An intelligent control method and system for forage grass planting irrigation

Abstract

This application provides a method and system for intelligent control of irrigation in forage planting. Based on the humidity distribution characteristics of the target forage planting area and the water stress index of the target forage, a regional soil moisture distribution map is constructed, and the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map is determined. Confidence decisions are made on the irrigation amount for each grid area within the future irrigation window period using each effective utilization coefficient and the water requirement threshold of each growth stage of the target forage. Based on these confidence decisions and the hydraulic constraints of the irrigation equipment, the irrigation travel path and valve opening of the irrigation equipment are optimized through multi-objective collaboration, generating an irrigation instruction set including irrigation sequence, travel speed, and valve control parameters, driving the irrigation equipment to perform variable irrigation operations. Based on the above scheme, variable irrigation decision-making based on multi-source data fusion and multi-objective collaboration can be achieved.

Description

Technical Field

[0001] This application relates to the field of agricultural irrigation technology, and more specifically, to a method and system for intelligent control of irrigation for forage planting. Background Technology

[0002] Forage cultivation refers to the agricultural activity of cultivating forage or feed crops on a large scale for livestock production. The cultivation process includes land preparation, variety selection, sowing, water and fertilizer management, pest and disease control, and timely harvesting. Forage cultivation is not only directly related to the safety and cost of livestock feed, but also profoundly affects soil health, water resource utilization, and the sustainability of agricultural ecosystems.

[0003] Existing irrigation decision-making technologies generally suffer from limitations such as single data sources and insufficient sensing dimensions. They rely solely on discrete soil moisture monitoring data or strictly adhere to pre-set fixed irrigation plans. This approach, which substitutes local environmental variables or historical experience for the actual needs of crops, fails to acquire and analyze direct signals reflecting the crop's own water physiological state. It cannot determine whether the crop is experiencing water stress and the degree of stress, nor can it perceive the dynamic changes in its water requirements at different growth stages. The decision-making process is disconnected from the actual physiological state of the crop, leading to irrigation operations often lagging behind the crop's true needs or wasting water resources unnecessarily, making it difficult to achieve precise, on-demand water supply. Therefore, how to achieve variable irrigation decision-making based on multi-source data fusion and multi-objective collaboration to improve water use efficiency in forage cultivation has become a challenge for the industry. Summary of the Invention

[0004] This application provides a method and system for intelligent regulation of irrigation in forage planting, which can realize variable irrigation decision-making based on multi-source data fusion and multi-objective collaboration, thereby improving the water use efficiency of forage planting.

[0005] Firstly, this application provides a method for intelligent regulation and control of irrigation for forage planting, including: Acquire multi-source monitoring data of the target forage planting area, including canopy spectral data and root zone soil moisture profile data; The water stress index of the target forage is extracted from the canopy spectral data. A regional soil moisture distribution map is constructed based on the water stress index and the humidity distribution characteristics in the humidity profile data. Then, the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map is determined. By using various effective utilization coefficients and water requirement thresholds for each growth stage of the target forage, a multi-period confidence decision is made on the irrigation amount of each grid area within the future irrigation window, resulting in the confidence decision value of the irrigation amount of each grid area within the future irrigation window. Based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment, the irrigation travel path and valve group opening of the irrigation equipment are optimized in a multi-objective collaborative manner, generating an irrigation instruction set including irrigation sequence, travel speed and valve control parameters, which drives the irrigation equipment to perform variable irrigation operations.

[0006] In some embodiments, extracting the water stress index of the target forage from the canopy spectral data specifically includes: The canopy spectral data are preprocessed, including atmospheric correction, radiometric calibration, and noise filtering. Determine the reflectance ratio of the near-infrared band to the red-edge band in the preprocessed canopy spectral data; Auxiliary characteristics of the target forage grass were determined by vegetation indices and red-edge vegetation indices in the preprocessed canopy spectral data. The water stress index of the target forage is determined based on the reflectance ratio and the auxiliary features.

[0007] In some embodiments, constructing a regional soil moisture distribution map based on the moisture stress index and the humidity distribution characteristics in the humidity profile data specifically includes: The humidity profile data is divided vertically into multiple humidity features, including surface humidity, root distribution layer humidity, and deep humidity. Rasterized spatial interpolation is performed on each layer of humidity features of the moisture stress index and the multi-layer humidity features to obtain the regional distribution layer of soil moisture index for each region. By overlaying and merging the various regional distribution layers, a regional soil moisture distribution map is obtained.

[0008] In some embodiments, determining the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map specifically includes: The soil moisture distribution map of the region is divided into multiple grid regions with homogeneous moisture conditions; For each grid area of ​​the regional soil moisture distribution map, determine the humidity deviation between the average humidity of the root distribution layer in the grid area and the target humidity threshold. Determine the risk factor for evaporation loss of surface humidity in the grid area; The effective utilization coefficient of irrigation water in the sub-region is determined based on the humidity deviation and the evaporation loss risk coefficient, thereby obtaining the effective utilization coefficient of irrigation water in each grid sub-region of the regional soil moisture distribution map.

