An intelligent irrigation control method and system for high-standard farmland

Abstract

The present invention provides an intelligent irrigation control method and system for high-standard farmland. The method obtains crop canopy image data and farmland terrain elevation data of different crop planting areas in the high-standard farmland; determines the crop growth stage based on the morphological feature data in the crop canopy image data, and constructs a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage; generates soil moisture migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters, and generates pipe network pressure control instructions in combination with the soil moisture migration parameters and a preset irrigation strategy. According to the pipe network pressure control instructions, the outlet pressure distribution of the intelligent irrigation pipe network is adjusted to generate irrigation control instructions. The present invention realizes precise spatiotemporal matching of irrigation in multiple crop rotation areas, improves water utilization efficiency, and solves the problems of irrigation uniformity due to terrain differences and rotation boundaries.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural intelligent irrigation, and in particular to an intelligent irrigation control method and system for high-standard farmland. Background Art

[0002] In the multi-crop rotation planting model of high-standard farmland, the growth cycles and water requirements of different crops vary significantly, and irrigation strategies need to be dynamically adjusted according to their water absorption patterns and root active layer depths during different growth periods. For example, shallow-rooted crops rely on surface soil moisture during the seedling stage, while deep-rooted crops require continuous water supply from deep soil during maturity. At the same time, the undulating topography of farmland leads to uneven surface water infiltration paths and distribution. Especially at the junction of rotation areas, the difference in root active layer depths of adjacent crops and the slope changes in the terrain transition zone may cause ineffective infiltration of irrigation water or local waterlogging. In addition, in the rotation model, it is necessary to quickly respond to changes in water demand after crop replacement, especially when switching between adjacent crops. Refined irrigation control is needed to reduce water competition and resource conflicts in boundary areas.

[0003] Some current smart irrigation solutions deploy networks of soil moisture sensors and meteorological monitoring equipment, combined with pre-set crop water demand models, to achieve automated irrigation control based on soil surface moisture thresholds. However, these solutions fail to fully account for the dynamic changes in root distribution depth and water absorption characteristics of different crops within crop rotation zones. This is particularly true during crop rotation transitions, making it difficult to accurately match the root water absorption needs of newly planted crops. Furthermore, simply adjusting irrigation duration based on terrain elevation results in uneven deep soil moisture distribution in areas with undulating terrain. This can lead to ineffective irrigation water infiltration or localized waterlogging, particularly at rotation zone boundaries, resulting in low irrigation efficiency and crop yields. Summary of the Invention

[0004] The present invention provides an intelligent irrigation control method and system for high-standard farmland, which is used to solve the problems in the existing technology that it cannot accurately match the root water absorption needs of newly planted crops; it is easy to cause ineffective infiltration of irrigation water or local water accumulation at the boundaries of rotation areas, resulting in low irrigation efficiency and crop yield.

[0005] In a first aspect, the present invention provides an intelligent irrigation control method for high-standard farmland, comprising:

[0006] Obtain crop canopy image data and farmland terrain elevation data for different crop planting areas in high-standard farmland;

[0007] Determining the crop growth stage based on the morphological feature data in the crop canopy image data, and constructing a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage;

[0008] Based on the farmland terrain elevation data and soil porosity parameters, soil water migration parameters are generated using the soil hydrodynamics simulation model;

[0009] generating a pipe network pressure control instruction based on the soil moisture migration parameters and a preset irrigation strategy;

[0010] According to the pipe network pressure control instruction, the outlet pressure distribution of the intelligent irrigation pipe network is adjusted to obtain the adjusted outlet pressure distribution, and according to the adjusted outlet pressure distribution, the irrigation control instruction at the boundary of the crop rotation area is generated.

