Surface water resource dynamic prediction method under digital twinborn condition

Abstract

The invention provides a surface water resource dynamic prediction method under digital twinning, and relates to the technical field of water resource management, and the method comprises the steps: obtaining hydrogeological monitoring data; transmitting to a digital twin module, and constructing a hydrogeological model; obtaining a surface water resource scheduling instruction; introducing a surface water resource scheduling risk prediction module, and performing water resource scheduling risk prediction in combination with a hydrogeological model and a surface water resource scheduling scheme; if the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, optimizing and adjusting the surface water resource scheduling scheme; and on the basis of the future time zone, surface water resource scheduling is executed according to the water resource scheduling optimization strategy. According to the method and the device, the technical problem of low efficiency of water resource management caused by excessive development or waste due to the fact that water resource scheduling cannot adapt to a rapidly changing natural environment in the prior art can be solved, water resource scheduling is performed by combining digital twinning, and the accuracy and efficiency of surface water resource management are improved.

Description

Technical Field

[0001] The present application relates to the technical field of water resource management, and in particular to a method for dynamic prediction of surface water resources under digital twins. Background Art

[0002] Dynamic prediction of surface water resources refers to the establishment of a model to predict the changing trend of surface water resources in the future by conducting a comprehensive analysis of various natural factors such as hydrology, meteorology, and geology. It can not only reasonably dispatch water resources and reduce resource waste, but also respond to extreme climate events (such as droughts, floods, etc.) in advance. Existing water resource scheduling methods mostly rely on static models or historical data, which are difficult to reflect hydrological and meteorological changes in real time. When faced with extreme weather or sudden hydrological events, it is impossible to provide timely and accurate predictions, and the scheduling plan may deviate or be unsuitable for the rapidly changing environment, resulting in waste or shortage of water resources. In addition, the existing water resource scheduling methods lack a comprehensive assessment of the risks of the scheduling plan, especially when faced with unpredictable extreme events (such as floods, droughts, etc.), it is difficult to carry out effective risk control, which may lead to unreasonable scheduling and even cause resource conflicts or waste.

[0003] In summary, the existing technology has the technical problem that water resource scheduling cannot adapt to the rapidly changing natural environment, resulting in over-exploitation or waste, leading to inefficient water resource management. Summary of the invention

[0004] The purpose of this application is to provide a dynamic prediction method for surface water resources under digital twins, so as to solve the technical problems in the prior art that water resource scheduling cannot adapt to the rapidly changing natural environment, resulting in over-exploitation or waste, leading to inefficient water resource management.

[0005] In view of the above problems, the present application provides a dynamic prediction method for surface water resources under digital twins, wherein the dynamic prediction method for surface water resources under digital twins includes: obtaining hydrogeological monitoring data of the region according to a multi-source monitoring module; transmitting the hydrogeological monitoring data to the digital twin module to construct a hydrogeological model; obtaining surface water resource scheduling instructions for the region, wherein the surface water resource scheduling instructions include a surface water resource scheduling plan corresponding to a future time zone; introducing a surface water resource scheduling risk prediction module, combining the hydrogeological model and the surface water resource scheduling plan to perform water resource scheduling risk prediction on the region, and obtaining a water resource scheduling risk prediction result; judging whether the water resource scheduling risk prediction result meets the water resource scheduling risk constraint; if the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, optimizing and adjusting the surface water resource scheduling plan according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy; based on the future time zone, executing surface water resource scheduling in the region according to the water resource scheduling optimization strategy.

[0006] The technical solution provided in this application has at least the following technical effects or advantages:

[0007] According to the multi-source monitoring module, the hydrogeological monitoring data of the region is obtained; the hydrogeological monitoring data is transmitted to the digital twin module to construct a hydrogeological model; the surface water resource scheduling instructions of the region are obtained, wherein the surface water resource scheduling instructions include a surface water resource scheduling plan corresponding to the future time zone; a surface water resource scheduling risk prediction module is introduced, and water resource scheduling risk prediction is performed on the region in combination with the hydrogeological model and the surface water resource scheduling plan to obtain a water resource scheduling risk prediction result; it is determined whether the water resource scheduling risk prediction result meets the water resource scheduling risk constraint; if the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, the surface water resource scheduling plan is optimized and adjusted according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy; based on the future time zone, the surface water resource scheduling of the region is executed according to the water resource scheduling optimization strategy. That is to say, by collecting regional hydrogeological monitoring data and transmitting it to the digital twin module, a detailed hydrogeological model is constructed, surface water resource scheduling instructions are obtained and scheduling risk predictions are carried out, and optimization and adjustment are carried out according to the risk prediction results, thereby reducing losses caused by emergencies or unreasonable scheduling and improving the accuracy and efficiency of surface water resource management.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a flow chart of the surface water resources dynamic prediction method based on the digital twin of this application;

[0011] Figure 2 This is a flow chart of obtaining the water resources scheduling optimization strategy in the dynamic prediction method of surface water resources under the digital twin of this application. DETAILED DESCRIPTION

[0012] This application solves the technical problem in the prior art that water resource management is inefficient due to over-exploitation or waste caused by the inability of water resource scheduling to adapt to the rapidly changing natural environment by providing a dynamic prediction method for surface water resources under digital twins. By collecting regional hydrogeological monitoring data and transmitting it to the digital twin module, a detailed hydrogeological model is constructed, surface water resource scheduling instructions are obtained and scheduling risk prediction is performed, and optimization and adjustment are performed according to the risk prediction results, reducing losses caused by emergencies or unreasonable scheduling, and improving the accuracy and efficiency of surface water resource management.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] For examples, please see the attached Figure 1The present application provides a method for dynamic prediction of surface water resources under digital twins, wherein the method for dynamic prediction of surface water resources under digital twins specifically includes the following steps:

[0015] S100: Obtaining regional hydrogeological monitoring data according to a multi-source monitoring module.