[0009] In some embodiments, the irrigation amount of each grid area within a future irrigation window is determined by multi-period confidence decision based on various effective utilization coefficients and water requirement thresholds at various growth stages of the target forage, resulting in confidence decision values ​​for the irrigation amount in each grid area within the future irrigation window. Specifically, this includes: For each grid area, obtain meteorological forecast data for the future irrigation window period to predict the reference crop evapotranspiration and effective rainfall for the grid area; Based on the reference crop evapotranspiration, the effective rainfall, the crop coefficient of the target forage at the current growth stage, and the water requirement threshold, the theoretical net water requirement of the grid area is calculated. The theoretical net water demand is corrected based on the effective utilization coefficient of the grid area to obtain the confidence decision value of irrigation amount in the grid area within multiple future decision periods, and then the confidence decision value of irrigation amount in each grid area within the future irrigation window period is obtained.

[0010] In some embodiments, multi-objective collaborative optimization of the irrigation travel path and valve group opening of the irrigation equipment is performed based on various confidence decision values ​​and hydraulic constraints of the irrigation equipment to generate an irrigation instruction set including irrigation sequence, travel speed, and valve orifice control parameters. Specifically, this includes: The irrigation equipment is modeled as a mobile service node, and the hydraulic constraints include pipeline pressure limits, minimum / maximum valve opening, and minimum transition time between adjacent irrigation points. A multi-objective optimization model is constructed with the objectives of minimizing total operation time, energy consumption, and irrigation uniformity. Each confidence decision value is used as a constraint on irrigation demand in the multi-objective optimization model; A multi-objective optimization model is used to iteratively optimize the feasible path sequence and valve group opening combination of irrigation equipment to obtain an irrigation instruction set including irrigation sequence, travel speed and valve control parameters.

[0011] In some embodiments, the irrigation equipment is a variable irrigation machine based on autonomous combined navigation.

[0012] Secondly, this application provides an intelligent control system for irrigation of forage crops, comprising: The acquisition module is used to acquire multi-source monitoring data of the target forage planting area, including canopy spectral data and root zone soil moisture profile data. The processing module is used to extract the water stress index of the target forage from the canopy spectral data, construct a regional soil moisture distribution map based on the water stress index and the humidity distribution characteristics in the humidity profile data, and then determine the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map. The processing module is also used to make multi-period confidence decisions on the irrigation amount of each grid area within the future irrigation window period based on each effective utilization coefficient and the water requirement threshold of each growth stage of the target forage, so as to obtain the confidence decision value of the irrigation amount of each grid area within the future irrigation window period. The execution module is used to perform multi-objective collaborative optimization of the irrigation travel path and valve group opening of the irrigation equipment based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment. It generates an irrigation instruction set including irrigation sequence, travel speed and valve control parameters, and drives the irrigation equipment to perform variable irrigation operations.

[0013] Thirdly, this application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent control method for forage planting and irrigation.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned intelligent control method for forage planting and irrigation.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: This application provides a method and system for intelligent regulation and control of irrigation for forage planting. The method involves acquiring multi-source monitoring data of a target forage planting area, including canopy spectral data and root zone soil moisture profile data. A water stress index for the target forage is extracted from the canopy spectral data. Based on the water stress index and the moisture distribution characteristics in the moisture profile data, a regional soil moisture distribution map is constructed, thereby determining the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map. Multi-period confidence decisions are made on the irrigation amount in each grid area during the future irrigation window period using each effective utilization coefficient and the water requirement threshold for each growth stage of the target forage. Confidence decision values ​​for the irrigation amount in each grid area during the future irrigation window period are obtained. Based on each confidence decision value and the hydraulic constraints of the irrigation equipment, multi-objective collaborative optimization is performed on the irrigation travel path and valve opening of the irrigation equipment. An irrigation instruction set, including irrigation sequence, travel speed, and valve control parameters, is generated to drive the irrigation equipment to perform variable irrigation operations.

[0016] Therefore, this application utilizes a multi-objective collaborative optimization of the irrigation travel path and valve opening of the irrigation equipment based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment. This generates an irrigation instruction set including irrigation sequence, travel speed, and valve control parameters, driving the irrigation equipment to perform variable irrigation operations. Firstly, determining the effective utilization coefficient of irrigation water yields a quantitative efficiency index reflecting soil spatial heterogeneity and potential water transport losses. The effective utilization coefficient integrates surface evaporation risk and root zone water deficit, transforming qualitative water distribution characteristics into calculable efficiency correction parameters. It establishes a mapping relationship from non-uniform soil moisture distribution to differentiated irrigation efficiency, providing a regional efficiency correction benchmark for irrigation volume decisions. This fundamentally avoids the local water waste or insufficient supply problems caused by neglecting soil spatial variability in traditional uniform irrigation decisions, ensuring that subsequent irrigation decisions can be differentiated based on the actual regional water use potential, thus improving efficiency. This lays the foundation for the conversion of quantity and efficiency in overall water use efficiency. Then, by determining the confidence decision value for irrigation volume, a dynamic irrigation plan integrating future weather uncertainties and crop stage-specific water requirements can be obtained. This decision value, by combining the effective utilization coefficient with a multi-period water demand prediction model, realizes the transformation of irrigation decision-making from static response to rolling optimization in the time dimension. It reflects both the inherent uncertainty of weather forecasts and meets the deterministic threshold requirements of crop growth, upgrading a single irrigation volume recommendation into a decision scheme that includes risk assessment. This enables the irrigation system to maintain decision robustness under climate change conditions, avoiding insufficient or excessive irrigation caused by weather forecast deviations. It allows water resources to dynamically match crop needs in both time and space, thereby optimizing water use efficiency. In summary, based on the above scheme, variable irrigation decision-making based on multi-source data fusion and multi-objective collaboration can be achieved, thereby improving the water use efficiency of forage planting. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is an exemplary flowchart of an intelligent control method for forage planting irrigation according to some embodiments of this application; Figure 2 This is a flowchart illustrating the process of determining confidence decision values ​​according to some embodiments of this application; Figure 3 This is a schematic diagram of the structure of an intelligent control system for forage planting irrigation according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a computer device for implementing an intelligent control method for forage planting and irrigation, according to some embodiments of this application. Detailed Implementation