[0011] Optionally, determining the crop growth stage based on the morphological feature data in the crop canopy image data, and constructing a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage, including:

[0012] extracting a color distribution matrix, a texture density parameter, and a structural profile parameter of the crop canopy from each image frame of the crop canopy image data to generate morphological feature data of the crop canopy;

[0013] According to the expansion rate of the structural profile parameters in the morphological feature data and the dominant wavelength offset of the color distribution matrix, a preset crop growth stage mapping relationship is matched to determine the crop growth stage;

[0014] Selecting a root distribution depth interval and a theoretical water absorption rate coefficient per unit root length corresponding to the crop growth stage from a pre-stored crop root parameter database;

[0015] Dividing the farmland terrain elevation data into a plurality of grid cells, and binding the root distribution depth intervals and elevation values to corresponding grid cells to generate a geographic feature association table;

[0016] According to the geographical feature association table and the preset slope water absorption rate correction coefficient, the theoretical water absorption rate coefficient is adjusted to generate an actual water absorption rate coefficient;

[0017] According to the actual water absorption rate coefficient, a soil hydrodynamics simulation model is constructed in a three-dimensional space coordinate system.

[0018] Optionally, adjusting the theoretical water absorption rate coefficient according to the geographical feature association table and a preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient includes:

[0019] Extracting the slope angle corresponding to each grid cell from the geographic feature association table;

[0020] According to the preset slope water absorption rate correction coefficient, define the correction coefficient corresponding to different slope angles;

[0021] generating a first adjusted water absorption rate parameter based on the correction coefficient and the theoretical water absorption rate coefficient;

[0022] If the parameter difference between adjacent soil layers in the same grid unit exceeds a preset layer difference threshold, the water absorption rate parameter adjusted for the first time is redistributed according to the root distribution depth interval to obtain the water absorption rate parameter adjusted for the second time;

[0023] If the slope angle difference between adjacent grid cells exceeds a preset angle mutation threshold, the water absorption rate parameter after the second adjustment is recalculated according to the average value of the correction coefficients of the adjacent grid cells to obtain the actual water absorption rate coefficient corresponding to each grid cell.

[0024] Optionally, based on the farmland terrain elevation data and soil porosity parameters, soil water migration parameters are generated using the soil hydrodynamics simulation model, including:

[0025] Defining the pore connectivity parameters of each soil layer in the high-standard farmland according to the soil porosity parameter;

[0026] Calculating the elevation difference between each grid cell and its adjacent grid cells to obtain an elevation difference set, and taking the direction of the maximum elevation difference in the elevation difference set as the initial slope direction;

[0027] Calculating an angle difference between the initial slope direction and the actual slope direction of adjacent grid cells; if the angle difference exceeds a preset threshold, adjusting the initial slope direction to the arithmetic mean of the actual slope directions to generate a slope parameter set;

[0028] Based on the slope parameter set, a slope direction weight coefficient is assigned to each soil layer, and the slope direction weight coefficient is superimposed with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell;

[0029] Calculate the seepage resistance coefficient corresponding to each soil layer in each grid cell based on the inverse relationship between the pore connectivity parameter and the preset resistance base value;

[0030] The water flow direction priority parameter and the penetration resistance coefficient are input into the soil hydrodynamics simulation model to calculate the water migration amount and migration direction data between adjacent grid cells, and the soil water migration parameters are generated by combining the water migration amount and migration direction data.

[0031] Optionally, based on the slope parameter set, a slope direction weight coefficient is assigned to each soil layer, and the slope direction weight coefficient is superimposed with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell, including:

[0032] Extracting the final slope direction of each grid cell from the slope parameter set, and calculating a slope direction weight coefficient according to an angle between the final slope direction and the true north direction of the geographic coordinate system;

[0033] Assigning a pore connectivity weight coefficient to each soil layer according to the pore connectivity parameter;

[0034] The slope direction weight coefficient is superimposed with the pore connectivity weight coefficient of the corresponding soil layer to generate an initial water flow direction priority parameter;

[0035] The initial water flow direction priority parameters corresponding to each soil layer in the same grid cell are vertically weighted and fused to generate the water flow direction priority parameters to be verified;

[0036] The water flow direction priority parameter to be verified of the target grid cell is corrected so that the priority parameter difference between the target grid cell and the adjacent grid cells does not exceed a preset smoothing threshold, and finally the water flow direction priority parameter corresponding to each grid cell is generated.