[0016] Specifically, comprehensive real-time data on the hydrogeological conditions of the target area are obtained through a variety of monitoring methods, including at least hydrological data (such as precipitation, runoff, groundwater level, river level, evaporation, etc.), geological data (such as groundwater permeability, soil moisture content, rock type, etc.), and ecological data (such as vegetation cover, wetland water level, ecological water volume, etc.). Hydrogeological monitoring data involves the distribution, flow, quality and related geological characteristics of surface water and groundwater. A region refers to a specific geographical area that needs to be paid attention to in the process of surface water resource management or scheduling, which may be a river basin, a reservoir basin, or a specific water resource supply and demand area. Different target areas have different hydrogeological conditions, climate characteristics and water demand, so targeted monitoring and management are required.

[0017] The multi-source monitoring module refers to a module that integrates multiple monitoring methods and data sources, including meteorological data, remote sensing data, hydrological monitoring data, soil moisture data, watershed water use data, etc. For example, ground meteorological stations provide rainfall and temperature data, satellite remote sensing provides soil moisture and vegetation coverage, groundwater monitoring wells are used to provide groundwater level change data, and river flow meters provide river flow information. The hydrogeological monitoring data obtained through the multi-source monitoring module provides accurate basic data support for the dynamic prediction of the entire surface water resources, which can accurately understand the hydrological and geological conditions of the target area, thereby improving the accuracy of water resources prediction.

[0018] S200: Transmitting the hydrogeological monitoring data to the digital twin module to construct a hydrogeological model.

[0019] Specifically, the hydrogeological monitoring data is preprocessed to remove errors, missing data, duplicate data and inconsistent data, so that it meets specific quality standards and usage requirements, and the digital twin module can accurately identify it. The preprocessed data is input into the digital twin module through a data transmission system (such as wireless communication, satellite communication, optical fiber communication, etc.), and the hydrological data (such as precipitation, flow, water level, etc.) in the hydrogeological monitoring data is completed through hydrological modeling tools (such as HEC-HMS, SWAT model, etc.) to complete the modeling of the hydrological model, simulating the water flow, evaporation, precipitation and runoff in the region; the geological data (such as soil permeability, groundwater level, rock structure, etc.) in the hydrogeological monitoring data is completed through geological modeling tools (such as MODFLOW, Feflow and other groundwater modeling software) to complete the modeling of the geological model, simulating how water flows through different soil layers and how they are affected by geological conditions.

[0020] The digital twin module integrates the regional hydrological model and the regional geological model to generate a comprehensive hydrogeological model, taking into account the impact of hydrological and geological factors on water resource management. Once constructed, the hydrogeological model will output prediction results, including hydrological process prediction, underground flowing water prediction, etc. The hydrogeological model generated by the digital twin module accurately simulates and predicts the dynamic changes of water resources, provides a comprehensive basis for water resource scheduling decisions, avoids over-exploitation or waste of resources, and improves the utilization efficiency and management level of water resources.

[0021] S300: Obtaining a surface water resource scheduling instruction for the area, wherein the surface water resource scheduling instruction includes a surface water resource scheduling plan corresponding to a future time zone.

[0022] Specifically, obtain the surface water resource dispatching instructions for the region, including the surface water resource dispatching plan for the future period of time. The surface water resource dispatching instructions are the decisions made by the management department on the use, allocation and dispatch of water resources in a certain area, involving water resource allocation plans, water use priorities, dispatching strategies and other contents in different time periods. The surface water resource dispatching plan determines the water resource allocation strategy based on various factors such as water demand, ecological demand, emergency demand, etc. in different regions. It is used to guide the management and allocation of surface water resources in the future time zone, including how to allocate water resources, when to release water from reservoirs, how to deal with possible droughts or floods, control the direction of water flow, and adjust the amount of water in the irrigation system.

[0023] By simulating the future water resources situation, the water demand of each water-using area in the future period is calculated, and it is matched with the current water resources reserve, precipitation forecast and other factors in order to formulate a reasonable scheduling plan. The future time zone refers to the time period that has not yet arrived but requires advance planning and decision-making. It predicts and simulates the hydrogeological and environmental conditions of a certain area in the future (such as a week, a month or a season). By simulating the changes in water resources under different scenarios, water resource scheduling instructions for future time zones are automatically generated to avoid excessive waste or shortage of resources and optimize the efficiency of water resource use.

[0024] S400: introducing a surface water resource scheduling risk prediction module, and performing water resource scheduling risk prediction for the region in combination with the hydrogeological model and the surface water resource scheduling plan to obtain a water resource scheduling risk prediction result.

[0025] Specifically, we first conduct regional environmental forecasts, that is, we predict environmental changes in the future based on historical meteorological data and environmental trends. According to the regional environmental forecast results, we combine the predicted environmental forecast results with the hydrogeological model to simulate water resource scheduling. Through computer simulation, we combine the hydrogeological model to predict the effect of the water resource scheduling plan, especially to evaluate the performance of water resource allocation, water supply guarantee, water quality and disaster risk under the scheduling plan. We input environmental forecast data (such as precipitation, temperature, evaporation, etc.) into the hydrogeological model to simulate the flow and use of water resources under the scheduling plan, such as reservoir scheduling, river flow regulation, etc., and evaluate the stability and reliability of the scheduling plan under different time periods and climate conditions.

[0026] The water resource scheduling simulation results are input into the surface water resource scheduling risk prediction module to predict the risks of the scheduling plan, including water supply security risk, water quality risk and hydrogeological disaster risk. Based on the simulation results, determine whether the scheduling plan can guarantee sufficient water supply, focusing on future changes in water sources and whether the scheduling plan can meet various water needs. Determine whether the scheduling plan will have the risk of water pollution. For example, excessive reservoir water release can cause eutrophication or pollutant diffusion, affecting water quality. Evaluate whether the water resource scheduling plan may cause hydrogeological disasters, especially in disaster-prone areas. For example, excessive scheduling of reservoirs or rivers may lead to disasters such as dam breaches, floods, and landslides.

[0027] After predicting water supply security risks, water quality risks and hydrogeological disaster risks, the water resources scheduling risk prediction results are obtained, and the risk assessment information of the scheduling plan is provided to determine the existing risks. Through the water resources scheduling risk prediction module, potential water supply security, water quality and disaster risks can be identified and prevented in advance, effectively avoiding water quality pollution and hydrogeological disasters caused by the scheduling plan, and ensuring the stability of the ecological environment of the water source.

[0028] S500: Determine whether the water resource scheduling risk prediction result meets the water resource scheduling risk constraint.

