Irrigation parameter configuration method and system based on digital model processing

Abstract

The invention discloses an irrigation parameter configuration method and system based on digital model processing, and belongs to the technical field of water supply, and the method specifically comprises the steps: collecting target growth environment and state data in real time through a sensor, and building a quantitative relation model of target growth and environmental factors after preprocessing; predicting a target water demand and a water supply demand based on the model, making a preliminary water supply strategy in combination with water source and water supply facility conditions, and configuring a water supply prescription by using an intelligent optimization algorithm; combining real-time data, using a machine learning algorithm to optimize a moisture supply strategy and a moisture supply amount, and obtaining an optimized moisture supply prescription; the operation of the water supply equipment is remotely controlled through an Internet of Things method, the water supply effect is monitored in real time, the water supply prescription is regularly evaluated and adjusted, the precision, automation and intelligence of water supply are realized, and the target yield and the water resource utilization efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of water supply, and in particular relates to an irrigation parameter configuration method and system based on digital model processing. Background Art

[0002] Traditional water supply methods are often based on experience and fixed water supply plans, making them difficult to adapt to the dynamic changes in the target growth environment and the needs of different growth stages. With the development of the Internet of Things, big data, and artificial intelligence technologies, water supply decision-making systems based on target digital models are becoming an important means to improve water supply efficiency and water resource utilization. However, most existing systems only consider the basic needs of target growth and lack the ability to comprehensively consider environmental factors and dynamically adjust.

[0003] For example, Chinese patent publication CN107798471B discloses a method for optimizing water resource allocation in a multi-reservoir, multi-station system with direct canal recharge under full irrigation conditions. This technical solution, employing a dynamic programming aggregation solution, can determine the minimum water shortage for all receiving areas within a given water supply period, as well as the optimal water supply, water abandonment, and water transfer volumes for each reservoir and time period, and the water replenishment capacity of each recharge canal pumping station. This technical solution has important theoretical significance and practical application value for optimizing water resource allocation in plain reservoir irrigation areas.

[0004] For example, the Chinese patent with authorization announcement number CN115796077B discloses a method, computer device, and storage medium for allocating irrigation water in a tidal drainage irrigation area. The method includes: using MIKE11 and MIKE21 to construct a one-dimensional hydrodynamic model and a two-dimensional water flow evolution model, respectively; under simulated working conditions, the one-dimensional hydrodynamic model and the two-dimensional water flow evolution model are used to simulate the tidal drainage irrigation process and the water inflow and outflow process, obtain simulation results, and determine the tank storage change value and irrigation water consumption corresponding to the simulated working conditions. This technical solution uses MIKE11 and MIKE21 to construct a one-dimensional hydrodynamic model and a two-dimensional water flow evolution model, respectively. It combines the good operability of MIKE11 with MIKE21's excellent simulation ability of changes in flow velocity and flow field in the study area during the water inflow and outflow process, thereby achieving good operability and diversity while optimizing the allocation of irrigation water in the tidal drainage irrigation area.

[0005] The above existing technologies all have the following problems: high cost and investment, poor applicability and scalability, poor real-time performance and flexibility, and are challenging for users without a background in water conservancy engineering. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention proposes an irrigation parameter configuration method and system based on digital model processing, which collects target growth environment and status data in real time through sensors, and establishes a quantitative relationship model between target growth and environmental factors after preprocessing; based on the model, the target water demand and water supply demand are predicted, and a preliminary water supply strategy is formulated in combination with the conditions of water sources and water supply facilities, and a water supply prescription is configured using an intelligent optimization algorithm; combined with real-time data, a machine learning algorithm is used to optimize the water supply strategy and water supply amount to obtain an optimized water supply prescription; through the Internet of Things method, the operation of the water supply equipment is remotely controlled, the water supply effect is monitored in real time, and the water supply prescription is regularly evaluated and adjusted, thereby realizing the precision, automation and intelligence of water supply, and improving the target yield and water resource utilization efficiency.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An irrigation parameter configuration method based on digital model processing, comprising:

[0009] Obtain real-time target growth environment data collected by sensors;

[0010] According to the real-time target growth environment data, combined with a preset target empirical digital model, a water supply prescription map is obtained; the target empirical digital model is established based on historical target growth state data and historical target growth environment data;

[0011] The target water supply parameters are configured according to the water supply prescription map.