[0019] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] refer to Figure 1 The figure is an exemplary flowchart of an intelligent control method for irrigation of forage planting according to some embodiments of this application. The intelligent control method for irrigation of forage planting mainly includes the following steps: In step 101, multi-source monitoring data of the target forage planting area is obtained, including canopy spectral data and root zone soil moisture profile data.

[0021] It should be noted that, in this application, the target forage planting area is the geographic spatial range used to implement the intelligent irrigation control method; multi-source monitoring data is a collection of sensor data from multiple sources used to comprehensively diagnose crop water status and environmental conditions; canopy spectral data is aerial and ground remote sensing reflectance spectral data used to invert the physiological state of the forage canopy and the degree of water stress; and humidity profile data is continuous monitoring data from underground sensors characterizing the vertical distribution of soil moisture in and below the crop root activity layer.

[0022] In practice, multi-source monitoring data of the target forage planting area is acquired. Under clear, cloudless weather conditions, a drone platform equipped with multispectral or hyperspectral sensors performs low-altitude flight scans of the target area within a set time window to acquire canopy spectral image data covering the entire area. Simultaneously, a network of multiple soil moisture sensors pre-installed in typical plots continuously collects volumetric water content data of soil layers at different depths at fixed time intervals, forming soil moisture profile data of the root zone. The canopy spectral images acquired from the air are synchronized with the moisture profile data collected by the ground sensor network in terms of time and geographic coordinates. The registered canopy spectral image data and soil moisture profile data are then combined into multi-source monitoring data of the target forage planting area.

[0023] In step 102, the water stress index of the target forage is extracted from the canopy spectral data. Based on the water stress index and the humidity distribution characteristics in the humidity profile data, a regional soil moisture distribution map is constructed, and then the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map is determined.

[0024] In some embodiments, extracting the water stress index of the target forage from the canopy spectral data can be achieved using the following steps: The canopy spectral data are preprocessed, including atmospheric correction, radiometric calibration, and noise filtering. Determine the reflectance ratio of the near-infrared band to the red-edge band in the preprocessed canopy spectral data; Auxiliary characteristics of the target forage grass were determined by vegetation indices and red-edge vegetation indices in the preprocessed canopy spectral data. The water stress index of the target forage is determined based on the reflectance ratio and the auxiliary features.

[0025] It should be noted that, in this application, atmospheric correction is a process used to eliminate interference caused by atmospheric scattering and absorption on the canopy reflectance spectral signal received by the remote sensing sensor; radiometric calibration is a process used to convert the raw digital quantization values ​​recorded by the sensor into physically meaningful apparent reflectance or radiance values; noise filtering is a process used to suppress and remove abnormal fluctuations in the canopy spectral data caused by sensor noise or instantaneous environmental interference; the reflectance ratio of the near-infrared band to the red-edge band is a spectral index feature used to enhance sensitivity to changes in vegetation moisture content; the vegetation index is a calculation parameter used to assess the greenness status of vegetation cover; the red-edge vegetation index is a calculation parameter used to assess the early response of perceived vegetation to physiological stress; auxiliary features are a set of derived spectral parameters that enhance the robustness of water stress index estimation; and the water stress index is an evaluation index that quantifies the degree to which the physiological growth of target forage is restricted due to insufficient water supply.

[0026] In specific implementation, firstly, the canopy spectral data is preprocessed. This preprocessing includes atmospheric correction, radiometric calibration, and noise filtering. This can be achieved as follows: Preprocessing the canopy spectral data to improve data quality and usability involves using a mature atmospheric radiative transfer model, combined with meteorological parameters from the acquisition time, to perform atmospheric correction on the original canopy spectral data, eliminating atmospheric influences. Using the calibration coefficients provided with the sensor at the factory, the atmospherically corrected data is radiometrically calibrated and converted into surface reflectance. Noise filtering is then applied to the radiometrically calibrated reflectance data using methods such as moving window averaging or wavelet transform to smooth abnormal spectral curves, ultimately obtaining reliable preprocessed canopy spectral data. Secondly, determining the reflectance ratio of the near-infrared band to the red-edge band in the preprocessed canopy spectral data can be achieved as follows: Extracting the average reflectance value within a predefined near-infrared band range and the average reflectance value within the red-edge band range from the preprocessed canopy spectral data, dividing these two reflectance values, and calculating the reflectance ratio of the near-infrared band to the red-edge band. The ratio of vegetation index to red edge vegetation index is used to determine the auxiliary characteristics of the target forage. This can be achieved by: calculating the vegetation index based on the reflectance of the red and near-infrared bands in the preprocessed canopy spectral data using the normalized difference vegetation index formula; calculating the red edge vegetation index based on the reflectance of the near-infrared and red edge bands in the preprocessed canopy spectral data using the normalized difference vegetation index formula; and using the set of vegetation index and red edge vegetation index as a reference. Auxiliary features; Finally, the water stress index of the target forage can be determined based on the reflectance ratio and the auxiliary features in the following manner: the calculated reflectance ratio of the near-infrared band and the red-edge band, as well as the auxiliary features consisting of the vegetation index and the red-edge vegetation index, are input into a multivariate regression model that has been trained with experimental data. The multivariate regression model fits the relationship between these input features and the measured leaf water potential or soil-plant continuum water status, and finally outputs the quantified water stress index of the target forage.