[0029] S600: If the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, the surface water resource scheduling plan is optimized and adjusted according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy.

[0030] Specifically, determine whether the water resources scheduling risk prediction results meet the water resources scheduling risk constraints, obtain the water supply security risk coefficient, water quality risk coefficient and hydrogeological disaster risk coefficient from the water resources scheduling risk prediction module, compare the water supply security risk coefficient, water quality risk coefficient and hydrogeological disaster risk coefficient with the water supply security risk constraint, water quality risk constraint and hydrogeological disaster risk constraint in the water resources scheduling risk constraint, and determine whether there are risk indicators that are lower than or equal to the specified safety threshold. If all risk indicators meet the constraints, the scheduling plan is considered feasible; if any risk indicator exceeds the threshold, the scheduling plan is considered to have unacceptable risks and needs to be adjusted.

[0031] When the water resource scheduling risk prediction results do not meet the water resource scheduling risk constraints, the existing scheduling scheme is further optimized through optimization algorithms (such as particle swarm optimization, genetic algorithm, etc.), and its various risk indicators are optimized by adjusting scheduling parameters, optimizing resource allocation, modifying scheduling strategies, etc., until all risk indicators are within the tolerance range. Obtain the water resource scheduling target of the surface water resource scheduling scheme, search for scheduling schemes in the region, analyze the triggering characteristics, and determine which conditions (such as reservoir water level exceeding the warning line) will trigger the scheme adjustment. Define a spatial range based on the triggering characteristics, adjust the surface water resource scheduling scheme that does not meet the water resource scheduling risk constraints, and generate an adjusted scheme set.

[0032] The adjusted scheme is predicted through the surface water resource scheduling risk prediction module, and the prediction results are judged in combination with the water resource scheduling risk constraints, and all scheme sets that meet the water resource scheduling risk constraints are retained. Weights are assigned to water supply security risks, water quality risks, and hydrogeological disaster risks, and a multi-factor risk assessment framework is constructed to comprehensively evaluate the impact of different types of risks on water resource scheduling. The relevant data of each scheme in the second space of water resource scheduling adjustment are input into the comprehensive risk assessment channel, and the comprehensive risk value of each scheme is calculated. This value is the weighted average of each individual risk coefficient and its corresponding weight. The optimization algorithm (such as genetic algorithm, particle swarm optimization, multi-objective optimization, etc.) is used to search for the scheme with the minimum comprehensive risk in the second space, and the scheme parameters are continuously adjusted through an iterative process to find the scheme that minimizes the comprehensive risk value.

[0033] After optimization and adjustment, a new water resource scheduling plan is obtained, called the water resource scheduling optimization strategy. Under the premise of ensuring that the water resource scheduling risk constraints are met, the use and allocation of water resources are optimized to achieve the best scheduling effect. The water resource scheduling optimization strategy finally generated needs to re-risk prediction to verify whether it meets all water resource scheduling risk constraints. If the new scheduling plan still cannot meet the constraints, optimization and adjustment will continue until an optimal plan that meets the risk constraints is generated. By optimizing the water resource scheduling plan, the scheduling strategy can be dynamically adjusted according to real-time environmental changes and water resource conditions to ensure the rational allocation of resources and minimize risks. By continuously optimizing the scheduling plan, the risks of water supply security, water pollution and hydrogeological disasters can be reduced, thereby improving the safety of water resource management.

[0034] S700: Based on the future time zone, perform surface water resource scheduling in the area according to the water resource scheduling optimization strategy.

[0035] Specifically, according to the water resource scheduling optimization strategy, specific scheduling decisions are executed in the future time zone, including water resource allocation, scheduling plan and risk control measures. When executing the scheduling, the goal is to ensure that various needs are met in the future time zone without exceeding the risk constraints by adjusting the allocation of various water resources. According to the data of climate, water demand, existing water resources and other data in the future time zone, they are input into the water resource scheduling system, and real-time prediction is performed based on the input data. According to the current water resource status and prediction results, a reasonable water resource allocation plan is determined.

[0036] According to the water resource demand of different demand areas (such as drinking water, agricultural water, industrial water, etc.), water resource scheduling optimization strategy is used to allocate, control facilities such as reservoirs, rivers and irrigation systems, and dispatch water sources on demand. During the implementation of water resource scheduling, the use of water sources, rainfall, changes in water demand, etc. are continuously monitored and adjusted in time. If it is found that water resource scheduling deviates from the predetermined target, feedback adjustments are made to ensure that the scheduling plan always meets the set risk constraints. By executing surface water resource scheduling according to the water resource scheduling optimization strategy in future time zones, planning and responding to possible water supply challenges such as droughts or floods in advance will help improve the efficiency and effectiveness of water resource management and reduce the risks caused by poor water resource management.

[0037] Further, the present application S200 includes:

[0038] S210: Perform data cleaning according to the hydrogeological monitoring data to obtain hydrological monitoring standard data and geological monitoring standard data; S220: Input the hydrological monitoring standard data into the digital twin module to obtain a regional hydrological model; S230: Based on the digital twin module, perform modeling according to the geological monitoring standard data to generate a regional geological model; S240: Fusion the regional hydrological model and the regional geological model to generate the hydrogeological model.

[0039] Specifically, hydrogeological monitoring data may have missing values, outliers, or inconsistent formats. The collected hydrogeological monitoring data is cleaned to remove errors, missing, duplicate, and inconsistent data to make it meet specific quality standards and usage requirements. For example, suppose that in the data of a hydrological monitoring station, the water level data for a certain period is missing, or some data points have obvious errors (such as negative water level values). Through data cleaning, these outliers can be deleted, missing values ​​can be filled (such as using surrounding data for interpolation or prediction), and the integrity and accuracy of the data can be ensured.

[0040] The cleaned hydrogeological monitoring data are divided into hydrological monitoring standard data and geological monitoring standard data according to the data type. The hydrological monitoring standard data refers to the hydrological data after data cleaning and processing, which meets certain quality standards and can accurately reflect the hydrological conditions of the region, such as precipitation, flow, water level, etc. The geological monitoring standard data refers to the geological data that meets the quality standards after data cleaning, such as groundwater level, soil permeability, rock and soil layer distribution, etc.