[0012] Specifically, obtaining a water supply prescription map based on the real-time target growth environment data in combination with a preset target empirical digital model includes:

[0013] Establishing a quantitative relationship model between target growth and environmental factors based on the real-time target growth environment data;

[0014] Based on the quantitative relationship model between target growth and environmental factors, the water demand and water supply requirements of the target at different growth stages are predicted. In combination with the distribution of water sources and the conditions of water supply facilities, a preliminary water supply strategy is formulated. Based on the preliminary water supply strategy, a water supply prescription map is configured using an intelligent optimization algorithm;

[0015] The water supply prescription map is combined with the real-time updated target growth environment data, and a target growth model and a water demand prediction model are constructed using a machine learning algorithm. The optimal water supply strategy and water supply amount are automatically calculated to obtain an optimized water supply prescription map.

[0016] Specifically, the specific steps of configuring the water supply prescription map include:

[0017] Loading the quantitative relationship model between target growth and environmental factors, and obtaining the target growth environment data at the current time;

[0018] The target growth environment data of the current time is input into the quantitative relationship model between target growth and environmental factors. , farmland moisture , farmland soil fertility Target pest and disease severity , combining the current temperature, farmland moisture, farmland soil fertility and the coefficient of target pests and diseases, and predicting the water requirement of the target at different growth stages by cumulative summation ;

[0019] Water requirements at different growth stages according to predicted targets Flow rate of water supply equipment The ratio of t and water supply volume is obtained for each target farmland. ; The water supply amount is the predicted water requirement of the target at different growth stages.

[0020] Specifically, the specific steps of configuring the water supply prescription map also include:

[0021] Based on the GIS geographic information system, we collect farmland geographic information, determine the distribution of water sources for farmland water supply, and evaluate water supply facilities to form basic farmland information;

[0022] Based on the basic farmland information, a farmland attribute layer is created, wherein the farmland attribute layer includes a soil type layer, a slope layer, a water source distribution layer, a target distribution layer, and a water supply facility layer;

[0023] Add the created soil type layer, slope layer, water source distribution layer, target distribution layer, and water supply facility layer to the same GIS project, and use the reclassification tool in the GIS software to reclassify each attribute layer.

[0024] Specifically, the specific steps of configuring the water supply prescription map also include:

[0025] Select the weighted overlay tool in the GIS software and add all reclassified attribute layers as input. Run the weighted overlay tool to generate the overlaid comprehensive attribute layer.

[0026] Based on the superimposed comprehensive attribute layer, a clustering algorithm is used to determine the final water supply area boundary, forming N independent water supply areas;

[0027] According to the calculation results of water supply time and water supply amount, a water supply schedule is set for each water supply area, and the water supply amount is allocated according to the proportion of water supply area to generate a preliminary water supply strategy;

[0028] Set the constraints of the preliminary water supply strategy, adjust the preliminary water supply strategy based on the constraints, and output the final water supply prescription using an intelligent optimization algorithm.

[0029] Specifically, the specific steps of optimizing the water supply prescription map include:

[0030] Obtaining the water supply prescription and collecting target growth environment data;

[0031] Preprocessing and feature extraction of target growth environment data to generate a target growth environment feature data set;

[0032] Load the pre-built decision tree model framework, train the pre-built decision tree model using the target growth environment feature dataset, and generate the target growth model and water demand prediction model;

[0033] Collect and update the latest data of the target growth environment in real time, input the collected real-time target growth environment data into the target growth model and water demand prediction model, and output the target growth status prediction and current water demand prediction results;

[0034] Based on the prediction results, the optimization algorithm is used to calculate the optimal water supply strategy and water supply amount;

[0035] An optimized water supply prescription is generated according to the calculated optimal water supply strategy and water supply amount, wherein the water supply prescription includes water supply time, water supply amount, and water supply method information.

[0036] An irrigation parameter configuration system based on digital model processing, comprising: a data acquisition module, a quantitative relationship model construction module, a prescription configuration module, a water supply optimization module, a water supply execution module, and an effect evaluation module;

[0037] The data acquisition module is used to collect target growth environment data and target growth status data in real time and perform preprocessing, the target growth environment data including soil moisture, temperature, and light intensity; the target growth status data including plant height, leaf area index, and biomass;

[0038] The quantitative relationship model building module establishes a quantitative relationship model between target growth and environmental factors based on the preprocessed target growth environment data and target growth status data;

[0039] The prescription configuration module formulates a preliminary water supply strategy based on the water demand and water supply requirements predicted by the target growth model, combined with the distribution of water sources and the conditions of water supply facilities, and configures the water supply prescription using an intelligent optimization algorithm;

[0040] The water supply optimization module is used to combine the water supply prescription with the real-time updated target growth environment data, and use a machine learning algorithm to dynamically adjust the water supply strategy and water supply amount to obtain an optimized water supply prescription;

[0041] The water supply execution module is used to transmit the optimized water supply prescription to the water supply control system, remotely control the water supply equipment to automatically perform water supply operations using the Internet of Things method, and monitor the water supply effect in real time through the sensor network and intelligent decision-making system;

[0042] The effect evaluation module is used to regularly evaluate the effect of water supply and adjust and optimize the water supply prescription according to the evaluation results.