[0027] In some embodiments, constructing a regional soil moisture distribution map based on the moisture stress index and the humidity distribution characteristics in the humidity profile data can be achieved through the following steps: The humidity profile data is divided vertically into multiple humidity features, including surface humidity, root distribution layer humidity, and deep humidity. Rasterized spatial interpolation is performed on each layer of humidity features of the moisture stress index and the multi-layer humidity features to obtain the regional distribution layer of soil moisture index for each region. By overlaying and merging the various regional distribution layers, a regional soil moisture distribution map is obtained.

[0028] It should be noted that, in this application, surface moisture is a moisture characteristic representing the moisture status of the shallowest soil layer directly affected by meteorological factors; root distribution layer moisture is a moisture characteristic representing the average moisture status of the soil depth range where the target forage roots mainly absorb water and nutrients; deep moisture is a moisture characteristic representing the moisture replenishment potential of deep soil below the root distribution layer; multi-layer moisture characteristics are a data set reflecting the vertical distribution structure of moisture in different functional layers of the soil profile; regional distribution layer is a digital image used to express the continuous spatial distribution of specified soil moisture indicators in the target forage planting area in the form of raster cells; and regional moisture distribution map is a thematic geographic information map used to visually display the comprehensive spatial distribution of soil moisture in the target forage planting area.

[0029] In specific implementation, the humidity profile data can be divided into multiple humidity features in the vertical direction, namely, surface humidity, root distribution layer humidity and deep humidity. This can be achieved in the following way: based on the typical root depth distribution pattern of the target forage, the specific upper and lower limits of the root distribution layer (e.g., 0-30 cm) are determined, and the average humidity of the shallow soil above this depth (e.g., 0-10 cm) is classified as surface humidity, and the average humidity of the soil below this depth (e.g., 30-50 cm) is classified as deep humidity. Therefore, the original continuous or layered humidity profile data is analyzed into multi-layered humidity characteristics that reflect the vertical structure of soil moisture, consisting of surface humidity, root distribution layer humidity, and deep humidity. Then, rasterized spatial interpolation is performed on each layer of the humidity characteristics, including the water stress index and the multi-layered humidity features, to obtain the regional distribution layers of soil moisture indicators for each area. This can be achieved as follows: using the locations of the sensor monitoring points deployed in the field as spatial coordinates, and their corresponding values ​​for the water stress index, surface humidity, root distribution layer humidity, and deep humidity as attribute values, rasterized spatial interpolation is performed using the Kriging spatial interpolation algorithm. Each indicator generates a raster layer with uniform resolution, resulting in a layer covering the entire target forage for water stress index and each humidity layer. The pixel values ​​of the planting area represent the regional distribution layer of the index. Finally, the various regional distribution layers are overlaid and fused to obtain the regional soil moisture distribution map. This can be achieved in the following way: using the layer weighted overlay fusion method in the geographic information system, the generated regional distribution layers of water stress index, surface humidity, root distribution layer humidity, and deep humidity are overlaid. According to the contribution of different indicators to irrigation decisions, a weight coefficient is assigned to each layer. At the scale of the raster cell, the pixel values ​​of the corresponding positions of each layer are multiplied and accumulated with the weight coefficient. Then, the accumulated result is normalized to finally generate a regional soil moisture distribution map with values ​​between 0 and 1 that comprehensively reflects the regional water status.

[0030] In some embodiments, determining the effective utilization coefficient of irrigation water in each grid region of a regional soil moisture distribution map can be achieved by the following steps: The soil moisture distribution map of the region is divided into multiple grid regions with homogeneous moisture conditions; For each grid area of ​​the regional soil moisture distribution map, determine the humidity deviation between the average humidity of the root distribution layer in the grid area and the target humidity threshold. Determine the risk factor for evaporation loss of surface humidity in the grid area; The effective utilization coefficient of irrigation water in the sub-region is determined based on the humidity deviation and the evaporation loss risk coefficient, thereby obtaining the effective utilization coefficient of irrigation water in each grid sub-region of the regional soil moisture distribution map.

[0031] It should be noted that, in this application, the grid area is the basic spatial analysis unit used for unitized management and decision-making of irrigation; the humidity deviation is a parameter used to quantify the degree to which the actual soil moisture content in a single grid area deviates from the target ideal moisture state; the evaporation loss risk coefficient is a parameter used to assess the likelihood of water loss due to surface evaporation after irrigation; and the irrigation water effective utilization coefficient is a percentage indicator used to characterize the efficiency of irrigation water being effectively absorbed and utilized by crops.