[0041] By inputting the hydrological monitoring standard data into the digital twin module, the regional hydrological model is generated by using simulation technology (such as hydrological simulation algorithms, statistical models, physical models, etc.). After the hydrological monitoring standard data is input into the digital twin module, a regional hydrological model is generated according to the hydrological monitoring standard data and the corresponding hydrological physical processes (such as precipitation, evaporation, runoff, soil infiltration, etc.). Usually, a certain hydrological simulation algorithm (such as precipitation-runoff model, hydrological cycle model, etc.) is used to simulate the hydrological process in the region. The generated regional hydrological model can reflect the hydrological conditions in the region in real time. It can not only evaluate the current water resources situation, but also predict the dynamic changes of water resources in the future, such as flow, changes in river water levels, precipitation and evaporation in the region, etc. The precipitation-runoff model is used to simulate the process of precipitation conversion into runoff, such as the SCS-CN model, the HEC-HMS model, etc.; the hydrological cycle model is used to simulate the circulation process of water in the atmosphere, soil and water bodies; the distributed hydrological model is used to consider the hydrological model with spatial distribution differences for more refined simulation.

[0042] At the same time, the collected geological monitoring data and the digital twin module are used to generate a virtual geological model. By inputting standard geological data (such as soil type, groundwater level, etc.), the digital twin module creates a virtual geological model to simulate the flow of groundwater, soil permeability, and the distribution of rock and soil layers. The regional geological model is a virtual model built in the digital twin module based on geological monitoring standard data. It describes the geological characteristics of a region by simulating different characteristics of the geological environment (such as soil layers, rock and soil structure, groundwater flow, etc.) and is used to analyze geological factors such as changes in groundwater resources and the impact of soil permeability on water flow. The regional geological model shows the distribution of different soil layers and rock layers, the flow path of groundwater, and the way water and soil interact. It not only describes the type of soil, groundwater level, and rock and soil layer distribution, but also simulates how these geological factors interact to affect the distribution and flow of water resources. The regional geological model can not only generate static geological maps, but also realize dynamic updates. That is to say, when new monitoring data (such as changes in groundwater levels, new soil test data, etc.) is input into the digital twin module, the model can be updated in real time and reflect the latest geological status. It can cope with rapidly changing environmental conditions, such as sudden precipitation events, changes in soil types, etc.

[0043] The hydrological model and the geological model are integrated to generate a hydrogeological model, which comprehensively considers the impact of hydrological processes and geological conditions on water resources, provides more comprehensive support for the management and dispatch of water resources, and considers the changes in groundwater, soil permeability, and the impact of geological conditions on water flow when predicting water resources. By integrating the hydrological model and the geological model, we can fully understand the dynamic changes of water resources in the region and improve the accuracy of prediction.

[0044] Further, the present application S400 includes:

[0045] S410: Based on the future time zone, perform environmental prediction on the region to obtain regional environmental prediction results; S420: Based on the regional environmental prediction results, simulate water resource scheduling for the hydrogeological model according to the surface water resource scheduling plan to obtain water resource scheduling simulation data; S430: Input the water resource scheduling simulation data into the surface water resource scheduling risk prediction module to generate the water resource scheduling risk prediction results.

[0046] Specifically, according to the future time zone, the regional environment is predicted to obtain the regional environmental prediction results. That is to say, according to the meteorological, hydrological, soil and other data of the future time zone, the model is used to predict the changes in the environment in the future period of time. Environmental prediction models are usually based on meteorological principles, and are trained and predicted using statistical regression models, physical process models (such as precipitation-runoff models), machine learning algorithms, etc. According to historical data (such as historical precipitation, temperature, humidity data), regression analysis is used to predict future meteorological changes and predict temperature, precipitation, etc. in the future period of time. The model is trained using historical data, and the results of model training (the predicted environmental data for the next time period predicted based on the data of a certain time period) are compared with the actual data of historical data (the actual environmental data for the next time period), and the model parameters are adjusted according to the differences to minimize the prediction error.

[0047] The regional environmental prediction results are predicted, that is, the environmental prediction results of the region in the future time zone, including changes in precipitation, temperature, humidity, wind speed and other factors in the future. According to the predicted regional environmental prediction results, combined with the surface water resource scheduling plan, the hydrogeological model is simulated for water resource scheduling. The hydrogeological model is a multi-physics field model that integrates the hydrological model and the geological model. It is a mathematical model that can describe hydrological processes such as groundwater flow, precipitation, evaporation, evapotranspiration, groundwater recharge, and soil moisture movement.

[0048] Based on the water resource scheduling plan, the hydrogeological model will simulate hydrogeological processes such as precipitation, evaporation, flow, water storage, etc., and predict the water resource allocation after the scheduling plan is implemented. The water resource scheduling plan is input into the hydrogeological model, including various water allocations (agriculture, industry, life, ecology, etc.) and basin scheduling (for example, by reducing irrigation water, increasing the priority of urban water supply, etc.). After that, the environmental prediction results (such as precipitation, temperature, humidity, etc.) are input into the hydrogeological model, and different water resource use scenarios are simulated according to the scheduling plan. The hydrogeological model will output the changes in various hydrological parameters (such as reservoir water level, basin flow, groundwater level, etc.), reflecting the dynamic changes of water resources under the scheduling plan.

[0049] After completing the simulation of the hydrogeological model, the water resources scheduling simulation data is obtained, including reservoir water level, basin flow, groundwater level, water demand, water supply, etc., which reflects the hydrological changes after the implementation of the scheduling plan and helps to evaluate the feasibility and effectiveness of the scheduling plan.

[0050] The water resource scheduling simulation data is input into the water resource scheduling risk prediction module to generate risk prediction results. The water resource scheduling risk prediction module is a module used to evaluate the risks of water resource scheduling plans, including water supply security risk prediction model, water quality risk prediction model and hydrogeological disaster risk prediction model. It obtains water supply security risk coefficient, water quality risk coefficient and hydrogeological disaster risk coefficient, evaluates the overall risk of the existing scheduling plan, and ensures that the risks in the water resource scheduling process are controllable. By accurately adjusting the water resource scheduling plan based on the environmental prediction results of the future time zone, the flexibility and efficiency of the scheduling are improved. The water resource scheduling risk prediction module can identify possible water resource risks in advance, so as to take measures to reduce the risks of water shortage and over-exploitation and ensure the sustainable use of water resources.