[0037] In a second aspect, the present invention provides an intelligent irrigation control system for high-standard farmland, comprising:

[0038] An acquisition module is used to obtain crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland;

[0039] A construction module is used to determine the crop growth stage based on the morphological feature data in the crop canopy image data, and to construct a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage;

[0040] A first generating module is configured to generate soil water migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters;

[0041] A second generating module is configured to generate a pipe network pressure control instruction based on the soil moisture migration parameter and a preset irrigation strategy;

[0042] The adjustment module is used to adjust the outlet pressure distribution of the intelligent irrigation network according to the pipe network pressure control instruction, obtain the adjusted outlet pressure distribution, and generate irrigation control instructions at the boundary of the crop rotation area according to the adjusted outlet pressure distribution.

[0043] In a third aspect, the present invention provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute an intelligent irrigation control method for high-standard farmland as described in any one of the first aspects.

[0044] In a fourth aspect, the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement an intelligent irrigation control method for high-standard farmland as described in any one of the first aspects.

[0045] In the present invention, crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland are obtained; based on the morphological feature data in the crop canopy image data, the crop growth stage is determined, and according to the root distribution depth range and theoretical water absorption rate coefficient corresponding to the crop growth stage, a soil hydrodynamics simulation model is constructed; based on the farmland terrain elevation data and soil porosity parameters, soil moisture migration parameters are generated using the soil hydrodynamics simulation model; based on the soil moisture migration parameters and preset irrigation strategies, pipe network pressure control instructions are generated; according to the pipe network pressure control instructions, the outlet pressure distribution of the intelligent irrigation pipe network is adjusted to obtain the adjusted outlet pressure distribution, and according to the adjusted outlet pressure distribution, irrigation control instructions at the boundary of the crop rotation area are generated. The technical solution provided by the present invention breaks through the limitations of traditional single data sources, realizes multi-dimensional data fusion of crop physiological characteristics and terrain spatial characteristics, and solves the problem of one-sided irrigation strategies caused by data fragmentation in existing technologies; through the dynamic correlation between canopy morphological characteristics and root parameters, a simulation model adapted to the crop growth stage is constructed, overcoming the accuracy defects of traditional models relying on static root parameters; coupling the synergistic effect of terrain slope and soil pore structure, dynamic simulation of water migration paths is realized, breaking through the path prediction distortion problem caused by the separation of terrain and soil parameters in existing methods; based on the deviation analysis of water migration status and irrigation targets, reverse pipe network pressure control instructions are generated to solve the industry problem that traditional open-loop control cannot dynamically suppress water loss; through dynamic adaptation of boundary pressure differences and crop characteristic differences, water competition in multiple crop planting areas is suppressed, breaking through boundary irrigation conflicts caused by fixed threshold control. Furthermore, the crop canopy morphological characteristics and root growth stage parameters are integrated to solve the defect of traditional models relying on single-dimensional data; geographic grid modeling and slope correction strategies are used to significantly improve the simulation accuracy of water movement in complex terrain farmland; the water absorption rate coefficient is dynamically adjusted to adapt to the differences in root characteristics of different crops, thereby suppressing water competition and leakage risks in rotation areas.

[0046] These and other aspects of the present invention will become more readily apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flowchart of an intelligent irrigation control method for high-standard farmland provided by an embodiment of the present invention;

[0049] Figure 2 A schematic structural diagram of an intelligent irrigation control system for high-standard farmland provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0052] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] Figure 1 The present invention provides a flowchart of an intelligent irrigation control method for high-standard farmland. Figure 1 As shown, the method includes:

[0055] In high-standard farmland multi-crop rotation planting patterns, existing intelligent irrigation technology is unable to dynamically match the root water absorption characteristics of different crops during their growth period with the precise irrigation needs of terrain conditions. Specifically, although existing solutions achieve automated control through soil moisture sensors and meteorological data, they have the following core flaws: 1. They do not fully consider the dynamic changes in the root distribution depth and water absorption characteristics of the rotating crops, especially during the rotation switching phase, and are unable to accurately match the deep or shallow root water requirements of the new crop. 2. They only correct the irrigation duration based on terrain elevation, and fail to simulate the water migration path by combining soil porosity and the depth of the active root layer. This leads to uneven deep soil moisture distribution in areas with undulating terrain, and is prone to ineffective infiltration or localized water accumulation at the boundaries of the rotation area. 3. They lack real-time identification of crop growth stages and are unable to dynamically adjust irrigation strategies to adapt to the changing water absorption patterns of the same crop at different growth periods (for example, shallow-rooted crops rely on surface water during the seedling stage, while deep-rooted crops require deep water supply during maturity). In response to the above problems, the present invention proposes: by acquiring crop canopy image data, combining morphological characteristics (such as leaf density, height, etc.) to intelligently identify the crop growth stage, and then accurately obtain the root distribution depth and water absorption characteristics (such as water absorption rate, water potential gradient) of the corresponding stage; secondly, based on farmland terrain elevation data and soil porosity parameters, a soil hydrodynamics simulation model is constructed to simulate the migration path of water in the root active layer, and quantify the interaction between terrain slope, soil permeability and irrigation water flow; furthermore, by comparing the deviation between the simulated water migration path and the preset irrigation strategy, the pipe network pressure control instructions are dynamically generated to accurately adjust the outlet pressure distribution of the irrigation pipe network, especially at the boundary of the rotation area, the irrigation water flow rate and duration are optimized through the pressure gradient to avoid water competition or resource waste caused by root depth differences and terrain transitions. Based on this, the present invention provides an intelligent irrigation control method for high-standard farmland, such as Figure 1 ,include:

[0056] Step 101: Acquire crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland;

[0057] In this step, high-standard farmland refers to high-standard farmland constructed through engineering measures such as land leveling, improved water conservancy facilities, and soil improvement, providing efficient irrigation and disaster resistance and mitigation capabilities. Crop planting areas refer to specific areas within high-standard farmland designated for growing different crops (such as wheat and corn rotation areas), requiring irrigation strategies tailored to their growth needs. Crop canopy image data refers to three-dimensional crop canopy structure data acquired using optical sensors or laser scanners, including parameters such as leaf area index, canopy height, and leaf color distribution matrix. Three-dimensional farmland terrain elevation data, obtained through geographic information system mapping systems or drone mapping, reflects surface undulation, slope, and aspect.

[0058] In this embodiment of the present invention, crop canopy image data is first acquired using canopy image acquisition equipment (e.g., a laser scanner equipped with a fisheye lens) deployed on high-quality farmland. This data is then combined with a geographic information system (GIS) mapping system or drone aerial photography to obtain farmland terrain elevation data. The canopy image data must include morphological features such as texture density parameters, color distribution matrix, and height. The terrain elevation data must cover the three-dimensional topographic relief of the planting area. After acquisition, the data is transmitted to a cloud platform via an IoT gateway for storage, ensuring the real-time and complete nature of subsequent analysis.

[0059] Step 102: determining the crop growth stage based on the morphological feature data in the crop canopy image data, and constructing a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage;

[0060] In this step, morphological characteristic data refers to crop growth parameters extracted from crop canopy image data, such as leaf density, color, height, and cover, used to determine growth stage. Crop growth stages refer to the stages of a crop's life cycle (e.g., seedling, heading, and maturity). Root distribution and water absorption requirements vary significantly across these stages. Root distribution depth refers to the vertical distribution of crop roots within the soil, such as shallow-rooted crops (0-30 cm) and deep-rooted crops (30-60 cm). Root water absorption characteristics refer to the root system's water absorption rate, water potential gradient, and response to varying soil moisture conditions. The soil hydrodynamics simulation model is a mathematical model based on the Richards equation and the van Genenten model, used to simulate water movement in the soil.

