Digital Twin Irrigation District Full Life Cycle Intelligent Management System for Food Security

Abstract

This invention relates to the field of food security technology, specifically to a digital twin intelligent management system for the entire lifecycle of irrigation districts, oriented towards food security. The system includes: a data creation terminal, a scheme generation terminal, and a management execution terminal. The data creation terminal is used for data collection and preprocessing of the collected data to provide data support for subsequent modules. The scheme generation terminal builds a digital twin model based on the collected data and performs scheme deduction within the digital twin model. The management execution terminal selects the optimal scheme based on the scheme generated by the scheme generation terminal and performs fine-tuning during execution to achieve optimal results, while also storing system data. This system features efficient data interaction and linkage between modules, replacing traditional experience-based reliance with data-driven predictive models and intelligent optimization methods, and possesses capabilities for precise disaster response, quantitative risk-return assessment, and secure data reuse.

Description

Technical Field

[0001] This invention belongs to the field of food security technology, specifically relating to a digital twin intelligent management system for the entire life cycle of irrigation districts aimed at food security. Background Technology

[0002] As a core infrastructure for ensuring national food security and supporting sustainable agricultural development, the management level of irrigation districts directly affects water resource utilization efficiency, crop yield stability, and the quality of regional agricultural economic development. Irrigation district management refers to the systematic and refined control of the irrigation engineering system (such as canals, pumping stations, and sluices), the dynamic allocation of water resources, and the entire crop growth cycle within the irrigation district through the comprehensive application of modern water conservancy engineering technology, information management methods, and standardized systems and regulations. Its core objective is to achieve sustainable water resource utilization and optimize crop yield and quality through scientifically planned irrigation schemes and efficient water resource allocation, thereby providing crucial support for the food security strategy.

[0003] Currently, existing irrigation district management technologies have initially established a basic information management framework. For example, sensor networks enable real-time collection of fundamental data such as soil moisture, weather (temperature, precipitation), and canal water levels. Simple control systems are used to perform routine scheduling operations such as irrigation flow regulation and pump station start-up and shutdown, thus improving the automation level of irrigation district management to some extent. However, as food security goals increasingly demand more refined and intelligent irrigation district management, the existing technological system still has significant shortcomings and struggles to meet actual needs. These shortcomings include:

[0004] (1) Insufficient depth of multi-source data synergy and integration: Irrigation district management involves multi-dimensional data such as geospatial data (e.g., irrigation district topography, soil type), meteorological observation data (short-term precipitation forecast, solar radiation), crop growth data (plant height, water requirement), and water conservancy project operation data (gate opening, channel flow). However, the existing technology has limited ability to integrate such multi-source data, low correlation between data, a lot of redundant information, and insufficient standardization. It has failed to form an integrated data foundation to support the construction of a high-fidelity digital twin model, resulting in a lack of accurate and comprehensive data support for subsequent model construction.

[0005] (2) Existing dynamic simulation technologies mostly focus on single elements (such as simulating only the movement of water flow in channels or the growth stage of a single crop), and do not adequately simulate the coupling mechanism between multiple elements such as "water flow-soil-crop-meteorology" (such as the influence of meteorological conditions on crop water demand, and the dynamic response relationship between soil moisture and irrigation water flow). They cannot fully restore the actual operating state of the physical scene of the irrigation area, and the model output results deviate greatly from the real situation, making it difficult to use for predicting the operating risks of the irrigation area or optimizing management plans.

[0006] (3) Under the guidance of the goal of food security, irrigation district management needs to cope with sudden disasters such as drought and flood, as well as the dynamic needs of crops at different growth stages. However, the decision support function of existing technologies is still dominated by human experience; the ability to generate intelligent plans based on scenarios is insufficient, and it is impossible to quickly match response plans for different types of disasters; at the same time, it lacks the ability to quantify and extrapolate the benefits (such as crop yield increase) and risks (such as extreme loss probability) of the plan, making it difficult to form a scientific and efficient decision-making basis and failing to meet the actual needs of refined and intelligent management of the entire life cycle of irrigation districts.

[0007] In view of this, the present invention is hereby proposed. Summary of the Invention

[0008] To address the aforementioned technical problems in existing technologies, this invention provides a digital twin intelligent management system for the entire lifecycle of irrigation districts, oriented towards food security. This system solves the problems of insufficient depth of multi-source data synergy and integration, lack of accuracy in dynamic simulation of multi-element coupling, and weak scenario-based contingency plan generation and risk simulation functions in existing irrigation district management technologies, making it difficult to meet the needs of refined and intelligent full lifecycle management of irrigation districts under the goal of food security.