[0051] Furthermore, the present application also includes the following steps:

[0052] S431: The surface water resource scheduling risk prediction module includes a water supply security risk prediction model, a water quality risk prediction model and a hydrogeological disaster risk prediction model; S432: The water resource scheduling simulation data is input into the water supply security risk prediction model to obtain a water supply security risk coefficient; S433: The water resource scheduling simulation data is input into the water quality risk prediction model to obtain a water quality risk coefficient; S434: The water resource scheduling simulation data is input into the hydrogeological disaster risk prediction model to obtain a hydrogeological disaster risk coefficient; S435: The water supply security risk coefficient, the water quality risk coefficient and the hydrogeological disaster risk coefficient are output as the water resource scheduling risk prediction result.

[0053] Specifically, the surface water resource scheduling risk prediction module is an integrated model used to evaluate the potential risks of water resource scheduling plans. By analyzing water resource scheduling simulation data, it calculates different types of risk factors, including water supply security, water quality, and hydrogeological disasters, to help identify and avoid potential risks and ensure the safety of water supply, quality, and ecological environment during the water resource scheduling process.

[0054] Collect historical water supply data, water demand data, climate data, environmental impact data, hydrological data of reservoirs and rivers, etc. Select features that have a significant impact on water supply security from the collected data, such as rainfall, evaporation, reservoir water level, water consumption, etc. Select a suitable mathematical model to build a water supply security risk prediction model, such as linear regression, machine learning algorithms (such as random forests, support vector machines, etc.). For example, build a neural network model, including an input layer, a hidden layer, and an output layer. The input layer receives preprocessed data, usually including multiple input features, each of which is a neuron. The hidden layer is used to learn the nonlinear relationship of the data. In the water supply security risk prediction model, the number of hidden layers and the number of neurons in each layer should be adjusted according to the complexity of the data. The output layer is used to predict the risk of water supply security. The output is usually a continuous value, representing the water supply security risk coefficient.

[0055] Use historical data to train the model and adjust the model parameters to minimize the prediction error. Use data that was not involved in the training to verify and test the model to evaluate the accuracy and reliability of the model. Through the back propagation algorithm, calculate the contribution of each neuron to the output error and adjust the network weights. Through multiple iterations of training, the neural network will gradually learn the relationship between the input features and the water supply security risk coefficient, and then provide more accurate risk predictions. The trained water supply security risk prediction model is used to predict the water supply security risk coefficient, indicating whether the supply and demand of water resources are balanced in the future and whether there is a risk of insufficient water supply. Similarly, the training process of the water quality risk prediction model and the hydrogeological disaster risk prediction model is similar to that of the water supply security risk prediction model, so I will not go into details here.

[0056] The water supply security risk prediction model is used to evaluate whether the water resource scheduling plan can meet the water resource demand of various users (such as agriculture, cities, industry, ecology, etc.). By simulating the matching degree of water resource supply and demand, the water supply security risk coefficient is calculated to measure the risk of insufficient or excessive water supply under a specific scheduling plan. In the dry season, the water supply decreases and the water supply security risk increases. The data such as reservoir water level, river basin flow, water demand, etc. generated during the simulation process are input into the water supply security risk prediction model, and the water supply security risk coefficient is calculated based on the current water supply and predicted demand.

[0057] The water quality risk prediction model is used to assess the water pollution risk that may occur during the water resource scheduling process. Water quality changes are usually affected by factors such as water flow, pollution sources, and temperature. Based on the hydrological data of the water resource scheduling plan, it is predicted whether the water quality will be polluted and the water quality risk coefficient is calculated. The water flow, temperature change and other data in the simulation results are input into the water quality risk prediction model, and the water quality is evaluated based on factors such as pollutant concentration, flow and temperature changes.

[0058] The hydrogeological disaster risk prediction model is used to predict the risks of hydrogeological disasters that may be caused by water resource scheduling, such as floods, droughts, landslides, mud-rock flows and other disasters. By inputting hydrological data and scheduling plans, the model evaluates the possibility of natural disasters and their impact. The hydrogeological model simulation data (such as basin flow, precipitation, groundwater level, etc.) is input into the hydrogeological disaster risk prediction model to evaluate whether various hydrological changes will lead to geological disasters, such as heavy precipitation may cause floods, long-term drought may cause surface subsidence or landslides, and whether water resource scheduling will exacerbate these risks.

[0059] The three independently calculated risk factors (water supply security risk factor, water quality risk factor, and hydrogeological disaster risk factor) are combined and output as the overall risk prediction result of water resource scheduling, providing a comprehensive risk assessment of the scheduling plan, helping it to optimize the water resource scheduling plan according to different types of risks. By comprehensively assessing the three types of risks, namely water supply security, water quality, and hydrogeological disasters, a comprehensive water resource scheduling risk analysis is provided, which helps to identify and respond to multiple possible risks in advance and avoid ignoring risks in a single dimension.

[0060] Further, as attached Figure 2 As shown, the present application S600 includes:

[0061] S610: Adjust the surface water resource scheduling plan and establish a first space for water resource scheduling adjustment; S620: Based on the surface water resource scheduling risk prediction module, perform optimization analysis on the first space for water resource scheduling adjustment according to the water resource scheduling risk constraints to obtain a second space for water resource scheduling adjustment; S630: Perform optimization to minimize the comprehensive risk of water resource scheduling according to the second space for water resource scheduling adjustment to obtain the water resource scheduling optimization strategy.

[0062] Specifically, the formulation and implementation of water resource scheduling plans are guided according to the regional water resource scheduling goals, including ensuring water supply security, maintaining ecological flow, flood control and drought relief, etc. According to the water resource scheduling goals, a set of water resource scheduling plans that may be applicable are retrieved from historical plans or preset plans. The retrieved plans are analyzed to identify the key features that may be triggered under current conditions, and determine which plans may be triggered or implemented under current conditions. Based on the triggering features, the range of conditions that may trigger water resource scheduling is determined. Within the triggering space, the water resource scheduling plan is preliminarily adjusted to form an adjusted plan set, that is, the first space for water resource scheduling adjustment.