[0032] In specific implementation, firstly, dividing the regional soil moisture distribution map into multiple grid sub-regions with homogeneous moisture conditions can be achieved in the following way: using an equal-interval division method or a natural breakpoint method based on the regional soil moisture distribution map values, the numerical range of the distribution map is divided into several consecutive numerical intervals, and all grid cells on the distribution map falling into the same numerical interval are merged into a grid sub-region with homogeneous moisture conditions. For example, all grid cells with distribution map values ​​between 0.7 and 0.8 are merged into a sub-region, thereby dividing the entire target area into multiple grid sub-regions with homogeneous moisture conditions. Secondly, for each grid sub-region of the regional soil moisture distribution map, determining the humidity deviation between the average humidity of the root distribution layer in the grid sub-region and the target humidity threshold can be achieved in the following way: for a grid sub-region, the root distribution layer humidity values ​​corresponding to all grid cells in the region are extracted from the regional soil moisture distribution map, and the arithmetic mean of these humidity values ​​is calculated to obtain the average humidity of the root distribution layer in the grid sub-region. Based on the current growth stage of the target forage, a suitable target humidity threshold (e.g., 25% volumetric water content) is set. The absolute difference between the average humidity of the root distribution layer and the target humidity threshold is calculated, and this difference is divided by the target humidity threshold to obtain a dimensionless proportional value, which is used as the humidity deviation of the grid area. Then, the evaporation loss risk coefficient of surface humidity in the grid area can be determined as follows: for the same grid area, the surface humidity values ​​corresponding to all grid cells in the area are extracted from the regional soil moisture distribution map, and their arithmetic mean is calculated as the average surface humidity. Risk assessment rules are established based on the relationship between the average surface humidity and the set soil field capacity. For example, the lower the average surface humidity (drought), the higher the potential risk of irrigation water penetrating into the dry soil and being rapidly evaporated. According to such rules or a preset risk comparison table, each grid sub-region is assigned a value between 0 and 1. This value is the evaporation loss risk coefficient for that grid sub-region. The larger the coefficient, the greater the possibility of water evaporation loss after irrigation. Finally, the effective utilization coefficient of irrigation water in the sub-region is determined based on the humidity deviation and the evaporation loss risk coefficient. The effective utilization coefficient of irrigation water in each grid sub-region of the regional soil moisture distribution map can be obtained in the following way: For each grid sub-region, the calculated humidity deviation is multiplied by an influence weight α (α>0), and the evaporation loss risk coefficient is multiplied by another influence weight β (β>0). Then, the difference between 1 and the sum of these two weighted terms is calculated, i.e., 1-(α×humidity deviation+β×evaporation loss risk coefficient). To ensure the rationality of the coefficient, this calculation result is limited to the range of 0 to 1, with 0 taken when it is below 0 and 1 taken when it is above 1.The value calculated in this way is the irrigation water effective utilization coefficient of the grid area. The irrigation water effective utilization coefficient comprehensively reflects the impact of water deficit and potential evaporation loss on the effectiveness of irrigation water. By repeating this process for all grid areas, the irrigation water effective utilization coefficient of all grid areas within the target forage planting area can be obtained.

[0033] In step 103, the irrigation amount of each grid area within the future irrigation window is determined by multi-period confidence decision based on the effective utilization coefficients and the water requirement thresholds of each growth stage of the target forage, so as to obtain the confidence decision value of the irrigation amount of each grid area within the future irrigation window.

[0034] In some embodiments, multi-period confidence decisions are made on the irrigation amount of each grid area within a future irrigation window based on various effective utilization coefficients and water requirement thresholds at each growth stage of the target forage, resulting in confidence decision values ​​for the irrigation amount in each grid area within the future irrigation window. Figure 2 The diagram is a flowchart illustrating the determination of confidence decision values ​​in some embodiments of this application. In this embodiment, the determination of confidence decision values ​​can be achieved using the following steps: In step 1031, for each grid area, meteorological forecast data for the future irrigation window period is obtained to predict the reference crop evapotranspiration and effective rainfall for the grid area; In step 1032, the theoretical net water requirement of the grid area is calculated based on the reference crop evapotranspiration, the effective rainfall, the crop coefficient of the target forage at the current growth stage, and the water requirement threshold. In step 1033, the theoretical net water demand is corrected according to the effective utilization coefficient of the grid area to obtain the confidence decision value of the irrigation amount in the grid area within multiple future decision periods, and then the confidence decision value of the irrigation amount in each grid area within the future irrigation window period is obtained.

[0035] It should be noted that, in this application, meteorological forecast data is a set of basic data used to predict the impact of weather conditions on crop water requirements and soil moisture balance over a future period; reference crop evapotranspiration is a parameter used to calculate the total potential of water evaporation and surface evaporation consumption of standard reference vegetation under specified meteorological conditions; effective rainfall is a parameter used to calculate the portion of precipitation that can be effectively retained by the soil and utilized by crops during a rainfall event; the crop coefficient is an empirical proportionality coefficient used to convert standard reference crop evapotranspiration into the actual water requirements of a specified crop and a specified growth stage; theoretical net water requirement is used to characterize the amount of water that needs to be supplemented by irrigation after deducting effective rainfall to meet the normal growth requirements of the target forage under ideal conditions; and confidence decision value is a numerical range or probability distribution result used to quantify the recommended irrigation amount and its predicted confidence level at different decision points in the future.