[0043] Specifically, the quantitative relationship model construction module includes: a data analysis unit, a model construction unit, and a model verification unit;

[0044] The data analysis unit is used to perform statistical analysis on the pre-processed target growth environment data and target growth status data;

[0045] The model building unit uses a machine learning algorithm to build a quantitative relationship model between target growth and environmental factors;

[0046] The model verification unit verifies the quantitative relationship model through historical data.

[0047] Specifically, the prescription configuration module includes: a demand forecasting unit, a strategy formulation unit, and a prescription configuration unit;

[0048] The demand prediction unit predicts the water demand of the target at different growth stages based on the quantitative relationship model;

[0049] The strategy formulation unit is used to formulate a preliminary water supply strategy based on the distribution of water sources and the conditions of water supply facilities;

[0050] The prescription configuration unit uses an intelligent optimization algorithm to configure the water supply prescription.

[0051] Specifically, the water supply optimization module includes: a data access unit, a model building unit, and an optimization unit;

[0052] The data access unit is used to receive real-time updated target growth environment data;

[0053] The model building unit builds a target growth model and a water demand prediction model based on the water supply prescription and in combination with the target growth environment data updated in real time;

[0054] The optimization unit calculates the optimal water supply strategy and water supply amount according to the target growth model and the water demand prediction model.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. The present invention proposes an irrigation parameter configuration system based on digital model processing, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0057] 2. The present invention proposes an irrigation parameter configuration method based on digital model processing. Through real-time data collection, preprocessing and modeling, it can accurately predict the water demand and water supply requirements of the target at each growth stage. Combined with the intelligent optimization algorithm, a more scientific and reasonable water supply strategy is formulated, which effectively improves the water supply efficiency and water resource utilization rate; it uses machine learning algorithms to continuously optimize water supply prescriptions, and realizes remote automatic water supply and real-time monitoring through Internet of Things technology, which not only improves the intelligence level of water supply operations, but also ensures the continuous optimization of water supply effects.

[0058] 3. The present invention proposes an irrigation parameter configuration method based on digital model processing. Through real-time monitoring and data analysis, it realizes the accurate prediction of target water supply demand and intelligent optimization of water supply strategy, thereby improving the accuracy and efficiency of water supply. The application of Internet of Things technology makes the water supply process more automated and intelligent, which helps to monitor the water supply effect in real time and adjust the water supply prescription in time, thereby ensuring the optimal water conditions for target growth and promoting the target increase in production and income. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a schematic diagram of an irrigation parameter configuration method based on digital model processing according to the present invention;

[0060] Figure 2 This is a principle flow chart of an irrigation parameter configuration method based on digital model processing according to the present invention;

[0061] Figure 3 This is a flow chart of the method for configuring a water supply prescription according to the present invention;

[0062] Figure 4 This is an architecture diagram of an irrigation parameter configuration system based on digital model processing according to the present invention. DETAILED DESCRIPTION

[0063] Example 1

[0064] See also Figure 1 and Figure 2 The present invention provides an embodiment of an irrigation parameter configuration method based on digital model processing, the method comprising S101 to S103. The target of this application includes but is not limited to rice, wherein:

[0065] S101: Acquire real-time target growth environment data collected by sensors;

[0066] In this application, target growth environment data refers to crop growth environment data.

[0067] Among them, the target growth environment data collected in real time through the sensor network include soil moisture, temperature, and light intensity; the target growth status data include plant height, leaf area index, and biomass; the collected data are preprocessed, including data cleaning, data formatting, and data normalization to ensure data quality and analysis accuracy.

[0068] S102: Obtaining a water supply prescription map based on the real-time target growth environment data and a preset target empirical digital model; the target empirical digital model is established based on historical target growth state data and historical target growth environment data;

[0069] S103: configuring the target water supply parameters according to the water supply prescription map.

[0070] Furthermore, a method for configuring irrigation parameters based on digital model processing also includes:

[0071] S104: Transmitting the optimized water supply prescription to the water supply control system, utilizing the Internet of Things to remotely control the water supply equipment to automatically perform water supply operations according to the configured optimized water supply prescription, and monitoring the water supply effect in real time through the sensor network and intelligent decision-making system;

[0072] Furthermore, the specific steps of S104 include:

[0073] (1) The optimized water supply prescription, including water supply time, water supply amount, water supply method and other information, is transmitted from the decision-making system to the water supply control system through the TCP / IP communication protocol;

[0074] (2) The water supply control system receives the transmitted water supply prescription, analyzes it, and extracts key information such as water supply time, water supply amount, and water supply method;

[0075] (3) Based on the analyzed water supply prescription, the water supply control system remotely controls the water supply equipment, such as the switching and adjustment of water pumps and valves, through the Internet of Things technology to achieve automatic water supply;

[0076] (4) Through the sensor network installed in the farmland, such as soil moisture sensors, temperature sensors, and flow sensors, the soil moisture, temperature, water supply flow and other parameters in the water supply process are monitored in real time;

[0077] (5) The monitored data is transmitted to the intelligent decision-making system in real time for data analysis and processing to evaluate the water supply effect.