[0009] To achieve the above objectives, the technical solution of the present invention is as follows:

[0010] A digital twin-based intelligent management system for the entire lifecycle of irrigation districts, geared towards food security, includes:

[0011] Data creation end: used to collect geographic datasets and meteorological datasets; for all sub-data items in the collected geographic datasets and meteorological datasets, data cleaning is performed by filling in missing values, and normalization is performed; and data is extracted from the geographic datasets and meteorological datasets to obtain feature vectors;

[0012] Solution generation end: used to build a digital twin model based on the geographic dataset, meteorological dataset and feature vector, and generate corresponding alternative solutions for different scenarios; the digital simulation module simulates the alternative solutions based on the digital twin model, evaluates the simulation results and sends them to the management execution end;

[0013] Management execution end: Used to select the optimal solution that meets the food security goal and execute it based on the simulation and evaluation results of the solution generation end; dynamically fine-tune the execution operation during the solution execution process and store system data.

[0014] Furthermore, the data establishment terminal includes a data acquisition module and a data preprocessing module;

[0015] The data acquisition module includes a geographic data acquisition unit and a meteorological data acquisition unit;

[0016] A geographic data acquisition unit is used to acquire geographic datasets, which include soil moisture parameters, crop parameters, and hydrological data.

[0017] The meteorological data acquisition unit is used to acquire meteorological datasets, which include short-term precipitation forecasts, temperature data, and solar radiation intensity data.

[0018] The data preprocessing module includes a data cleaning unit and a feature extraction unit;

[0019] The data cleaning unit is used to clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula;

[0020] The feature extraction unit is used to extract features from geographical and meteorological datasets.

[0021] Furthermore, the specific steps for feature extraction from geographical and meteorological datasets include:

[0022] Crop moisture index is calculated based on geographic datasets. The specific calculation formula is as follows:

[0023]

[0024] in, This represents the current soil moisture content. It refers to the soil field water holding capacity;

[0025] Crop water requirements were calculated based on geographic and meteorological datasets. The specific calculation formula is as follows:

[0026]

[0027] in, The slope of the saturated water vapor pressure curve. This is net radiation data. For soil heat flux data, This is the constant of the wet and dry meter. The wind speed data is at a distance of 2 meters. The saturated vapor pressure, This is the actual water vapor pressure. Temperature data;

[0028] By packaging crop moisture index and crop water requirement, a feature vector is obtained. .

[0029] Furthermore, the scheme generation module includes a virtual mapping module, a contingency plan generation module, and a digital simulation module;

[0030] The virtual mapping module includes a basic modeling unit and a dynamic modeling unit;

[0031] The basic modeling unit is used to acquire geographical data of the irrigation area based on the data acquisition module, build a three-dimensional geometric model and establish a virtual model spatial framework through BIM+GIS technology, and introduce crop water requirements extracted by the data preprocessing module as dynamic input to the model.

[0032] Dynamic modeling units are used to build dynamic models based on geographic datasets. Through coupling with geometric models, they form high-fidelity models that are consistent with the physical irrigation district scene.

[0033] The contingency plan generation module includes a scenario triggering unit and a multi-solution generation unit;

[0034] The scenario triggering unit is used to determine the current disaster scenario and identify the type of disaster that needs to be addressed based on the historical disaster data stored in the data management module and the feature extraction data from the data preprocessing module.

[0035] The multi-solution generation unit is used to provide multi-dimensional solution selection based on the disaster type determined by the scenario triggering unit;

[0036] The digital simulation module includes a dynamic simulation unit and a benefit evaluation unit;

[0037] The dynamic simulation unit is used to obtain dynamic simulation results based on the current model state obtained from the virtual mapping module and the scheme imported from the contingency plan generation module; it sets the number of simulations based on the historical errors of meteorological data and introduces disturbance factors to simulate actual environmental fluctuations; at the same time, it provides an interactive interface for managers to input custom parameters to trigger a single simulation.

[0038] The benefit evaluation unit is used to calculate the key indicators for each simulation based on the coupled model of the virtual mapping module.

[0039] Furthermore, the steps involved in building a dynamic model based on a geographic dataset and fusing it with a geometric model to create a high-fidelity model consistent with the physical irrigation district scenario include:

[0040] Establish continuous equations based on geographic datasets;

[0041] Momentum equations were established based on geographic datasets.

[0042] A soil moisture model was established based on crop water requirement and soil moisture data to calculate the soil moisture content at the next time step. The specific calculation formula is as follows:

[0043]

[0044] in, This represents the current soil moisture content. For time step, For time, For irrigation water volume, This refers to the water that flows down the soil to the lower layers. For the water lost from the earth's surface, The calculation formula is used to calculate the thickness of the soil layer; its function is to dynamically predict soil moisture and provide soil environmental data for crop growth models.