[0036] In practice, firstly, for each grid area, meteorological forecast data for the future irrigation window is acquired. The reference crop evapotranspiration and effective rainfall for the grid area can be predicted as follows: For each grid area, meteorological forecast data covering the future irrigation window (e.g., the next 5 days) is acquired from a public meteorological service platform or a dedicated meteorological station network. This data includes daily maximum and minimum temperatures, average humidity, sunshine hours, wind speed, and other information. Based on the acquired meteorological forecast data, the daily reference crop evapotranspiration for the grid area is calculated using the Penman-Montess formula recommended by the FAO. Simultaneously, based on the predicted daily rainfall... Using a soil water-holding capacity model, after deducting runoff and deep seepage losses, the daily effective rainfall for the grid area is calculated. Then, based on the reference crop evapotranspiration, the effective rainfall, the crop coefficient of the target forage at its current growth stage, and the water requirement threshold, the theoretical net water requirement of the grid area can be calculated in the following way: Determine the corresponding crop coefficient and the soil moisture requirement threshold for maintaining healthy growth based on the target forage's current growth stage (e.g., tillering stage, jointing stage) from a table; Calculate the daily theoretical net water requirement of the grid area according to the crop water requirement principle. The calculation logic is: multiply the reference crop evapotranspiration by the crop coefficient to obtain the actual crop evapotranspiration. The actual crop evapotranspiration is then subtracted from the effective rainfall on the same day. If the result is positive, it represents the theoretical net water requirement that needs to be supplemented by irrigation on that day; if the result is negative or zero, the theoretical net water requirement is counted as zero. The daily results within the window period are accumulated to obtain the theoretical net water requirement for that grid area in future window periods. Finally, the theoretical net water requirement is corrected according to the effective utilization coefficient of the grid area to obtain the confidence decision value of irrigation amount in the grid area in multiple future decision periods. The confidence decision value of irrigation amount in each grid area in future irrigation window periods can be obtained by multiplying the theoretical net water requirement by the irrigation water amount of the grid area. An effective utilization coefficient is used to correct for the actual usable efficiency loss caused by differences in soil characteristics, resulting in a preliminary recommended irrigation amount. Taking into account the uncertainty of weather forecasts (e.g., the error distribution of precipitation prediction), a confidence interval is generated based on the preliminary recommended irrigation amount using Monte Carlo simulation or a probability distribution method based on historical errors. This interval could be a range of irrigation amounts at a 90% confidence level, or a probability distribution with expected value and variance. This allows us to obtain the confidence decision value of the irrigation amount with confidence information for each decision period in the grid area. Through the above methods, the confidence decision value of the irrigation amount in each grid area within the future irrigation window can be obtained.

[0037] In step 104, based on each confidence decision value and the hydraulic constraints of the irrigation equipment, the irrigation travel path and valve group opening of the irrigation equipment are optimized in a multi-objective collaborative manner to generate an irrigation instruction set including irrigation sequence, travel speed and valve control parameters, which drives the irrigation equipment to perform variable irrigation operations.

[0038] In some embodiments, the irrigation travel path and valve group opening of the irrigation equipment are optimized in a multi-objective manner based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment, and an irrigation instruction set including irrigation sequence, travel speed and valve orifice control parameters is generated. This can be achieved by the following steps: The irrigation equipment is modeled as a mobile service node, and the hydraulic constraints include pipeline pressure limits, minimum / maximum valve opening, and minimum transition time between adjacent irrigation points. A multi-objective optimization model is constructed with the objectives of minimizing total operation time, energy consumption, and irrigation uniformity. Each confidence decision value is used as a constraint on irrigation demand in the multi-objective optimization model; A multi-objective optimization model is used to iteratively optimize the feasible path sequence and valve group opening combination of irrigation equipment to obtain an irrigation instruction set including irrigation sequence, travel speed and valve control parameters.

[0039] It should be noted that, in this application, the irrigation equipment is a variable irrigation machine based on autonomous combined navigation; the mobile service node is an abstract mathematical model used to characterize a unit with mobility and irrigation service functions; the hydraulic constraints are a set of boundary conditions used to limit the physical operating boundary of the irrigation system to ensure operational safety and feasibility; the multi-objective optimization model is a mathematical model used to seek the best balance solution among multiple conflicting objectives; the irrigation demand constraint is a constraint used to ensure that the irrigation scheme solved by the multi-objective optimization model can meet the basic water demand requirements of each region; the feasible path sequence is an ordered access route used to determine the irrigation equipment to visit each irrigation service point in sequence without violating the movement constraints; the valve group opening combination is a set of opening degrees of each irrigation valve group at the corresponding service point when the irrigation equipment moves along the path sequence; and the irrigation instruction set is a data set containing a series of executable control parameters used to directly drive the irrigation equipment to perform precise variable irrigation operations.