[0078] S105: Regularly evaluate the water supply effect and adjust and optimize the water supply prescription based on the evaluation results.

[0079] In the present invention, the water supply effect is regularly evaluated in a weekly manner, and the evaluation of the water supply effect includes evaluating the target growth condition, yield, and water use efficiency.

[0080] According to the real-time target growth environment data, combined with the preset target empirical digital model, a water supply prescription map is obtained, including:

[0081] A1: Establishing a quantitative relationship model between target growth and environmental factors based on the real-time target growth environment data;

[0082] Among them, the quantitative relationship model between target growth and environmental factors is to identify the growth pattern of the target under different environmental conditions.

[0083] Furthermore, the specific steps of A1 include:

[0084] A1.1: Collect and pre-process target growth environment data and target growth status data to ensure data accuracy, completeness, and consistency;

[0085] A1.2: Using a machine learning algorithm to extract environmental factors and growth status features related to target growth from the preprocessed target growth environment data and target growth status data. Principal component analysis is employed for feature extraction. Principal component analysis converts high-dimensional data into low-dimensional data through linear transformation while retaining the data's primary feature information. The specific extraction process of principal component analysis is known in the art and does not constitute an inventive solution of the present application, and is not described in detail herein.

[0086] A1.3: Based on the extracted features, use machine learning algorithms to construct a quantitative relationship model between target growth and environmental factors;

[0087] The specific steps of A1.3 include:

[0088] (1) Obtain environmental factors and growth status characteristics according to A1.2;

[0089] (2) Loading a pre-built random forest regression model, using environmental factors and growth state characteristics, combined with corresponding target growth state data as a training set, training the pre-built random forest regression model to obtain a quantitative relationship model between target growth and environmental factors, wherein the random forest regression model is the prior art content in this field and is not an inventive solution of this application, and is not described in detail here;

[0090] (3) Apply the trained quantitative relationship model between target growth and environmental factors to actual scenarios, and predict the growth of the target based on the input environmental factor characteristics.

[0091] A1.4: Use historical data to train a quantitative relationship model between target growth and environmental factors to optimize model parameters and improve prediction accuracy.

[0092] A1.5: Verify the accuracy and reliability of the model by comparing the predicted results of the quantitative relationship model between target growth and environmental factors with actual observation data.

[0093] A2: Based on the quantitative relationship model between target growth and environmental factors, the target's water demand and water supply requirements at different growth stages are predicted. A preliminary water supply strategy is developed based on the distribution of water sources and the conditions of water supply facilities. Based on this preliminary water supply strategy, an intelligent optimization algorithm is used to configure a water supply prescription map.

[0094] Among them, the water supply prescription includes the settings of water supply time, water supply amount, and water supply method parameters.

[0095] Furthermore, the preliminary water supply strategy is based on the target water demand and water supply demand predicted by the quantitative relationship model between target growth and environmental factors, and is formulated in combination with actual conditions such as water source distribution and water supply facility conditions. This strategy is preliminary and takes into account some major influencing factors, but has not yet undergone fine-grained optimization and adjustment; and the water supply prescription is a specific water supply plan that is further refined and optimized based on the water supply strategy, including detailed parameters such as water supply time, water supply amount, and water supply method. The water supply prescription is configured using an intelligent optimization algorithm in order to obtain a more accurate and efficient water supply plan, thereby avoiding deviations and deficiencies that may occur when artificially formulating water supply strategies; therefore, formulating a preliminary water supply strategy is the first step in configuring the water supply prescription, which provides a framework and constraints for the intelligent optimization algorithm, and the intelligent optimization algorithm finds the optimal solution that meets these conditions.

[0096] A3: Combine the water supply prescription map with the real-time updated target growth environment data, use machine learning algorithms to build a target growth model and a water demand prediction model, automatically calculate the optimal water supply strategy and water supply amount, and obtain the optimized water supply prescription map.