[0045] A crop growth model was established based on crop water requirement and crop water index to calculate the crop height at the next time step. The specific calculation formula is as follows:

[0046]

[0047] in, The current crop height. The growth coefficient;

[0048] By coupling the continuity equation, momentum equation, soil moisture model, and crop growth model with the three-dimensional geometric model to build a virtual model spatial framework, a high-fidelity model consistent with the physical irrigation area scenario is obtained.

[0049] Furthermore, based on the disaster type determined by the scene triggering unit, the specific steps for providing multi-dimensional solution selection include:

[0050] When a drought disaster is identified, incremental water supply plans, water-saving storage plans, and emergency water replenishment plans are provided by combining geographical and meteorological datasets.

[0051] When a flood disaster is identified, incremental drainage schemes, seepage prevention drainage schemes, and emergency flood diversion schemes are provided by combining geographical and meteorological datasets.

[0052] The incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for drought disasters, and the incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for flood disasters, are sent to the digital simulation module for simulation.

[0053] Furthermore, based on the coupled model of the virtual mapping module, the steps for calculating the key indicators for each simulation include:

[0054] Calculate the average predicted output based on the total number of simulations. The specific calculation formula is as follows:

[0055]

[0056] in, Let i be the output of the i-th simulation. The total number of simulations; the average predicted output reflects the average return level of the scheme;

[0057] Based on average predicted output Calculations were performed to obtain the output volatility. The specific calculation formula is as follows:

[0058]

[0059] The extreme loss probability is calculated based on the total number of simulations. The specific calculation formula is as follows:

[0060]

[0061] in, To indicate function 3, This is normal production volume;

[0062] The average output, output volatility, extreme loss probability, and simulation interaction results are packaged together to generate a simulation report and send it to the management execution end.

[0063] Furthermore, the management execution terminal includes an intelligent decision-making module, an adaptive control module, and a data management module;

[0064] The intelligent decision-making module includes a scheme decision-making unit and a real-time monitoring unit;

[0065] The scheme decision unit is used to eliminate high-risk and low-return schemes based on the schemes and simulation reports generated by the scheme generation module, determine the optimal scheme with crop safety as the goal, and send the execution parameters of the optimal scheme and the simulation report to the adaptive control module for execution.

[0066] The real-time monitoring unit is used to receive the measured data after the adaptive control module has executed its function.

[0067] The adaptive control module includes an execution monitoring unit and a data reporting unit;

[0068] The execution monitoring unit is used to acquire the execution instructions of the intelligent decision-making module, parse the corresponding execution mechanism of the instructions, and collect parameters during the execution process through sensors. When the sensors detect that the current execution mechanism is abnormal, an alarm message is immediately sent to the data management module.

[0069] The data reporting unit is used to push execution instructions and simulation reports from the system terminal to the management personnel terminal, and sets a 10-minute confirmation window period. Management personnel can reject or confirm the instructions, and if no confirmation is made, the execution will be suspended. At the same time, the actual parameters after execution are sent to the intelligent decision-making module for fine-tuning.

[0070] Furthermore, the steps for receiving the measured data after the adaptive control module has executed include:

[0071] Based on the measured data and the predicted data in the projection report, the error value is calculated; when the error value is less than or equal to the preset threshold, it is determined that the expectation has been met; when the error value is greater than the preset threshold, it is determined that the expectation has not been met.

[0072] Based on the judgment result, when the judgment does not meet expectations, the adjustment amount is calculated based on the error. The specific calculation formula is as follows:

[0073]

[0074] in, To increase traffic, To adjust the coefficient, To mitigate execution errors; when the execution effect does not meet expectations, the flow command is corrected using a formula to ensure that the crop's water requirements are met; the fine-tuning parameters are then sent to the adaptive control module for execution.

[0075] Furthermore, the data management module is used to store basic system data and to provide final confirmation of execution instructions.

[0076] Compared with existing technologies, the digital twin irrigation district full life cycle intelligent management system for food security provided by this invention includes: a data establishment end, a scheme generation end, and a management execution end. The data establishment end is used for data collection and preprocessing of the collected data to provide data support for subsequent modules. The scheme generation end builds a digital twin model based on the collected data and completes the scheme deduction in the digital twin model. The management execution end selects the optimal scheme based on the scheme generated by the scheme generation end and performs fine-tuning during the execution process to achieve the best results, while storing the system data. The system modules have efficient data interaction and linkage, replacing traditional experience reliance with data-driven prediction models and intelligent optimization methods, and have the capabilities of accurate disaster response, risk-return quantitative assessment, and secure data reuse. Attached Figure Description

[0077] Figure 1 This is an architecture diagram of the digital twin irrigation district full life cycle intelligent management system provided in an embodiment of the present invention;

[0078] Figure 2 An architecture diagram of the data establishment terminal provided in an embodiment of the present invention;

[0079] Figure 3 This is an architecture diagram of the solution generation end provided in the embodiments of the present invention;

[0080] Figure 4 This is an architecture diagram of the management execution terminal provided in an embodiment of the present invention. Detailed Implementation

[0081] The technical solution of the present invention will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0082] It should be noted that, unless otherwise specifically stated, the relative arrangement and numerical expressions of the components and steps described in these embodiments should not be construed as limiting the scope of the invention.