[0040] In practical implementation, firstly, the irrigation equipment is modeled as a mobile service node. The hydraulic constraints, including pipeline pressure limits, minimum / maximum valve openings, and minimum transition time between adjacent irrigation points, can be implemented as follows: the irrigation equipment (e.g., a mobile sprinkler or translator) is abstracted as a mobile service node capable of moving along a preset track or road and stopping at a designated irrigation point (corresponding to the center point of the grid area) to perform irrigation operations. Simultaneously, the hydraulic constraints that the equipment must satisfy during operation are defined: pipeline pressure limits specify the minimum and maximum operating pressure range for the water delivery system to operate safely; the minimum and maximum valve openings specify the lower and upper boundaries of the adjustable opening of each irrigation valve; the minimum transition time between adjacent irrigation points specifies the shortest time required for the irrigation equipment to complete operations at one irrigation point and arrive at the next irrigation point and be ready, taking into account the equipment's startup, movement, and braking processes. Secondly, with the objectives of minimizing total operating time, minimizing energy consumption, and maximizing irrigation uniformity, a multi-objective optimization model can be constructed using the following methods. The implementation method is as follows: For the aforementioned mobile service nodes, a multi-objective optimization model is established. This model uses minimizing the total operation time, minimizing the total system energy consumption (mainly composed of water pump operation and mobile device driving energy consumption), and maximizing irrigation uniformity (measuring the degree of match between the actual irrigation amount and the demand in each grid area) as three optimization objectives. These three objectives are interdependent; for example, shortening the operation time may reduce uniformity or increase energy consumption. Then, the confidence decision values ​​are used as irrigation demand constraints in the multi-objective optimization model, which can be achieved by: considering the future decisions of each grid area... The confidence decision value of irrigation volume within a cycle (usually the expected value) is taken as the net irrigation water demand that the region must meet in a single irrigation operation. In the multi-objective optimization model, a constraint is established for each grid sub-region, requiring that the actual irrigation water volume provided by the planned irrigation scheme (determined by irrigation time, valve opening, and pressure) for that region must be greater than or equal to the corresponding irrigation demand for that region. This ensures that the optimized scheme can meet the basic water requirements of crops. These constraints are collectively referred to as irrigation demand constraints. Finally, the multi-objective optimization model is used to analyze the feasible path sequence of irrigation equipment and the valve opening sequence. The irrigation instruction set, including irrigation order, travel speed, and valve control parameters, can be obtained through iterative optimization by using a non-dominated sorting genetic algorithm with an elitist strategy as the solver. The solution process first randomly generates a set of initial candidate schemes. Each scheme contains a feasible path sequence (e.g., the order in which all grid sub-regions that need irrigation are visited) and a set of valve group opening combinations corresponding to each irrigation point. The total operation time, total energy consumption, and irrigation uniformity of each candidate scheme are evaluated, and it is checked whether all hydraulic constraints and irrigation demand constraints are met.New candidate solutions are iteratively generated through operations such as selection, crossover, and mutation. These solutions are then sorted and filtered according to the Pareto optimality principle of multi-objective optimization. After a set number of iterations, the algorithm converges, yielding a Pareto optimal solution set that achieves the best balance among multiple objectives. The operator selects a final solution from this set based on practical preferences (e.g., prioritizing uniformity) and decodes this solution into a specific set of irrigation instructions, including the order in which irrigation equipment visits each irrigation point, the speed of movement along each segment of the path, and precise control parameters (e.g., opening percentage) for each valve at each irrigation point.

[0041] In another aspect, in some embodiments, this application provides an intelligent control system for irrigation of forage crops, as described above. Figure 3 The figure is a schematic diagram of the structure of an intelligent control system for forage planting irrigation according to some embodiments of this application. The intelligent control system for forage planting irrigation includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below: The acquisition module 201 in this application is mainly used to acquire multi-source monitoring data of the target forage planting area. The multi-source monitoring data includes canopy spectral data and root zone soil moisture profile data. Processing module 202, in this application, is used to extract the water stress index of the target forage from the canopy spectral data, construct a regional soil moisture distribution map based on the water stress index and the humidity distribution characteristics in the humidity profile data, and then determine the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map. It should be noted that the processing module 202 is also used to make multi-period confidence decisions on the irrigation amount of each grid area within the future irrigation window period by using each effective utilization coefficient and the water requirement threshold of each growth stage of the target forage, so as to obtain the confidence decision value of the irrigation amount of each grid area within the future irrigation window period. The execution module 203 in this application is mainly used to perform multi-objective collaborative optimization of the irrigation travel path and valve group opening of the irrigation equipment based on various confidence decision values ​​and hydraulic constraints of the irrigation equipment, generate an irrigation instruction set including irrigation sequence, travel speed and valve port control parameters, and drive the irrigation equipment to perform variable irrigation operations.

[0042] The foregoing has detailed examples of the intelligent control method and system for forage planting irrigation provided in the embodiments of this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specified application, but such implementation should not be considered beyond the scope of this application.

[0043] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described intelligent control method for forage planting irrigation.

[0044] In some embodiments, reference Figure 4 The dashed lines in the figure indicate that the unit or module is optional. This figure is a structural schematic diagram of a computer device for implementing an intelligent control method for forage planting irrigation according to an embodiment of this application. The intelligent control method for forage planting irrigation described in the above embodiments can... Figure 4 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device may be a terminal device, a server or a chip.

[0045] Processor 301 can be a general-purpose processor or a special-purpose processor. For example, processor 301 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 305 for inputting (receiving) and outputting (transmitting) signals.

[0046] For example, the computer device may be a chip, and the communication unit 305 may be the input and / or output circuit of the chip, or the communication unit 305 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0047] For example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0048] The computer device may include one or more memories 302 storing a program 304. The program 304 can be executed by a processor 301 to generate instructions 303, causing the processor 301 to execute the method described in the above method embodiments according to the instructions 303. Optionally, the memory 302 may also store data (such as a target audit model). Optionally, the processor 301 may also read data stored in the memory 302, which may be stored at the same storage address as the program 304, or the data may be stored at a different storage address than the program 304.

[0049] The processor 301 and memory 302 can be configured separately or integrated together, for example, integrated on the system on chip (SOC) of the terminal device.

[0050] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0051] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described intelligent control method for forage planting and irrigation.