[0097] Example 2

[0098] See also Figure 3 In this embodiment, the specific steps of A2 include:

[0099] A2.1: Load the quantitative relationship model between target growth and environmental factors obtained in A1, and obtain the target growth environment data at the current time;

[0100] A2.2: Input the current target growth environment data into the quantitative relationship model between target growth and environmental factors to predict the target's water requirements at different growth stages. ; The water demand prediction formula is: ,in, Indicates the water demand of the target at different growth stages, a represents the initial value of farmland water, 、 、 and They represent the coefficients of current temperature, farmland moisture, farmland soil fertility and target pests and diseases, Indicates the current temperature. Indicates the moisture content of farmland. Indicates the fertility of farmland soil, Indicates the degree of target pests and diseases;

[0101] A2.3: Calculate the optimal water supply time for each target farmland based on the predicted water requirements at different growth stages. and water supply ,in, Indicates the flow rate of the water supply equipment;

[0102] A2.4: Using the GIS (Geographic Information System), collect farmland geographic information, determine the distribution of water sources for farmland water supply, and evaluate water supply facilities to form basic farmland information.

[0103] A2.5: Based on the basic farmland information provided by GIS, create farmland attribute layers, including soil type layers, slope layers, water source distribution layers, target distribution layers, and water supply facilities layers;

[0104] Furthermore, the specific steps of A2.5 include:

[0105] (1) Preparation:

[0106] Open the GIS software: Start ArcGIS and make sure the geographic database of the basic farmland information has been loaded.

[0107] Create a new project or file: Create a new project or file in the GIS software to store and edit the farmland attribute layer;

[0108] (2) Create soil type layer:

[0109] Create a new layer: In the GIS software, right-click the layer list and select the "New Layer" option to create a new layer to store soil type information. Import the soil type data into the newly created layer, ensuring that the data type is compatible with the GIS software and that the coordinate system is set correctly.

[0110] Edit layer properties: In the Layer Properties dialog box, set properties such as layer name, field name, and data type. For the soil type field, it is usually set to string type to store the names of different soil types.

[0111] Save the layer: Once you have finished editing, save the soil type layer and ensure it is correctly added to your GIS project.

[0112] (3) Create a slope layer:

[0113] Generate slope data: Use terrain analysis tools in GIS software, such as the "Slope" tool, to generate a slope layer based on elevation data to ensure the accuracy and completeness of elevation data;

[0114] Set slope classification: According to actual needs, divide the slope data into different categories, such as flat slope, gentle slope, and steep slope, and assign corresponding colors or symbols to each category;

[0115] Save slope layer: save the generated slope layer to the GIS project and set its name and properties;

[0116] (4) Create a water source distribution layer:

[0117] Collect water source data: Collect information on the distribution of water sources within the farm area, including the location, type, such as rivers, lakes, wells, and water volume;

[0118] Draw a water source distribution map: In GIS software, use drawing tools or import water source data to draw a water source distribution map, ensuring that the location and type of water sources are accurately represented in the map;

[0119] Add attribute information: add attribute information to the water source distribution layer, such as water source name, water volume, water quality, etc., where this information can be set through field name and data type;

[0120] Save the water source distribution layer: After completing the drawing and adding attributes, save the water source distribution layer;

[0121] (5) Create target distribution layer:

[0122] Collect target data: Collect information about the distribution of targets within the farm area, including target types, planting areas, and yields;

[0123] Draw a target distribution map: Use the drawing tools in the GIS software or import the target data to draw a target distribution map, ensuring that the target types and planting areas are accurately represented in the map;

[0124] Add attribute information: add attribute information to the target distribution layer, such as target name, growth cycle, and water requirement;

[0125] Save the target distribution layer: After completing the drawing and adding attributes, save the target distribution layer;

[0126] (6) Create a water supply facility layer:

[0127] Collect water supply facility data: Collect information on water supply facilities within the farmland area, including the location, type, capacity, and efficiency of water supply equipment, including sprinkler irrigation and drip irrigation;

[0128] Draw a map of water supply facilities: In GIS software, use drawing tools or import water supply facility data to draw a map of water supply facilities, ensuring that the location and type of water supply equipment are accurately represented in the map;

[0129] Add attribute information: Add attribute information to the water supply facility layer, such as equipment name, model, and installation date;

[0130] Save the water supply facility layer: After completing the drawing and adding attributes, save the water supply facility layer.

[0131] A2.6: Add the created soil type layer, slope layer, water source distribution layer, target distribution layer, and water supply facility layer to the same GIS project. Use the reclassification tool in the GIS software to reclassify each attribute layer to convert the attribute values in each layer into a unified evaluation level.

[0132] A2.7: Select the Weighted Overlay tool in the GIS software and add all reclassified attribute layers as input. Run the Weighted Overlay tool to generate the overlaid composite attribute layer.