[0061] In an embodiment of the present invention, morphological feature data (including the color distribution matrix, texture density parameters, and structural profile parameters of the crop canopy) are first extracted from crop canopy image data using an image processing algorithm (such as an improved Otsu threshold segmentation method); the crop growth stage is determined based on the expansion rate of the structural profile parameters in the morphological feature data and the dominant wavelength offset of the color distribution matrix; the root distribution depth range corresponding to the crop growth stage (such as 0-30 cm for shallow-rooted crops and 30-60 cm for deep-rooted crops) and the theoretical water absorption rate coefficient per unit root length are selected from a pre-stored crop root parameter database; the theoretical water absorption rate coefficient is adjusted based on the root distribution depth range, farmland terrain elevation data, and a preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient, and based on this, a soil hydrodynamics simulation model is constructed in a three-dimensional spatial coordinate system to simulate the movement of water in the root active layer.

[0062] Step 103: generating soil water migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters;

[0063] In this step, soil porosity parameters, such as total porosity and effective porosity, reflect soil pore structure and are obtained using soil three-phase meters deployed at farmland monitoring nodes. The crop root layer refers to the organs through which crops absorb water and nutrients. Its distribution depth and activity directly influence the formulation of irrigation strategies. Water migration pathways refer to the paths by which water infiltrates and diffuses through the soil and are influenced by terrain slope, soil porosity parameters, and root distribution. Soil water migration parameters refer to quantitative indicators output by soil hydrodynamic simulation models, such as permeability coefficient, matrix suction, and water saturation.

[0064] In an embodiment of the present invention, farmland terrain elevation data is first divided into multiple grid cells, and the elevation difference between each grid cell and the adjacent grid cells is calculated, and the direction of the largest elevation difference is selected as the initial slope direction; the angle difference between the initial slope direction and the actual slope direction of the adjacent grid cells is calculated. If the angle difference exceeds a preset threshold, the initial slope direction is adjusted to the arithmetic mean of the actual slope directions, and finally a slope parameter set is generated; based on this, a slope direction weight coefficient is assigned to each grid cell, and the pore connectivity parameters of each soil layer are superimposed to generate a water flow direction priority parameter; further, the permeability resistance coefficient of each soil layer is calculated through the inverse relationship between the pore connectivity parameter and the preset resistance base value; finally, the water flow priority parameter and the permeability resistance coefficient are input into the soil hydrodynamics simulation model, and the soil water migration parameter is output.

[0065] Step 104: generating a pipe network pressure control instruction based on the soil moisture migration parameter and the preset irrigation strategy;

[0066] In this step, the preset irrigation strategy refers to an irrigation plan based on historical data or experience, such as a fixed irrigation duration or triggering irrigation based on a soil moisture threshold. The deviation refers to the difference between the simulated water migration path and the preset strategy, which is used to guide irrigation parameter adjustments. The pipe network pressure control command refers to the control signal generated by the algorithm, which is used to adjust the pressure distribution at the outlet of the irrigation pipe network.

[0067] In this embodiment of the present invention, the water migration amount and dominant direction for each grid cell are extracted from the soil water migration parameters. The absolute difference between this value and the preset irrigation strategy target value is calculated to form a migration amount deviation parameter. A directional deviation parameter is then calculated based on the dominant direction angular difference. These two parameters are weighted and fused to generate a comprehensive deviation index. The corresponding pressure adjustment amplitude and direction are then determined based on a preset pressure control mapping table. Based on this, local pressure control instructions are generated. If the angle between the pressure adjustment directions of adjacent cells exceeds a threshold, the adjustment amplitude is redistributed based on the water migration amount to optimize the instructions, ultimately generating a network pressure control instruction.