[0083] The following description of exemplary embodiments is merely illustrative and is not intended to limit the invention or its application or use in any way. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail herein, but where applicable, such techniques, methods, and apparatus should be considered part of this specification.

[0084] See Figure 1 , Figure 1 This is an architecture diagram of the digital twin irrigation district full lifecycle intelligent management system for food security proposed in this invention. The system can be set up on a cloud server. In terms of implementation, it can be implemented as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the implemented functions, the digital twin irrigation district full lifecycle intelligent management system for food security can include a geographic data acquisition module, a meteorological data acquisition module, a data preprocessing module, a virtual mapping module, a contingency plan generation module, a digital extrapolation module, an intelligent decision-making module, an adaptive control module, and a data management module. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory. Specifically, they include:

[0085] M1, Data Acquisition End: Used to collect geographic and meteorological datasets. It performs data cleaning by imputing missing values ​​for all sub-data items in the collected geographic and meteorological datasets, and normalizes all sub-data items to the range [0, 1] based on a normalization formula. Simultaneously, it extracts data from the geographic and meteorological datasets to obtain feature vectors; see [link / reference]. Figure 2 Specifically, it includes:

[0086] M11, Data Acquisition Module: Includes geographic data acquisition unit and meteorological data acquisition unit;

[0087] M111, Geographic Data Acquisition Unit, is used to collect geographic datasets to provide raw data models for the scheme generation end. The geographic datasets include soil moisture parameters, crop parameters and hydrological data.

[0088] M112, the meteorological data acquisition unit, is used to collect meteorological datasets to provide real-time meteorological data for establishing dynamic models at the scheme generation end. The meteorological datasets include short-term precipitation forecasts, temperature data, and solar radiation intensity data.

[0089] M12, Data Preprocessing Module: Includes a data cleaning unit and a feature extraction unit;

[0090] M121, Data Cleaning Unit, is used to clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula;

[0091] Removing outliers refers to data such as negative solar radiation intensity; the base dataset includes geographical and meteorological datasets; the specific expression of the normalization formula is:

[0092]

[0093] in, Normalized value Any sub-data item of the basic data, This represents the historical maximum value of any given sub-data item. This is the historical minimum value of this arbitrary sub-data item.

[0094] M122, Feature Extraction Unit, is used for feature extraction from geographical and meteorological datasets; specific steps include:

[0095] M1221. Crop moisture index is calculated based on geographic datasets. The specific calculation formula is as follows:

[0096]

[0097] in, The current soil moisture content, The purpose of calculating the crop water index is to represent the degree of water shortage in plants numerically. When the crop water index is greater than or equal to 0.8, it indicates severe water shortage, providing an indicator for the evaluation of the contingency plan generation module.

[0098] M1222, based on geographical and meteorological datasets, calculates crop water requirements. The specific calculation formula is as follows:

[0099]

[0100] in, The slope of the saturated water vapor pressure curve. This is net radiation data. For soil heat flux data, This is the constant of the wet and dry meter. The wind speed data is at a distance of 2 meters. The saturated vapor pressure, This is the actual water vapor pressure. Temperature data is used; calculating crop water requirements helps to accurately quantify the daily water needs of crops, providing water requirement input for crop growth simulation in the virtual mapping module.

[0101] in, It reflects the contribution of solar radiation to water demand; It reflects the contribution of temperature and wind speed to water demand;

[0102] M1223, the packaged crop moisture index, and crop water requirement are used to obtain the feature vector. .

[0103] M2, Solution Generation Terminal: Used to build digital twin models based on collected geographic and meteorological datasets and extracted feature vectors. It generates different alternative solutions for different scenarios. The digital simulation module then simulates and extrapolates these solutions based on the digital twin model, evaluating the simulation results and sending them to the management execution terminal. This provides a complete basis for intelligent decision-making and ensures traceability of the simulation process. (See also...) Figure 3 Specifically, it includes:

[0104] M21, Virtual Mapping Module: Includes basic modeling units and dynamic modeling units;

[0105] M211, the basic modeling unit, is used to acquire geographical data of the irrigation area based on the data acquisition module, and to build a three-dimensional geometric model to construct a virtual model spatial framework through BIM+GIS technology, providing a geometric basis for the dynamic simulation process. At the same time, the crop water requirement extracted by the data preprocessing module is introduced as the dynamic input of the model, providing real-time driving data for the dynamic model and ensuring that the model is synchronized with the physical irrigation area status.