[0133] A2.8: Based on the superimposed comprehensive attribute layer, use a clustering algorithm to determine the final water supply area boundaries and form N independent water supply areas;

[0134] Furthermore, after obtaining N independent water supply areas, the topology of the water supply area can also be reconstructed for each independent water supply area to achieve accurate division of the water supply area. The topology reconstruction of the water supply area adopts a reconstruction method based on graph theory, in which each water supply area is regarded as a node in the graph, and the connection relationship between the water supply areas is regarded as an edge. A topological map of the water supply area is constructed, and the weights of the edges in the topological map are adjusted or the nodes are merged or split according to the real-time evaluation results. For example, when it is found that two adjacent water supply areas have high similarity in target growth indicators and water supply requirements, they are merged into a new water supply area through edge merging operations to achieve more efficient water supply management.

[0135] A2.9: Based on the calculated water supply time and water supply amount, set a water supply schedule for each water supply area, allocate water supply amount, and generate a preliminary water supply strategy.

[0136] A2.10: Set constraints for the preliminary water supply strategy. Based on the constraints, use an intelligent optimization algorithm to adjust the preliminary water supply strategy and output the final water supply prescription. The intelligent optimization algorithm in the present invention uses a genetic algorithm, but the genetic algorithm is a prior art in this field and is not an inventive solution of this application, so it will not be described here.

[0137] The constraints of the preliminary water supply strategy in A2.10 include: ,in, Indicates the total amount of water required by the water supply system during the entire water supply cycle. The total amount of available water resources, represents the amount of water applied in the i-th water supply, Indicates the maximum amount of water that can be applied each time the water is supplied. represents the water requirement of the target at the jth growth stage, represents the growth status of the target in the jth growth stage, represents the temperature condition of the target at the jth growth stage, represents the precipitation of the target in the jth growth stage, Represents the target growth function, which is determined by the target growth model.

[0138] The specific steps of step A3 include:

[0139] A3.1: Obtain the water supply prescription in A2 and collect target growth environment data;

[0140] A3.2: Preprocessing and feature extraction of the target growth environment data to generate a target growth environment feature dataset. In the present invention, feature extraction is implemented using wavelet transform. Wavelet transform is a prior art in this field and does not constitute an inventive solution of this application, so its detailed description is omitted here.

[0141] A3.3: Load a pre-built decision tree model framework and train it using the target growth environment feature dataset to generate a target growth model and a water demand prediction model. The decision tree model is prior art in this field and does not constitute an inventive solution of this application, so its detailed description is omitted here.

[0142] A3.4: Collect and update the latest data on the target growth environment in real time, input the collected real-time target growth environment data into the target growth model and water demand prediction model, and output the target growth status prediction and current water demand prediction results;

[0143] A3.5: Based on the prediction results, an optimization algorithm is used to calculate the optimal water supply strategy and water supply amount. In the present invention, the optimization algorithm adopts a simulated annealing algorithm. The simulated annealing algorithm is a prior art in this field and does not constitute an inventive solution of this application. Therefore, it will not be described in detail here.

[0144] A3.6: Generate an optimized water supply prescription based on the calculated optimal water supply strategy and water supply amount, wherein the water supply prescription includes water supply time, water supply amount, and water supply method information.

[0145] Example 3

[0146] See also Figure 4 Another embodiment provided by the present invention is an irrigation parameter configuration system based on digital model processing, comprising:

[0147] Data acquisition module, quantitative relationship model construction module, prescription configuration module, water supply optimization module, water supply execution module, effect evaluation module;

[0148] The data acquisition module is used to collect target growth environment data and target growth status data in real time and perform preprocessing to provide data input for subsequent modeling and prediction. The target growth environment data includes soil moisture, temperature, and light intensity; the target growth status data includes plant height, leaf area index, and biomass. Preprocessing includes cleaning, denoising, outlier processing, data format conversion, and other preprocessing operations on the collected data.

[0149] A quantitative relationship model building module is used to build a quantitative relationship model between target growth and environmental factors based on the pre-processed target growth environment data and target growth status data;

[0150] The prescription configuration module formulates a preliminary water supply strategy based on the water demand and water supply requirements predicted by the target growth model, combined with the distribution of water sources and the conditions of water supply facilities, and configures the water supply prescription using an intelligent optimization algorithm;

[0151] The water supply optimization module is used to combine the water supply prescription with the real-time updated target growth environment data, and use machine learning algorithms to dynamically adjust the water supply strategy and water supply amount to obtain the optimized water supply prescription;

[0152] The water supply execution module is used to transmit the optimized water supply prescription to the water supply control system, remotely control the water supply equipment to automatically perform water supply operations using the Internet of Things method, and monitor the water supply effect in real time through the sensor network and intelligent decision-making system;

[0153] The effect evaluation module is used to regularly evaluate the effect of water supply and adjust and optimize the water supply prescription based on the evaluation results.