[0068] Step 105: adjusting the outlet pressure distribution of the intelligent irrigation network according to the pipe network pressure control instruction to obtain an adjusted outlet pressure distribution, and generating an irrigation control instruction at the boundary of the crop rotation zone according to the adjusted outlet pressure distribution;

[0069] In this step, outlet pressure distribution refers to the pressure configuration at each outlet of the intelligent irrigation network, which determines the irrigation flow rate and penetration depth. Crop rotation areas refer to farmland areas where multiple crops are rotated, requiring irrigation to balance the root depths of different crops with the terrain. Irrigation control instructions are specific execution commands containing parameters such as irrigation duration and flow rate, which are issued to field equipment to achieve precise irrigation.

[0070] In an embodiment of the present invention, at the boundary of the crop rotation area, the adjusted outlet pressure distribution of the grid cells of the adjacent crop planting area is extracted, and the pressure difference on both sides of the boundary is calculated; the boundary irrigation correction amount is calculated in combination with the actual water absorption rate coefficient and the soil porosity ratio on both sides; if a directional conflict occurs, the boundary irrigation correction amount is recalculated based on the preset priority weight of the crop growth stage to generate a target boundary irrigation correction amount; finally, an irrigation control instruction is generated based on the target boundary irrigation correction amount to achieve precise regulation and promote healthy crop growth.

[0071] The embodiments of the present invention solve the problems of low irrigation efficiency and uneven water distribution in multi-crop rotation areas caused by differences in root depth and terrain undulations. Specifically, it accurately matches the water absorption characteristics of the root system to reduce deep or shallow water waste; combines terrain elevation and porosity parameters to avoid ineffective infiltration or water accumulation at the rotation boundaries; and dynamically adjusts irrigation parameters through pressure control instructions to improve water utilization efficiency.

[0072] The present invention provides a specific embodiment, step 102, determining the crop growth stage based on the morphological feature data in the crop canopy image data, and constructing a soil hydrodynamic simulation model based on the root distribution depth range and theoretical water absorption rate coefficient corresponding to the crop growth stage, specifically including the following steps:

[0073] Step 201: extracting a color distribution matrix, texture density parameters, and structural profile parameters of the crop canopy from each image frame of the crop canopy image data to generate morphological feature data of the crop canopy;

[0074] In this step, the color distribution matrix refers to the statistical distribution of pixel values for each color channel in the crop canopy image data, including color proportions and spatial distribution characteristics. This matrix is used to quantify the color variations of the crop canopy. The texture density parameter refers to the intensity of texture variations within a local area of the image. It is calculated using the contrast characteristics of the gray-level co-occurrence matrix and reflects the surface roughness of the canopy. The structural contour parameter refers to the boundary shape of the canopy projection area. It is obtained through edge detection and curve fitting and is used to characterize the canopy expansion morphology.

[0075] In an embodiment of the present invention, pixel-level analysis is performed on each frame of crop canopy image data, the color channel value of each pixel point in the crop canopy coverage area is extracted, and the distribution histogram of each color channel in the canopy area is calculated to obtain a color distribution matrix; the contrast characteristics of the local area of the image are statistically analyzed based on the gray-level co-occurrence matrix algorithm, and the intensity of texture changes within the unit area is calculated to obtain texture density parameters; the canopy contour boundary point set is identified through an edge detection algorithm, the contour curve is fitted and its curvature change is calculated to obtain structural contour parameters; the color distribution matrix difference between adjacent frames (calculated by histogram cosine similarity) and the texture density parameter change rate (calculated by the texture value difference between adjacent frames) are weightedly summed to generate morphological feature data reflecting the canopy growth dynamics.

[0076] Step 202: According to the expansion rate of the structural profile parameters in the morphological feature data and the dominant wavelength offset of the color distribution matrix, a preset crop growth stage mapping relationship is matched to determine the crop growth stage;

[0077] In this step, the expansion rate refers to the growth rate of the projected area of the structural profile parameters per unit time, calculated by dividing the difference in the profile areas of adjacent frames by the time interval. The dominant wavelength offset refers to the cumulative change in the wavelength value of the dominant hue in the color distribution matrix. The preset crop growth stage mapping relationship refers to a predefined table or function that stores the correspondence between the morphological characteristics (expansion rate, wavelength offset) of different crop varieties and their growth stages (seedling stage, jointing stage, etc.).