[0106] M212, the dynamic modeling unit, is used to build dynamic models based on geographic datasets. Through coupling with geometric models, it forms a high-fidelity model consistent with the physical irrigation district scene. Specific steps include:

[0107] M2121. A continuous equation is established based on a geographic dataset to describe the conservation of water flow mass and reflect the spatiotemporal relationship between flow rate and water level.

[0108] M2122. Momentum equations are established based on geographic datasets to describe the conservation of water flow and ensure the accuracy of water flow simulation.

[0109] M2123. Based on crop water requirement and soil moisture data, a soil moisture model is established to calculate the soil moisture content at the next time step. The specific calculation formula is as follows:

[0110]

[0111] in, This represents the current soil moisture content. For time step, For time, For irrigation water volume, This refers to the water that flows down the soil to the lower layers. For the water lost from the earth's surface, The calculation formula is used to calculate the thickness of the soil layer; its function is to dynamically predict soil moisture and provide soil environmental data for crop growth models.

[0112] M2124. A crop growth model was established based on crop water requirement and crop water index to calculate the crop height at the next time step. The specific calculation formula is as follows:

[0113]

[0114] in, The current crop height. This is the growth coefficient; the calculation formula is used to simulate the dynamic growth of crop height and provide growth status data for the plan generation module.

[0115] M2125. The continuity equation, momentum equation, soil moisture model and crop growth model are coupled with the three-dimensional geometric model to build a virtual model space framework, resulting in a high-fidelity model consistent with the physical irrigation area scene.

[0116] M22, Contingency Plan Generation Module: Includes a scenario triggering unit and a multi-solution generation unit;

[0117] M221, the scenario triggering unit, is used to determine the current disaster scenario and clarify the type of disaster that needs to be addressed based on the historical disaster data stored in the data management module and the feature extraction data from the data preprocessing module, thus providing direction for the formulation of solutions.

[0118] M222, a multi-solution generation unit, is used to provide multi-dimensional solution selection based on the disaster type determined by the scenario triggering unit; specific steps include:

[0119] M2221. When a drought disaster is identified, incremental water supply plans, water-saving storage plans, and emergency water replenishment plans are provided by combining geographical and meteorological datasets.

[0120] It should be explained that the incremental water supply plan includes setting an increase in channel flow to ensure the current water needs of crops; the water-saving reserve plan includes setting an increase in channel flow and simultaneously activating water-saving irrigation modes in the fields to reserve water to cope with possible continued drought; the emergency water replenishment plan includes setting an increase in channel flow and simultaneously starting foliar spraying of crops to alleviate acute water stress.

[0121] M2222: When a flood disaster is identified, incremental drainage schemes, seepage prevention drainage schemes, and emergency flood diversion schemes are provided by combining geographical and meteorological datasets.

[0122] It should be explained that the incremental drainage plan includes setting an incremental field drainage flow to accelerate the discharge of accumulated water; the seepage prevention drainage plan includes setting an incremental field drainage flow while activating temporary seepage prevention membranes in the channels to reduce rainwater entering the channels; and the emergency flood diversion plan includes setting an incremental field drainage flow while simultaneously opening backup flood diversion ditches to prevent channels from overflowing.

[0123] M2223. Send the incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for drought disasters, and the incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for flood disasters to the digital simulation module for simulation.

[0124] M23, Digital Simulation Module: Includes dynamic simulation unit and benefit evaluation unit;

[0125] M231, the dynamic simulation unit, is used to obtain dynamic simulation results based on the current model state obtained from the virtual mapping module and the scheme imported from the contingency plan generation module. Based on the historical error of meteorological data, the number of simulations is set, and a disturbance factor is introduced to simulate actual environmental fluctuations to ensure that the simulation results are close to the real situation. At the same time, it provides an interactive interface for managers to input custom parameters to trigger a single simulation, meeting the personalized assessment needs of managers.

[0126] M232, the benefit evaluation unit, is used to calculate key indicators for each simulation based on the coupled model of the virtual mapping module; the specific steps include:

[0127] M2321, Calculate the average predicted output based on the total number of simulations. The specific calculation formula is as follows:

[0128]

[0129] in, Let i be the output of the i-th simulation. The total number of simulations; the average predicted output reflects the average return level of the scheme;

[0130] M2322. Based on the average predicted output from step B1, calculate the output volatility. This reflects the stability of production, and the specific calculation formula is as follows:

[0131]

[0132] M2323, Calculate the extreme loss probability based on the total number of simulations. The specific calculation formula is as follows:

[0133]

[0134] in, This is an indicator function used to determine whether production loss is severe. This represents normal production levels; the probability of extreme losses reflects the extreme risks of the proposed solution.