[0063] The risk prediction module of surface water resource scheduling is used to predict the risks of all the schemes in the first space of water resource scheduling and adjustment, and the risk prediction results of the schemes are obtained. The scheduling risk prediction results of each scheme are compared with the water resource scheduling risk constraints to determine whether the water supply guarantee risk constraints, water quality risk constraints and hydrogeological disaster risk constraints are met. All schemes in the first space of water resource scheduling and adjustment that do not meet the water resource scheduling risk constraints are eliminated, and all the remaining schemes that meet the water resource scheduling risk constraints constitute the second space of water resource scheduling and adjustment.

[0064] Construct a comprehensive risk assessment model, comprehensively considering multiple factors such as water supply security risk, water quality risk, and hydrogeological disaster risk, including water supply security risk weight, water quality risk weight, and hydrogeological disaster risk weight. According to the comprehensive risk assessment model, the optimal solution is searched in the second space of water resource scheduling and adjustment through genetic algorithm, particle swarm optimization or other optimization methods, and finally the water resource scheduling optimization strategy is obtained, which is the optimal water resource scheduling solution with the lowest comprehensive risk. By comprehensively considering multiple risk factors such as water supply security, water quality protection, and hydrogeological disasters, balance the needs of all parties and ensure the comprehensiveness and scientificity of the scheduling solution. Through trigger feature analysis and risk prediction, dynamic adjustments are made according to actual conditions to respond to environmental changes more flexibly. The optimization algorithm is used to optimize the scheduling solution to improve the quality and optimization efficiency of the solution.

[0065] Furthermore, the present application also includes the following steps:

[0066] S611: Obtain the water resource scheduling target of the surface water resource scheduling plan; S612: Search the water resource scheduling plan for the area according to the water resource scheduling target, and obtain a water resource scheduling plan retrieval set; S613: Perform trigger feature analysis according to the water resource scheduling plan retrieval set, and obtain a water resource scheduling trigger space; S614: Adjust the surface water resource scheduling plan according to the water resource scheduling trigger space, and generate the first water resource scheduling adjustment space.

[0067] Specifically, the water resource scheduling objectives of the surface water resource scheduling plan are determined through documents, water resource management plans or user needs, including regional water demand, water source protection and ecological needs, climate and environmental changes, etc., with the aim of maximizing the rational use of water resources and ensuring sustainability. For example, in an arid area, the water resource scheduling goal may be to ensure the priority supply of agricultural irrigation and urban water, while taking measures to protect the ecological environment of the water source and avoid water pollution.

[0068] According to the determined water resource dispatching target, water resource dispatching schemes that meet the target are searched in the region, and a series of water resource dispatching scheme search sets that meet the water resource dispatching target are obtained. According to different climatic conditions and reservoir water storage, the water resource dispatching scheme search set may contain multiple dispatching schemes. Each scheme is optimized according to different environmental, climatic and water resource conditions, and can meet water resource demand and ecological protection requirements to a certain extent. For example, some schemes focus on reducing industrial water use, while others focus on optimizing agricultural irrigation water use.

[0069] Trigger feature analysis refers to analyzing the key features and factors in different scheduling plans based on the water resource scheduling plan retrieval set, identifying which factors (such as precipitation, reservoir water level changes, water demand fluctuations, etc.) will have a significant impact on water resource scheduling under what conditions, thereby triggering further adjustments to the scheduling plan. Trigger features usually include weather changes, water demand fluctuations, changes in water volume in the basin, etc. For example, if the reservoir water level drops by more than 30%, the feature analysis is triggered, and the current water resource scheduling plan needs to be adjusted to give priority to residents' water use and agricultural irrigation needs. The water resource scheduling trigger space refers to identifying the specific areas or condition ranges for adjusting the water resource scheduling plan based on the trigger feature analysis, and defines which areas or hydrological conditions need to adjust the current water resource scheduling plan under different circumstances to ensure the achievement of the goal.

[0070] According to the water resource scheduling trigger space, the surface water resource scheduling plan is initially adjusted, including reallocating water resources, reducing unnecessary water use, or optimizing water release according to new hydrological conditions, to ensure that the scheduling goals can be achieved. The first space of water resource scheduling adjustment refers to adjusting the surface water resource scheduling plan according to the changes in the water resource scheduling trigger space to form an adjusted plan set. Through target-based scheduling plan retrieval and trigger feature analysis, it can quickly respond to environmental changes such as precipitation and water volume in the basin, adjust the scheduling plan in time, and reduce water resource waste and over-exploitation.

[0071] Furthermore, the present application also includes the following steps:

[0072] S621: Extract the first water resource scheduling adjustment plan based on the first water resource scheduling adjustment space; S622: Based on the surface water resource scheduling risk prediction module, perform water resource scheduling risk prediction on the first water resource scheduling adjustment plan to obtain the scheduling risk prediction result of the first plan; S623: Determine whether the scheduling risk prediction result of the first plan meets the water resource scheduling risk constraint; S624: If the scheduling risk prediction result of the first plan meets the water resource scheduling risk constraint, add the first water resource scheduling adjustment plan to the second water resource scheduling adjustment space; S625: If the scheduling risk prediction result of the first plan does not meet the water resource scheduling risk constraint, eliminate the first water resource scheduling adjustment plan; S626: Continue to perform optimization analysis on the first water resource scheduling adjustment space according to the surface water resource scheduling risk prediction module and the water resource scheduling risk constraint to generate the second water resource scheduling adjustment space.

[0073] Specifically, any one of the schemes selected from the first space of water resource scheduling adjustment obtained after the preliminary adjustment is used as the first water resource scheduling adjustment scheme. The selected first water resource scheduling adjustment scheme is evaluated through the water resource scheduling risk prediction module, including water supply security risk prediction, water quality risk prediction, and hydrogeological disaster risk prediction. The water supply security risk prediction is used to evaluate whether the scheduling scheme can meet future water resource supply needs and whether there is a risk of insufficient water resources; the water quality risk prediction is used to predict whether the scheduling scheme will cause water pollution in the water source and whether water quality problems may occur; the hydrogeological disaster risk prediction is used to evaluate whether the scheduling scheme will cause hydrogeological disasters, such as floods, droughts or mudslides.