[0053] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0054] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for intelligent regulation and control of irrigation for forage planting, characterized in that, Includes the following steps: Acquire multi-source monitoring data of the target forage planting area, including canopy spectral data and root zone soil moisture profile data; The water stress index of the target forage is extracted from the canopy spectral data. A regional soil moisture distribution map is constructed based on the water stress index and the humidity distribution characteristics in the humidity profile data. Then, the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map is determined. By using various effective utilization coefficients and water requirement thresholds for each growth stage of the target forage, a multi-period confidence decision is made on the irrigation amount of each grid area within the future irrigation window, resulting in the confidence decision value of the irrigation amount of each grid area within the future irrigation window. Based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment, the irrigation travel path and valve group opening of the irrigation equipment are optimized in a multi-objective collaborative manner, generating an irrigation instruction set including irrigation sequence, travel speed and valve control parameters, which drives the irrigation equipment to perform variable irrigation operations.

2. The method as described in claim 1, characterized in that, Extracting the water stress index of the target forage from the canopy spectral data specifically includes: The canopy spectral data are preprocessed, including atmospheric correction, radiometric calibration, and noise filtering. Determine the reflectance ratio of the near-infrared band to the red-edge band in the preprocessed canopy spectral data; Auxiliary characteristics of the target forage grass were determined by vegetation indices and red-edge vegetation indices in the preprocessed canopy spectral data. The water stress index of the target forage is determined based on the reflectance ratio and the auxiliary features.

3. The method as described in claim 1, characterized in that, Constructing a regional soil moisture distribution map based on the moisture stress index and the humidity distribution characteristics in the humidity profile data specifically includes: The humidity profile data is divided vertically into multiple humidity features, including surface humidity, root distribution layer humidity, and deep humidity. Rasterized spatial interpolation is performed on each layer of humidity features of the moisture stress index and the multi-layer humidity features to obtain the regional distribution layer of soil moisture index for each region. By overlaying and merging the various regional distribution layers, a regional soil moisture distribution map is obtained.

4. The method as described in claim 1, characterized in that, The effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map is specifically determined by: The soil moisture distribution map of the region is divided into multiple grid regions with homogeneous moisture conditions; For each grid area of ​​the regional soil moisture distribution map, determine the humidity deviation between the average humidity of the root distribution layer in the grid area and the target humidity threshold. Determine the risk factor for evaporation loss of surface humidity in the grid area; The effective utilization coefficient of irrigation water in the sub-region is determined based on the humidity deviation and the evaporation loss risk coefficient, thereby obtaining the effective utilization coefficient of irrigation water in each grid sub-region of the regional soil moisture distribution map.

5. The method as described in claim 1, characterized in that, By using various effective utilization coefficients and water requirement thresholds for each growth stage of the target forage, a multi-period confidence decision is made on the irrigation amount for each grid area within the future irrigation window. The specific confidence decision values ​​for the irrigation amount in each grid area within the future irrigation window include: For each grid area, obtain meteorological forecast data for the future irrigation window period to predict the reference crop evapotranspiration and effective rainfall for the grid area; Based on the reference crop evapotranspiration, the effective rainfall, the crop coefficient of the target forage at the current growth stage, and the water requirement threshold, the theoretical net water requirement of the grid area is calculated. The theoretical net water demand is corrected based on the effective utilization coefficient of the grid area to obtain the confidence decision value of irrigation amount in the grid area within multiple future decision periods, and then the confidence decision value of irrigation amount in each grid area within the future irrigation window period is obtained.

6. The method as described in claim 1, characterized in that, Based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment, a multi-objective collaborative optimization of the irrigation travel path and valve group opening of the irrigation equipment is performed to generate an irrigation instruction set including irrigation sequence, travel speed, and valve control parameters. Specifically, this includes: The irrigation equipment is modeled as a mobile service node, and the hydraulic constraints include pipeline pressure limits, minimum / maximum valve opening, and minimum transition time between adjacent irrigation points. A multi-objective optimization model is constructed with the objectives of minimizing total operation time, energy consumption, and irrigation uniformity. Each confidence decision value is used as a constraint on irrigation demand in the multi-objective optimization model; A multi-objective optimization model is used to iteratively optimize the feasible path sequence and valve group opening combination of irrigation equipment to obtain an irrigation instruction set including irrigation sequence, travel speed and valve control parameters.

7. The method as described in claim 1, characterized in that, The irrigation equipment is a variable-rate irrigation machine based on autonomous combined navigation.

8. A smart control system for irrigation of forage crops, characterized in that, include: The acquisition module is used to acquire multi-source monitoring data of the target forage planting area, including canopy spectral data and root zone soil moisture profile data. The processing module is used to extract the water stress index of the target forage from the canopy spectral data, construct a regional soil moisture distribution map based on the water stress index and the humidity distribution characteristics in the humidity profile data, and then determine the effective utilization coefficient of irrigation water in each grid area of ​​the regional soil moisture distribution map. The processing module is also used to make multi-period confidence decisions on the irrigation amount of each grid area within the future irrigation window period based on each effective utilization coefficient and the water requirement threshold of each growth stage of the target forage, so as to obtain the confidence decision value of the irrigation amount of each grid area within the future irrigation window period. The execution module is used to perform multi-objective collaborative optimization of the irrigation travel path and valve group opening of the irrigation equipment based on various confidence decision values ​​and the hydraulic constraints of the irrigation equipment. It generates an irrigation instruction set including irrigation sequence, travel speed and valve control parameters, and drives the irrigation equipment to perform variable irrigation operations.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs the intelligent control method for forage planting irrigation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement the intelligent control method for forage planting and irrigation as described in any one of claims 1 to 7.

Images