[0135] M2324, average packaged output, output volatility, extreme loss probability, and simulation interaction results are used to generate a simulation report and send it to the management execution terminal.

[0136] M3, Management Execution Terminal: Used to select the optimal solution that meets food security goals based on digital simulation results, archive the solution and push execution instructions to the adaptive control module, while receiving execution feedback data in real time, comparing and evaluating the effect, and dynamically fine-tuning instructions when expectations are not met, forming a closed loop of "decision-execution-evaluation-fine-tuning" to ensure the effective implementation of the solution. The adaptive control module executes decision instructions, drives the mechanism to act after manual supervision, handles execution anomalies to ensure continuity, and stores all system data in categories, pushes notifications, provides query interfaces, supports the operation of each module and data reuse; system data includes geographic datasets, meteorological datasets, feature vectors, simulation reports and adjustment quantities; see reference. Figure 4 Specifically, it includes:

[0137] M31, Intelligent Decision Module: Includes a solution decision unit and a real-time monitoring unit;

[0138] M311, the scheme decision unit, is used to eliminate high-risk and low-return schemes based on the schemes and simulation reports generated by the scheme generation module, determine the optimal scheme with crop safety as the goal, and send the execution parameters of the optimal scheme and the simulation report to the adaptive control module for execution, thereby realizing the traceability of the scheme and triggering the execution process simultaneously.

[0139] M312, the real-time monitoring unit, is used to receive measured data after the adaptive control module executes, providing data support for subsequent evaluation; the specific steps include:

[0140] M3121. Based on the measured data and the predicted data in the projection report, calculate the error value; when the error value is less than or equal to the preset threshold, it is determined that the expectation has been met; when the error value is greater than the preset threshold, it is determined that the expectation has not been met.

[0141] M3122. Based on the judgment result of step A1, when the judgment does not meet expectations, the adjustment amount is calculated based on the error. The specific calculation formula is as follows:

[0142]

[0143] in, To increase traffic, To adjust the coefficient, To mitigate execution errors; when the execution effect does not meet expectations, the flow command is corrected using a formula to ensure that the crop's water requirements are met; the fine-tuning parameters are then sent to the adaptive control module for execution.

[0144] M32, Adaptive Control Module: Includes an execution monitoring unit and a data reporting unit;

[0145] M321, Execution Monitoring Unit, is used to acquire the execution instructions of the intelligent decision-making module, parse the corresponding execution mechanism of the instructions, and collect parameters during the execution process through sensors. When the sensors detect that the current execution mechanism is abnormal, an alarm message is immediately sent to the data management module.

[0146] The M322 data reporting unit is used to push execution instructions and simulation reports from the system terminal to the management personnel terminal, and sets a 10-minute confirmation window period. Management personnel can reject or confirm the instructions. If no confirmation is made, the execution is suspended, thus realizing supervised autonomy and avoiding system misoperation. At the same time, the actual parameters after execution are sent to the intelligent decision-making module for fine-tuning.

[0147] M33, Data Management Module: Used to store basic system data and provide final confirmation of executed instructions;

[0148] The execution instructions and simulation reports are sent to the staff's email addresses via email, and staff are reminded to check their emails via SMS.

[0149] Each of the above modules can be implemented independently and can call other modules. This "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the sharing and evaluation module can call the same information collection module to obtain information collected by that module. Based on the above characteristics, the digital twin irrigation district full lifecycle intelligent management system for food security provided in this embodiment of the invention can adjust the applicability of the architecture of the digital twin irrigation district full lifecycle intelligent management system for food security without modifying the program code, by adding modules and directly calling them, thus achieving cluster-based horizontal expansion. This allows for quick and flexible expansion of the digital twin irrigation district full lifecycle intelligent management system for food security. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0150] In summary, the present invention has the following advantages:

[0151] 1. By setting up a data establishment terminal, the shortcomings of existing irrigation district management technologies in terms of the depth of multi-source data synergy and integration can be effectively made up for. This provides key support for the construction of digital twin irrigation district systems and the achievement of food security goals. The data acquisition module accurately acquires soil moisture, crop parameters, hydrological data, as well as meteorological data such as short-term precipitation forecasts, daily average temperature, and solar radiation intensity, achieving comprehensive coverage of multi-dimensional operational data of the irrigation district. This solves the problem of single and incomplete data acquisition in traditional technologies. The data preprocessing module removes data noise by cleaning outliers in geographic data. Then, through standardization and unified dimensions, and extraction of water stress index and crop water requirement, deep synergy and integration of geographic and meteorological data is achieved, improving data quality and usability.