[0074] After the water resources scheduling risk prediction is completed, the first plan scheduling risk prediction result is obtained, including the first plan water supply security risk coefficient, the first plan water quality risk coefficient, and the first plan hydrogeological disaster risk coefficient. The first plan scheduling risk prediction result is compared with the water resources scheduling risk constraint to determine whether the risk prediction result of the scheduling plan meets the water resources scheduling risk constraint, that is, whether it meets the following conditions: water supply security risk constraint, water quality risk constraint, and hydrogeological disaster risk constraint. If the first plan scheduling risk prediction result meets the water resources scheduling risk constraint, the first water resources scheduling adjustment plan is added to the second water resources scheduling adjustment space. On the contrary, if the first plan scheduling risk prediction result does not meet the water resources scheduling risk constraint, the plan is eliminated and the plan that does not meet the requirements is removed.

[0075] Continue to perform optimization analysis on other schemes in the first space of water resource scheduling and adjustment, and use the surface water resource scheduling risk prediction module to predict water resource scheduling risks, determine whether the prediction results meet the water resource scheduling risk constraints, and eliminate all schemes that do not meet the water resource scheduling risk constraints, and finally obtain the second space of water resource scheduling and adjustment. The second space of water resource scheduling and adjustment contains all schemes that meet the trigger characteristics and water resource scheduling risk constraints. By predicting and judging the risks of each water resource scheduling scheme, it is ensured that the final selected scheduling scheme achieves the best results in terms of water supply guarantee, water quality protection, and disaster prevention and mitigation, and reduces risks and potential problems.

[0076] Furthermore, the present application also includes the following steps:

[0077] S631: Construct a comprehensive risk assessment channel for water resource scheduling, wherein the comprehensive risk assessment channel for water resource scheduling includes water supply security risk weights, water quality risk weights and hydrogeological disaster risk weights; S632: Based on the comprehensive risk assessment channel for water resource scheduling, optimize the water resource scheduling comprehensive risk minimization for the second space of the water resource scheduling adjustment to generate the water resource scheduling optimization strategy.

[0078] Specifically, a comprehensive risk assessment channel for water resource scheduling is constructed to comprehensively assess various risks in water resource scheduling plans. By weighted analysis of water supply security risk, water quality risk and hydrogeological disaster risk, the importance of each risk in the comprehensive assessment is determined, and optimization decisions are made accordingly. The comprehensive risk assessment channel for water resource scheduling helps evaluate and quantify the performance of each plan under different risk dimensions, providing a basis for decision-making. According to the specific conditions of the region, different weights are assigned to each risk (water supply security risk weight, water quality risk weight and hydrogeological disaster risk weight), reflecting the importance of different risk types to the water resource scheduling goals. The weights are integrated into the evaluation model to form a comprehensive risk assessment channel for water resource scheduling.

[0079] The relevant data of each scheme in the second space of water resource scheduling adjustment are input into the comprehensive risk assessment channel, and the comprehensive risk value of each scheme is calculated according to the water supply security risk weight, water quality risk weight and hydrogeological disaster risk weight, that is, the weighted average of each individual risk coefficient and its corresponding weight. By adjusting the scheduling parameters (such as water source allocation ratio, water release volume of different reservoirs, changes in water demand, etc.), the comprehensive value of water supply security risk, water quality risk and hydrogeological disaster risk can be minimized.

[0080] Taking particle swarm optimization as an example, it is a group intelligence optimization algorithm that simulates the foraging behavior of bird flocks. It continuously adjusts its position through communication with other particles to find the global optimal solution. Each particle represents a possible water source allocation plan, and the position of the particle corresponds to the various parameters of water resource scheduling. By continuously updating the parameters of the particles, the particles gradually approach the optimal scheduling plan. The position and speed of the initial particles are randomly generated from the parameter range of the scheduling plan, and the comprehensive risk (fitness) of the plan is calculated based on the position of the particles (i.e., the water resource scheduling plan). The fitness function usually contains multiple risk factors, such as water supply security risk, water quality risk, hydrogeological disaster risk, etc. The speed and position of the particle are updated according to the current speed of the particle, the historical optimal position and the global optimal position. When all particles in the particle swarm converge to a certain position, or when the maximum number of iterations is reached, the search process ends.

[0081] The water resources scheduling optimization strategy is the optimal scheduling plan generated by the comprehensive risk minimization optimization process of water resources scheduling. It can not only ensure that the water supply demand is met, but also minimize the risks of water supply security, water quality and hydrogeological disasters. On the basis of ensuring the water supply demand, the goal of minimizing the comprehensive risk is achieved by rationally allocating water resources, optimizing water quality protection measures, and avoiding disaster risks. The comprehensive risk assessment channel of water resources scheduling can comprehensively evaluate the potential risks of water resources scheduling plans by weighting different risks, and ensure the reasonable weight and control of various risks in the plan. Through the optimization process of minimizing the comprehensive risk, the water resources allocation plan can be optimized, and the balance between water supply security, water quality protection and disaster prevention can be achieved, avoiding over-exploitation or waste of water resources.

[0082] In summary, the surface water resources dynamic prediction method under digital twin provided by this application has the following technical effects:

[0083] According to the multi-source monitoring module, the hydrogeological monitoring data of the region is obtained; the hydrogeological monitoring data is transmitted to the digital twin module to construct a hydrogeological model; the surface water resource scheduling instructions of the region are obtained, wherein the surface water resource scheduling instructions include a surface water resource scheduling plan corresponding to the future time zone; a surface water resource scheduling risk prediction module is introduced, and water resource scheduling risk prediction is performed on the region in combination with the hydrogeological model and the surface water resource scheduling plan to obtain a water resource scheduling risk prediction result; it is determined whether the water resource scheduling risk prediction result meets the water resource scheduling risk constraint; if the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, the surface water resource scheduling plan is optimized and adjusted according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy; based on the future time zone, the surface water resource scheduling of the region is executed according to the water resource scheduling optimization strategy. That is to say, by collecting regional hydrogeological monitoring data and transmitting it to the digital twin module, a detailed hydrogeological model is constructed, surface water resource scheduling instructions are obtained and scheduling risk predictions are carried out, and optimization and adjustment are carried out according to the risk prediction results, thereby reducing losses caused by emergencies or unreasonable scheduling and improving the accuracy and efficiency of surface water resource management.