[0154] The quantitative relationship model construction module includes: data analysis unit, model construction unit, and model verification unit;

[0155] A data analysis unit, configured to perform statistical analysis on the pre-processed target growth environment data and target growth status data and extract features;

[0156] Model building unit, which uses machine learning algorithms to build a quantitative relationship model between target growth and environmental factors;

[0157] The model verification unit verifies the quantitative relationship model through historical data to ensure the accuracy and reliability of the quantitative relationship model.

[0158] The prescription configuration module includes: demand forecasting unit, strategy formulation unit, and prescription configuration unit;

[0159] Demand forecasting unit, which predicts the water demand of the target at different growth stages based on the quantitative relationship model;

[0160] Strategy formulation unit, used to formulate preliminary water supply strategy based on water source distribution and water supply facility conditions;

[0161] The prescription configuration unit uses an intelligent optimization algorithm to finely configure the water supply prescription.

[0162] The water supply optimization module includes: data access unit, model building unit, and optimization unit;

[0163] A data access unit, used for receiving real-time updated target growth environment data;

[0164] The model building unit builds a target growth model and a water demand prediction model based on the water supply prescription and the real-time updated target growth environment data;

[0165] The optimization unit automatically calculates the optimal water supply strategy and water supply amount based on the target growth model and water demand prediction model.

[0166] The water supply execution module includes: a prescription transmission unit, an execution unit, and a feedback unit;

[0167] a prescription transmission unit, used for transmitting the optimized water supply prescription to the water supply control system;

[0168] The execution unit uses the Internet of Things method to remotely control the water supply equipment to perform water supply operations;

[0169] The feedback unit monitors key indicators of the water supply process in real time through a sensor network and an intelligent decision-making system, and provides feedback information.

[0170] The effect evaluation module includes: effect evaluation unit and prescription optimization unit;

[0171] Effect evaluation unit, which uses big data analysis technology to regularly evaluate the effect of water supply;

[0172] The prescription optimization unit adjusts and optimizes the water supply prescription based on the evaluation results to form an improved closed-loop system.

[0173] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention. These are all protected by the present invention.

Claims

1. A method for configuring irrigation parameters based on digital model processing, characterized in that: include: Obtain real-time target growth environment data collected by sensors; According to the real-time target growth environment data, combined with a preset target empirical digital model, a water supply prescription map is obtained; the target empirical digital model is established based on historical target growth state data and historical target growth environment data; The target water supply parameters are configured according to the water supply prescription map, and the water supply equipment is controlled to perform a water supply operation according to the water supply parameters.

2. The irrigation parameter configuration method based on digital model processing according to claim 1, characterized in that: The step of obtaining a water supply prescription map based on the real-time target growth environment data and a preset target empirical digital model includes: Establishing a quantitative relationship model between target growth and environmental factors based on the real-time target growth environment data; Based on the quantitative relationship model between target growth and environmental factors, the water demand and water supply requirements of the target at different growth stages are predicted. In combination with the distribution of water sources and the conditions of water supply facilities, a preliminary water supply strategy is formulated. Based on the preliminary water supply strategy, a water supply prescription map is configured using an intelligent optimization algorithm; The water supply prescription map is combined with the real-time updated target growth environment data, and a target growth model and a water demand prediction model are constructed using a machine learning algorithm. The optimal water supply strategy and water supply amount are automatically calculated to obtain an optimized water supply prescription map.

3. The irrigation parameter configuration method based on digital model processing according to claim 2, characterized in that: The specific steps of configuring the water supply prescription map include: Loading the quantitative relationship model between target growth and environmental factors, and obtaining the target growth environment data at the current time; The target growth environment data of the current time is input into the quantitative relationship model between target growth and environmental factors. , farmland moisture , farmland soil fertility Target pest and disease severity , combining the current temperature, farmland moisture, farmland soil fertility and the coefficient of target pests and diseases, and predicting the water requirement of the target at different growth stages by cumulative summation ; Water requirements at different growth stages according to predicted targets Flow rate of water supply equipment The ratio of t and water supply volume is obtained for each target farmland. ; The water supply amount is the predicted water requirement of the target at different growth stages.

4. The irrigation parameter configuration method based on digital model processing according to claim 3, characterized in that: The specific steps of configuring the water supply prescription map also include: Based on the GIS geographic information system, we collect farmland geographic information, determine the distribution of water sources for farmland water supply, and evaluate water supply facilities to form basic farmland information; Based on the basic farmland information, a farmland attribute layer is created, wherein the farmland attribute layer includes a soil type layer, a slope layer, a water source distribution layer, a target distribution layer, and a water supply facility layer; Add the created soil type layer, slope layer, water source distribution layer, target distribution layer, and water supply facility layer to the same GIS project, and use the reclassification tool in the GIS software to reclassify each attribute layer.

