data of the meteorological monitoring station, and generate the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data; to analyze the regional rainstorm convergence mechanism through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data, and generate the regional rainstorm convergence mechanism data; to analyze the regional flood mechanism of the standard area remote sensing image data based on the flood monitoring station data, and generate the regional flood mechanism data;

[0140] The model coupling module is used to compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and drainage network monitoring data to generate an urban flood model; and perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model.

[0141] The regional risk labeling module is used to simulate regional floods on standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; calculate the maximum flood depth of the regional flood simulation data to obtain regional flood depth simulation data; label the risk areas of regional geographic division data based on the regional flood depth simulation data to generate high-risk area labeling data and low-risk area labeling data; perform resource allocation simulation optimization on the high-risk area labeling data and the low-risk area labeling data to generate flood control resource allocation optimization data;

[0142] The heat map configuration module is used to convert the resource allocation optimization simulation data into a three-dimensional heat map to generate a three-dimensional flood control resource configuration heat map; to update and fuse the three-dimensional flood control resource configuration heat map with real-time data streams to generate dynamic heat map update data; to make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

[0143] The beneficial effect of the present invention is that by acquiring regional remote sensing image data and preprocessing, a variety of monitoring data related to flood control are screened out, making the data more comprehensive and reliable. By analyzing the changes in long and short-term rainfall extremes, the regional rainfall pattern can be accurately captured, and short-term and long-term heavy rainfall trend data can be generated, providing a basis for flood mechanism analysis, and regional flood mechanism analysis based on flood monitoring station data provides a scientific basis for subsequent flood control work. By analyzing the regional underlying surface change data and optimizing the regional flood mechanism, optimized flood mechanism data is generated. At the same time, an urban flood model is constructed and regional model coupling is performed, which improves the simulation accuracy of flood phenomena and makes flood control work more accurate and scientific. The maximum flood depth is calculated through flood simulation data, the risk area is marked in the region, and resource allocation simulation optimization is performed to ensure that flood control resources can be effectively allocated to high-risk areas and low-risk areas, thereby improving the efficiency and pertinence of resource allocation. The resource allocation optimization simulation data is converted into a three-dimensional flood control resource configuration heat map, and real-time data streams are updated and fused, so that the distribution of flood control resources can be presented intuitively and updated at any time, which improves the real-time and accuracy of emergency management. Through the intelligent emergency decision-making function, a flood control resource configuration heat map system is constructed, which can analyze dynamic data in real time, provide decision support, and help managers make scientific decisions quickly in emergency situations, thereby improving flood control response capabilities. The overall method provides comprehensive technical support for flood control management through precise data processing, optimized models, scientific resource allocation and real-time visualization, and significantly improves the scientificity, efficiency and emergency response capabilities of flood control work. Therefore, the present invention improves the accuracy, efficiency and intelligence level of the flood control resource configuration heat map system through systematic data integration, dynamic comprehensive analysis, model optimization and coupling, precise risk area identification and intelligent real-time updating.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A construction method for optimizing scheduling and resource allocation for water conservancy and flood control, characterized in that: The following steps are involved: Step S1: Acquire regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data; Step S2: Based on the meteorological monitoring station data, the long-term and short-term rainfall extreme value change analysis is performed on the remote sensing image data of the standard area to generate the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data; The regional rainstorm convergence mechanism data is generated by analyzing the regional short-duration heavy rainfall trend data and the regional long-duration heavy rainfall trend data; Based on the data of flood monitoring stations, regional flood mechanism analysis is conducted on standard regional remote sensing image data to generate regional flood mechanism data; Step S3: performing a comparison of regional impervious surface changes on the standard regional remote sensing image data to generate regional underlying surface change data; optimizing the regional flood mechanism data based on the regional underlying surface change data to generate regional flood mechanism optimization data; The urban flood model is constructed based on the hydrological water level station data and drainage network monitoring data to generate an urban flood model; the urban flood model and the storm surge model are coupled with regional models based on the regional rainstorm convergence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model; Step S4: performing regional flood simulation on the standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; performing maximum flood depth calculation on the regional flood simulation data to obtain regional flood depth simulation data; According to the regional flood inundation depth simulation data, the regional geographic division data is labeled with risk areas to generate high-risk area labeling data and low-risk area labeling data; Perform resource allocation simulation optimization on the labeled data of high-risk areas and low-risk areas to generate optimized data on flood control resource allocation; Step S5: converting the resource allocation optimization simulation data into a three-dimensional heat map to generate a three-dimensional flood control resource configuration heat map; Update and merge the three-dimensional flood control resource configuration heat map with real-time data streams to generate dynamic heat map update data; Intelligent emergency decision-making is carried out on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

2. The construction method for optimizing scheduling and resource allocation for water conservancy and flood control according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: using GIS to obtain regional remote sensing image data; Step S12: performing data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization; Step S13: extracting regional geographic features from the standard regional remote sensing image data to obtain regional geographic feature data; dividing the standard regional remote sensing image data into regions according to the regional geographic feature data to generate regional geographic division data; Step S14: Screening flood control resource sites of the standard regional remote sensing image data through regional geographic division data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data.

3. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 1 is characterized in that: Step S21 includes the following steps: Step S21: Screening the regional rainfall data of the remote sensing image data of the standard area based on the meteorological monitoring station data to obtain the regional rainfall data; analyzing the annual peak rainfall change trend of the regional rainfall data greater than the preset rainfall threshold to generate the regional short-duration heavy rainfall trend data; Step S22: Mapping the regional short-duration heavy rainfall trend data to the standard regional remote sensing image data to perform rainfall interannual distribution annotation, and generate regional rainfall interannual distribution data; performing rainfall spatial variation analysis on the regional rainfall interannual distribution data, and generating regional rainfall distribution balance data; Step S23: performing precipitation extreme value distribution calculation on regional rainfall data less than or equal to a preset rainfall threshold to generate long-duration regional rainfall extreme value distribution data; performing heavy rainfall change trend analysis on the long-duration regional rainfall extreme value distribution data in recent years to generate regional long-duration heavy rainfall trend data; Step S24: performing regional rainstorm convergence mechanism analysis based on the regional short-duration heavy rainfall trend data, the regional rainfall distribution balance data and the regional long-duration heavy rainfall trend data to generate regional rainstorm convergence mechanism data; Step S25: Perform regional flood mechanism analysis on the remote sensing image data of the standard area based on the flood monitoring station data to generate regional flood mechanism data.

4. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 3 is characterized in that: Step S25 includes the following steps: Step S251: screening the standard regional remote sensing image data for river channels to obtain regional river channel data; connecting the regional river channel data for river channels to generate regional river network data; Step S252: Analyze the river network tide characteristics of the regional river network data according to the flood monitoring station data to generate river network tide characteristic data; calculate the flood and tide encounter frequency of the regional river network data according to the river network tide characteristic data to obtain the river network flood and tide encounter frequency data; Step S253: Utilizing the river network flood and tide encounter frequency data and the river network tidal level characteristic data, the regional river network data is subjected to regional flood and tide mechanism analysis to generate regional flood and tide mechanism data.

5. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: converting the standard area remote sensing image data into geographic elevation data to generate regional geographic elevation data; performing regional impervious surface change comparison on the standard area remote sensing image data based on the regional geographic elevation data to generate regional underlying surface change data; optimizing the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; Step S32: Calculate the rainwater flow rate of the pipe network based on the hydrological water level station data and the drainage pipe network monitoring data to generate rainwater surface runoff simulation data and rainwater surface convergence dynamics data; construct an urban flood model based on the rainwater surface runoff simulation data and rainwater surface convergence dynamics data to generate an urban flood model; Step S33: extracting storm surge characteristics from the meteorological monitoring station data to obtain storm surge characteristic data; constructing a storm surge model for the storm surge characteristic data based on the hydrodynamic equation to generate a storm surge model; Step S34: Based on the regional rainstorm runoff mechanism data and the regional flood tide mechanism optimization data, the urban flood model and the storm surge model are coupled to generate an urban flood coupling model.

6. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 5 is characterized in that: The network rainwater flow calculation based on the hydrological water level station data and drainage network monitoring data includes: Perform time series spectrum analysis on hydrological water level station data to generate hydrological flow spectrum time series data; perform high-precision flow modeling on drainage network monitoring data to generate network fine flow model data; Perform multi-scale flow synthesis processing on the hydrological flow spectrum time series data and the pipe network fine flow model data to generate comprehensive flow distribution data; perform terrain-based rainfall runoff simulation on the comprehensive flow distribution data to generate rainwater surface runoff simulation data; Dynamically optimize the runoff path of rainwater surface runoff simulation data to generate rainwater surface runoff path optimization data; perform three-dimensional hydrodynamic runoff calculation on the rainwater surface runoff path optimization data to generate rainwater surface runoff dynamics data.

7. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing regional flood simulation on standard regional remote sensing image data through an urban flood coupling model to generate regional flood simulation data; Step S42: Calculate the maximum inundation depth of the regional flood simulation data to obtain regional flood inundation depth simulation data; compare the regional flood inundation depth simulation data with a preset standard water depth threshold, and when the regional flood inundation depth simulation data is greater than or equal to the preset standard water depth threshold, mark the regional geographic division data as a high-risk area based on the regional flood inundation depth simulation data to generate high-risk area marking data; Step S43: when the regional flood water depth simulation data is less than a preset standard water depth threshold, the regional geographic division data is marked as a low-risk area based on the regional flood water depth simulation data to generate low-risk area marking data; Step S44: forecast the demand for flood control resources for the high-risk area labeled data and the low-risk area labeled data to generate regional flood control resource demand forecast data; perform resource allocation simulation optimization on the high-risk area labeled data and the low-risk area labeled data based on the regional flood control resource demand forecast data to generate flood control resource allocation optimization data.

8. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 7 is characterized in that: Step S44 includes the following steps: Step S441: extracting spatiotemporal risk features from the high-risk area annotated data and the low-risk area annotated data to obtain the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data; performing joint risk assessment on the high-risk area spatiotemporal feature data and the low-risk area spatiotemporal feature data to generate comprehensive risk assessment data; Step S442: Divide the comprehensive risk assessment data into data sets to generate a model training set and a model test set; perform model training on the model training set using a time series prediction network algorithm to generate a flood control demand prediction pre-model; perform model optimization iteration on the flood control demand prediction pre-model using the model test set to generate a flood control resource demand prediction model; Step S443: Importing the comprehensive risk assessment data into the flood control resource demand prediction model to perform flood control resource demand prediction, and generate regional flood control resource demand prediction data; based on the regional flood control resource demand prediction data, geospatial mapping is performed on the high-risk area annotation data and the low-risk area annotation data to generate a high-risk area resource demand distribution prediction map and a low-risk area resource distribution prediction map; Step S444: Perform resource demand intensity analysis on the resource demand distribution forecast map of the high-risk area to generate resource demand intensity data for the high-risk area; optimize resource priority allocation of the high-risk area annotation data according to the resource demand intensity data of the high-risk area to generate flood control resource allocation optimization data for the high-risk area; confirm the basic configuration amount of flood control resources on the resource distribution forecast map of the low-risk area to obtain the basic configuration amount of flood control resources in the low-risk area; Step S445: Optimize the resource balance allocation of the low-risk area marked data according to the basic configuration of flood control resources in the low-risk area, and generate the low-risk area flood control resource allocation optimization data; integrate the high-risk area flood control resource allocation optimization data and the low-risk area flood control resource allocation optimization data to generate the flood control resource allocation optimization data.

9. The construction method for optimizing scheduling and resource allocation related to water conservancy and flood control according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: performing multi-dimensional data slicing processing on the resource allocation optimization simulation data to generate multi-dimensional resource distribution slice data; performing high-precision spatial interpolation on the multi-dimensional resource distribution slice data to generate continuous resource distribution grid data; Step S52: performing advanced color mapping conversion on the continuous resource distribution grid data to generate two-dimensional color mapping matrix data; performing three-dimensional data visualization processing on the two-dimensional color mapping matrix data to generate a three-dimensional flood control resource configuration heat map; Step S53: Update and merge the three-dimensional flood control resource configuration heat map in real time to generate dynamic heat map update data; make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

10. A construction system for optimizing scheduling and resource allocation for water conservancy and flood control, characterized in that: The method for constructing the optimal dispatching and resource allocation for water conservancy and flood control according to claim 1 comprises: The flood control site acquisition module is used to obtain regional remote sensing image data; perform data preprocessing on the regional remote sensing image data to generate standard regional remote sensing image data; perform flood control resource site screening on the standard regional remote sensing image data to obtain flood control resource site screening data, wherein the flood control resource site screening data includes meteorological monitoring site data, flood monitoring site data, hydrological water level site data and drainage network monitoring data; The rainstorm and flood mechanism analysis module is used to analyze the extreme changes of long-term and short-term rainfall on the remote sensing image data of the standard area based on the data of the meteorological monitoring station, and generate the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data; to analyze the regional rainstorm convergence mechanism through the regional short-term heavy rainfall trend data and the regional long-term heavy rainfall trend data, and generate the regional rainstorm convergence mechanism data; to analyze the regional flood mechanism of the standard area remote sensing image data based on the flood monitoring station data, and generate the regional flood mechanism data; The model coupling module is used to compare the regional impervious surface changes with the standard regional remote sensing image data to generate regional underlying surface change data; optimize the regional flood mechanism data according to the regional underlying surface change data to generate regional flood mechanism optimization data; construct an urban flood model based on the hydrological water level station data and drainage network monitoring data to generate an urban flood model; and perform regional model coupling on the urban flood model and the storm surge model based on the regional rainstorm confluence mechanism data and the regional flood mechanism optimization data to generate an urban flood coupling model. The regional risk labeling module is used to simulate regional floods on standard regional remote sensing image data through the urban flood coupling model to generate regional flood simulation data; calculate the maximum flood depth of the regional flood simulation data to obtain regional flood depth simulation data; label the risk areas of regional geographic division data based on the regional flood depth simulation data to generate high-risk area labeling data and low-risk area labeling data; perform resource allocation simulation optimization on the high-risk area labeling data and the low-risk area labeling data to generate flood control resource allocation optimization data; The heat map configuration module is used to convert the resource allocation optimization simulation data into a three-dimensional heat map to generate a three-dimensional flood control resource configuration heat map; to update and fuse the three-dimensional flood control resource configuration heat map with real-time data streams to generate dynamic heat map update data; to make intelligent emergency decisions on the dynamic heat map update data, thereby building a flood control resource configuration heat map system to perform flood control resource emergency decision support operations.

Images