[0152] 2. By setting up a scheme generation module to accurately reproduce the physical state and dynamic changes of the irrigation area in the virtual mapping module, a reliable simulation foundation is provided for scheme generation and digital simulation, solving the problem of lack of real-world scenario mapping in traditional management. The scheme generation module quickly generates multiple scheduling schemes based on this model, and automatically matches the optimal response strategies for disasters such as drought and floods by combining geographical and meteorological data, breaking the limitations of traditional schemes that rely on experience and have low generation efficiency. The digital simulation module uses the schemes as a basis to quantitatively evaluate the benefits and risks of the schemes through multiple rounds of disturbance simulation, filling the gap in traditional decision-making that lacks risk prediction.

[0153] 3. By setting up the management execution terminal, the intelligent decision-making module relies on historical plans, real-time geographic and meteorological data, and execution records stored in the data management module to accurately select the optimal scheduling plan and generate execution instructions. At the same time, it receives the actual execution results fed back by the adaptive control module and dynamically fine-tunes for situations that do not meet expectations, avoiding a disconnect between decision-making and actual execution. The adaptive control module converts the intelligent decision instructions into institutional operation signals, ensures execution compliance through a supervision mechanism, and synchronously pushes the execution process data and results to the data management module for archiving, forming a traceable execution link. The data management module stores all the data from the interaction of the three in real time, providing historical data references for intelligent decision-making to optimize plan selection, providing equipment parameter support for adaptive control to ensure execution accuracy, and pushing decision plans and fault warning information to management personnel as needed.

[0154] The above specific embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A digital twin intelligent management system for the entire lifecycle of irrigation districts, designed for food security, is characterized by: include: Data creation end: used to collect geographic datasets and meteorological datasets; for all sub-data items in the collected geographic datasets and meteorological datasets, data cleaning is performed by filling in missing values, and normalization is performed; and data is extracted from the geographic datasets and meteorological datasets to obtain feature vectors; Solution generation end: used to build a digital twin model based on the geographic dataset, meteorological dataset and feature vector, and generate corresponding alternative solutions for different scenarios; The alternative solutions are simulated and analyzed using a digital twin model through a digital simulation module. The simulation results are evaluated and then sent to the management execution terminal. The solution generation terminal includes a virtual mapping module, a contingency plan generation module, and a digital simulation module. The virtual mapping module includes a basic modeling unit and a dynamic modeling unit; The basic modeling unit is used to acquire geographical data of the irrigation area based on the data acquisition module, build a three-dimensional geometric model and establish a virtual model spatial framework through BIM+GIS technology, and introduce crop water requirements extracted by the data preprocessing module as dynamic input to the model. Dynamic modeling units are used to build dynamic models based on geographic datasets. Through coupling with geometric models, they form high-fidelity models that are consistent with the physical irrigation district scene. The contingency plan generation module includes a scenario triggering unit and a multi-solution generation unit; The scenario triggering unit is used to determine the current disaster scenario and identify the type of disaster that needs to be addressed based on the historical disaster data stored in the data management module and the feature extraction data from the data preprocessing module. The multi-solution generation unit is used to provide multi-dimensional solution selection based on the disaster type determined by the scenario triggering unit; The digital simulation module includes a dynamic simulation unit and a benefit evaluation unit; The dynamic simulation unit is used to obtain dynamic simulation results based on the current model state obtained from the virtual mapping module and the scheme imported from the contingency plan generation module; it sets the number of simulations based on the historical errors of meteorological data and introduces disturbance factors to simulate actual environmental fluctuations; at the same time, it provides an interactive interface for managers to input custom parameters to trigger a single simulation. The benefit evaluation unit is used to calculate the key indicators for each simulation based on the coupled model of the virtual mapping module. Management execution end: Used to select and execute the optimal solution that meets the food security objectives based on the simulation and evaluation results of the solution generation end; The execution process is dynamically fine-tuned, and system data is stored.

2. The digital twin irrigation district full lifecycle intelligent management system for food security according to claim 1, characterized in that, The data establishment terminal includes a data acquisition module and a data preprocessing module; The data acquisition module includes a geographic data acquisition unit and a meteorological data acquisition unit; A geographic data acquisition unit is used to acquire geographic datasets, which include soil moisture parameters, crop parameters, and hydrological data. The meteorological data acquisition unit is used to acquire meteorological datasets, which include short-term precipitation forecasts, temperature data, and solar radiation intensity data. The data preprocessing module includes a data cleaning unit and a feature extraction unit; The data cleaning unit is used to clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula; The feature extraction unit is used to extract features from geographical and meteorological datasets.

3. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 2, characterized in that, The specific steps for feature extraction from geographic and meteorological datasets include: Crop moisture index is calculated based on geographic datasets. The specific calculation formula is as follows: in, The current soil moisture content, It refers to the soil field water holding capacity; Crop water requirements were calculated based on geographic and meteorological datasets. The specific calculation formula is as follows: in, The slope of the saturated water vapor pressure curve. This is net radiation data. For soil heat flux data, This is the constant of the wet and dry meter. The wind speed data is at a distance of 2 meters. The saturated vapor pressure, This is the actual water vapor pressure. Temperature data; By packaging crop moisture index and crop water requirement, a feature vector is obtained. .

4. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 1, characterized in that, The steps involved in building a dynamic model based on a geographic dataset and fusing it with a geometric model to create a high-fidelity model consistent with the physical irrigation district scenario include: Establishing continuous equations based on geographic datasets; Momentum equations were established based on geographic datasets. A soil moisture model was established based on crop water requirement and soil moisture data to calculate the soil moisture content at the next time step. The specific calculation formula is as follows: in, This represents the current soil moisture content. For time step, For time, For irrigation water volume, This refers to the water that flows down the soil to the lower layers. For the water lost from the earth's surface, The calculation formula is used to calculate the thickness of the soil layer; its function is to dynamically predict soil moisture and provide soil environmental data for crop growth models. A crop growth model was established based on crop water requirement and crop water index to calculate the crop height at the next time step. The specific calculation formula is as follows: in, The current crop height. The growth coefficient; By coupling the continuity equation, momentum equation, soil moisture model, and crop growth model with the three-dimensional geometric model to build a virtual model spatial framework, a high-fidelity model consistent with the physical irrigation area scenario is obtained.

5. The digital twin irrigation district full lifecycle intelligent management system for food security according to claim 1, characterized in that, Based on the disaster type determined by the scene triggering unit, the specific steps for providing multi-dimensional solution selection include: When a drought disaster is identified, incremental water supply plans, water-saving storage plans, and emergency water replenishment plans are provided by combining geographical and meteorological datasets. When a flood disaster is identified, incremental drainage schemes, seepage prevention drainage schemes, and emergency flood diversion schemes are provided by combining geographical and meteorological datasets. The incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for drought disasters, and the incremental drainage plan, seepage prevention drainage plan, and emergency flood diversion plan for flood disasters, are sent to the digital simulation module for simulation.

6. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 1, characterized in that, Based on the coupled model of the virtual mapping module, the steps for calculating the key indicators for each simulation include: Calculate the average predicted output based on the total number of simulations. The specific calculation formula is as follows: in, Let i be the output of the i-th simulation. The total number of simulations; the average predicted output reflects the average return level of the scheme; Based on average predicted output Calculations were performed to obtain the output volatility. The specific calculation formula is as follows: The extreme loss probability is calculated based on the total number of simulations. The specific calculation formula is as follows: in, To indicate function 3, This is normal production volume; The average output, output volatility, extreme loss probability, and simulation interaction results are packaged together to generate a simulation report and send it to the management execution end.

7. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 1, characterized in that, The management execution terminal includes an intelligent decision-making module, an adaptive control module, and a data management module; The intelligent decision-making module includes a scheme decision-making unit and a real-time monitoring unit; The scheme decision unit is used to eliminate high-risk and low-return schemes based on the schemes and simulation reports generated by the scheme generation module, determine the optimal scheme with crop safety as the goal, and send the execution parameters of the optimal scheme and the simulation report to the adaptive control module for execution. The real-time monitoring unit is used to receive the measured data after the adaptive control module has executed its function. The adaptive control module includes an execution monitoring unit and a data reporting unit; The execution monitoring unit is used to acquire the execution instructions of the intelligent decision-making module, parse the corresponding execution mechanism of the instructions, and collect parameters during the execution process through sensors. When the sensors detect that the current execution mechanism is abnormal, an alarm message is immediately sent to the data management module. The data reporting unit is used to push execution instructions and simulation reports from the system terminal to the management terminal, and sets a 10-minute confirmation window period. The management personnel can reject or confirm the instructions, and if no confirmation is made, the execution will be suspended. At the same time, the actual parameters after execution are sent to the intelligent decision-making module for fine-tuning.

8. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 7, characterized in that, The steps for receiving the measured data after the adaptive control module has executed include: Based on the measured data and the predicted data in the projection report, the error value is calculated; when the error value is less than or equal to the preset threshold, it is determined that the expectation has been met; when the error value is greater than the preset threshold, it is determined that the expectation has not been met. Based on the judgment result, when the judgment does not meet expectations, the adjustment amount is calculated based on the error. The specific calculation formula is as follows: in, To increase traffic, To adjust the coefficient, To mitigate execution errors; when the execution effect does not meet expectations, the flow command is corrected using a formula to ensure that the crop's water requirements are met; the fine-tuning parameters are then sent to the adaptive control module for execution.

9. The digital twin irrigation district full life-cycle intelligent management system for food security according to claim 7, characterized in that, The data management module is used to store the system's basic data and to provide final confirmation of the execution instructions.

Images