5. The irrigation parameter configuration method based on digital model processing according to claim 4, characterized in that: The specific steps of configuring the water supply prescription map also include: Select the weighted overlay tool in the GIS software and add all reclassified attribute layers as input. Run the weighted overlay tool to generate the overlaid comprehensive attribute layer. Based on the superimposed comprehensive attribute layer, a clustering algorithm is used to determine the final water supply area boundary, forming N independent water supply areas; According to the calculation results of water supply time and water supply amount, a water supply schedule is set for each water supply area, and the water supply amount is allocated according to the proportion of water supply area to generate a preliminary water supply strategy; Set the constraints of the preliminary water supply strategy, adjust the preliminary water supply strategy based on the constraints, and output the final water supply prescription using an intelligent optimization algorithm.

6. The irrigation parameter configuration method based on digital model processing according to claim 5, characterized in that: The specific steps of optimizing the water supply prescription map include: Obtaining the water supply prescription and collecting target growth environment data; Preprocessing and feature extraction of target growth environment data to generate a target growth environment feature data set; Load the pre-built decision tree model framework, train the pre-built decision tree model using the target growth environment feature dataset, and generate the target growth model and water demand prediction model; Collect and update the latest data of the target growth environment in real time, input the collected real-time target growth environment data into the target growth model and water demand prediction model, and output the target growth status prediction and current water demand prediction results; Based on the prediction results, the optimization algorithm is used to calculate the optimal water supply strategy and water supply amount; An optimized water supply prescription is generated according to the calculated optimal water supply strategy and water supply amount, wherein the water supply prescription includes water supply time, water supply amount, and water supply method information.

7. An irrigation parameter configuration system based on digital model processing, which is used to implement the irrigation parameter configuration method based on digital model processing according to any one of claims 1 to 6, characterized in that: include: Data acquisition module, quantitative relationship model construction module, prescription configuration module, water supply optimization module, water supply execution module, effect evaluation module; The data acquisition module is used to collect target growth environment data and target growth status data in real time and perform preprocessing, the target growth environment data including soil moisture, temperature, and light intensity; the target growth status data including plant height, leaf area index, and biomass; The quantitative relationship model building module establishes a quantitative relationship model between target growth and environmental factors based on the preprocessed target growth environment data and target growth status data; The prescription configuration module formulates a preliminary water supply strategy based on the water demand and water supply requirements predicted by the target growth model, combined with the distribution of water sources and the conditions of water supply facilities, and configures the water supply prescription using an intelligent optimization algorithm; The water supply optimization module is used to combine the water supply prescription with the real-time updated target growth environment data, and use a machine learning algorithm to dynamically adjust the water supply strategy and water supply amount to obtain an optimized water supply prescription; The water supply execution module is used to transmit the optimized water supply prescription to the water supply control system, remotely control the water supply equipment to automatically perform water supply operations using the Internet of Things method, and monitor the water supply effect in real time through the sensor network and intelligent decision-making system; The effect evaluation module is used to regularly evaluate the effect of water supply and adjust and optimize the water supply prescription according to the evaluation results.

8. The irrigation parameter configuration system based on digital model processing according to claim 7, characterized in that: The quantitative relationship model construction module includes: a data analysis unit, a model construction unit, and a model verification unit; The data analysis unit is used to perform statistical analysis on the pre-processed target growth environment data and target growth status data; The model building unit uses a machine learning algorithm to build a quantitative relationship model between target growth and environmental factors; The model verification unit verifies the quantitative relationship model through historical data.

9. The irrigation parameter configuration system based on digital model processing according to claim 8, characterized in that: The prescription configuration module includes: a demand forecasting unit, a strategy formulation unit, and a prescription configuration unit; The demand prediction unit predicts the water demand of the target at different growth stages based on the quantitative relationship model; The strategy formulation unit is used to formulate a preliminary water supply strategy based on the distribution of water sources and the conditions of water supply facilities; The prescription configuration unit configures the water supply prescription using an intelligent optimization algorithm.

10. The irrigation parameter configuration system based on digital model processing according to claim 9, characterized in that: The water supply optimization module includes: a data access unit, a model building unit, and an optimization unit; The data access unit is used to receive real-time updated target growth environment data; The model building unit builds a target growth model and a water demand prediction model based on the water supply prescription and in combination with the target growth environment data updated in real time; The optimization unit calculates the optimal water supply strategy and water supply amount according to the target growth model and the water demand prediction model.

Images