[0084] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0085] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The dynamic prediction method of surface water resources based on digital twin is characterized by: include: According to the multi-source monitoring module, the regional hydrogeological monitoring data is obtained; Transmitting the hydrogeological monitoring data to the digital twin module to construct a hydrogeological model; Obtaining a surface water resource dispatching instruction for the area, wherein the surface water resource dispatching instruction includes a surface water resource dispatching plan corresponding to a future time zone; Introducing a surface water resource scheduling risk prediction module, combining the hydrogeological model and the surface water resource scheduling plan to perform water resource scheduling risk prediction for the region, and obtaining a water resource scheduling risk prediction result; Determining whether the water resources scheduling risk prediction result meets the water resources scheduling risk constraint; If the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, the surface water resource scheduling scheme is optimized and adjusted according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy; Based on the future time zone, surface water resource scheduling in the area is performed according to the water resource scheduling optimization strategy.

2. The method for dynamic prediction of surface water resources under digital twin according to claim 1, characterized in that: A surface water resource scheduling risk prediction module is introduced to perform water resource scheduling risk prediction for the region in combination with the hydrogeological model and the surface water resource scheduling plan to obtain water resource scheduling risk prediction results, including: Based on the future time zone, performing environmental prediction on the region to obtain a regional environmental prediction result; Based on the regional environmental prediction results, simulating water resource scheduling of the hydrogeological model according to the surface water resource scheduling plan to obtain water resource scheduling simulation data; The water resource scheduling simulation data is input into the surface water resource scheduling risk prediction module to generate the water resource scheduling risk prediction result.

3. The method for dynamic prediction of surface water resources under digital twin according to claim 2, characterized in that: Inputting the water resource scheduling simulation data into the surface water resource scheduling risk prediction module to generate the water resource scheduling risk prediction result, including: The surface water resource scheduling risk prediction module includes a water supply guarantee risk prediction model, a water quality risk prediction model and a hydrogeological disaster risk prediction model; Inputting the water resource scheduling simulation data into the water supply security risk prediction model to obtain a water supply security risk coefficient; Inputting the water resource scheduling simulation data into the water quality risk prediction model to obtain a water quality risk coefficient; Inputting the water resources scheduling simulation data into the hydrogeological disaster risk prediction model to obtain a hydrogeological disaster risk coefficient; The water supply security risk coefficient, the water quality risk coefficient and the hydrogeological disaster risk coefficient are output as the water resource scheduling risk prediction result.

4. The method for dynamic prediction of surface water resources under digital twin according to claim 1, characterized in that: If the water resource scheduling risk prediction result does not meet the water resource scheduling risk constraint, the surface water resource scheduling scheme is optimized and adjusted according to the water resource scheduling risk constraint and the surface water resource scheduling risk prediction module to generate a water resource scheduling optimization strategy, including: Adjust the surface water resource scheduling plan to establish a first space for water resource scheduling adjustment; Based on the surface water resource scheduling risk prediction module, the first water resource scheduling adjustment space is optimized and analyzed according to the water resource scheduling risk constraint to obtain the second water resource scheduling adjustment space; The second space is adjusted according to the water resource scheduling to perform water resource scheduling comprehensive risk minimization optimization to obtain the water resource scheduling optimization strategy.

5. The method for dynamic prediction of surface water resources under digital twin according to claim 4, characterized in that: Adjust the surface water resource dispatching plan and establish a first space for water resource dispatching adjustment, including: Obtaining a water resource dispatching target of the surface water resource dispatching scheme; Searching for water resource scheduling solutions for the region according to the water resource scheduling target to obtain a water resource scheduling solution search set; Perform trigger feature analysis according to the water resource scheduling scheme retrieval set to obtain a water resource scheduling trigger space; According to the water resource scheduling trigger space, the surface water resource scheduling plan is adjusted to generate the water resource scheduling adjustment first space.

6. The method for dynamic prediction of surface water resources under digital twin according to claim 4, characterized in that: Based on the surface water resource scheduling risk prediction module, the first water resource scheduling adjustment space is optimized and analyzed according to the water resource scheduling risk constraint to obtain the second water resource scheduling adjustment space, including: Extracting a first water resource scheduling adjustment plan according to the first water resource scheduling adjustment space; Based on the surface water resource scheduling risk prediction module, a water resource scheduling risk prediction is performed on the first water resource scheduling adjustment plan to obtain a scheduling risk prediction result of the first plan; Determining whether the first scheme scheduling risk prediction result meets the water resources scheduling risk constraint; If the first scheme scheduling risk prediction result meets the water resource scheduling risk constraint, adding the first water resource scheduling adjustment scheme to the second water resource scheduling adjustment space; If the first scheme scheduling risk prediction result does not meet the water resources scheduling risk constraint, the first water resources scheduling adjustment scheme is eliminated; The first water resource scheduling adjustment space is continuously optimized and analyzed according to the surface water resource scheduling risk prediction module and the water resource scheduling risk constraint to generate the second water resource scheduling adjustment space.

7. The method for dynamic prediction of surface water resources under digital twin according to claim 4, characterized in that: According to the water resource scheduling, the second space is adjusted to perform water resource scheduling comprehensive risk minimization optimization to obtain the water resource scheduling optimization strategy, including: Constructing a comprehensive risk assessment channel for water resource scheduling, wherein the comprehensive risk assessment channel for water resource scheduling includes water supply security risk weights, water quality risk weights, and hydrogeological disaster risk weights; According to the water resource scheduling comprehensive risk evaluation channel, the water resource scheduling comprehensive risk minimization optimization is performed on the second space of the water resource scheduling adjustment to generate the water resource scheduling optimization strategy.

8. The method for dynamic prediction of surface water resources under digital twin according to claim 1, characterized in that: The hydrogeological monitoring data is transmitted to the digital twin module to construct a hydrogeological model, including: Perform data cleaning based on the hydrogeological monitoring data to obtain hydrological monitoring standard data and geological monitoring standard data; Inputting the hydrological monitoring standard data into the digital twin module to obtain a regional hydrological model; Based on the digital twin module, modeling is performed according to the geological monitoring standard data to generate a regional geological model; The regional hydrological model and the regional geological model are integrated to generate the hydrogeological model.

Images