[0078] In an embodiment of the present invention, a time series analysis is performed on morphological feature data. The difference in the maximum inscribed circle diameters of the structural profile parameters of two consecutive image frames is divided by the time interval to obtain the expansion rate of the structural profile parameters (unit: cm / day). A Fourier transform is performed on the color distribution matrix, and the wavelength value corresponding to the peak of the energy spectrum is obtained. The difference in the wavelength values between adjacent frames is calculated as the dominant wavelength offset. The expansion rate and dominant wavelength offset are input into a predefined crop growth stage mapping relationship table. For example, the corn growth stage table includes the seedling stage (expansion rate ≤ 0.5 cm / day, dominant wavelength offset ≤ 10 nm), the jointing stage (0.5 cm / day < expansion rate ≤ 2 cm / day, 10 nm < offset ≤ 30 nm), and the tasseling stage (expansion rate > 2 cm / day, offset > 30 nm). The nearest neighbor matching algorithm is used to match the closest expansion rate interval and wavelength offset threshold to determine the current crop growth stage.

[0079] Step 203: selecting a root distribution depth interval and a theoretical water absorption rate coefficient per unit root length corresponding to the crop growth stage from a pre-stored crop root parameter database;

[0080] In this step, the pre-stored crop root parameter database refers to a structured dataset that stores the vertical root distribution range and water absorption capacity of different crop varieties at various growth stages. The root distribution depth range refers to the range of active root areas divided by vertical soil layers (e.g., 0-30 cm, 30-60 cm). The theoretical water absorption rate coefficient is the amount of water absorbed per unit length of root per unit time, measured under standard experimental conditions (no terrain slope, homogeneous soil). It reflects the theoretical water absorption capacity of the crop and is calibrated through water absorption experiments under controlled laboratory conditions.

[0081] In an embodiment of the present invention, a pre-stored crop root parameter database is accessed according to the crop growth stage, and the corresponding root distribution depth range (e.g., 0-50 cm for corn during the jointing stage and 0-80 cm for the tasseling stage) and the water absorption rate coefficient per unit root length (e.g., the water absorption rate of shallow roots is 0.8 L / (cm·d) and that of deep roots is 0.3 L / (cm·d)) are called.

[0082] Step 204: Divide the farmland terrain elevation data into a plurality of grid cells, and bind the root distribution depth intervals and elevation values to corresponding grid cells to generate a geographic feature association table;

[0083] In this step, the geographic feature association table refers to a structured data table containing geographic coordinates, elevation, slope angle, and corresponding root system parameters.

[0084] In an embodiment of the present invention, the longitude and latitude coordinates of the farmland are divided into regular geographic coordinate grid units at a preset resolution of 10 meters × 10 meters through a geographic information system. The geographic range of each unit is determined by the starting and ending values of the longitude and latitude, and a division data table containing all grid geographic boundary information is generated. According to the root distribution depth range of the crop at different growth stages, such as 20-60 cm during the jointing period of corn, the soil is vertically divided into a shallow active zone, a middle expansion zone, and a deep stable zone, and marked as level identifiers L1, L2, and L3 respectively. The elevation value of each grid center point is obtained by real-time dynamic carrier phase difference technology, and it is bound to the longitude and latitude coordinates of the corresponding grid to form a parameter table containing grid coordinates and elevation values. Finally, the grid division data table, the root distribution level identifier and the elevation parameter table are associated, the unique number of each grid unit is bound to the root level identifier, and the elevation value is mapped to the depth range of each level to generate an association table integrating geographic coordinates, elevation data and root distribution characteristics.

[0085] Step 205: adjusting the theoretical water absorption rate coefficient according to the geographical feature association table and the preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient;

[0086] In this step, the preset slope water absorption rate correction coefficient refers to the proportional parameter used to adjust the root water absorption rate based on the elevation gradient angle. For example, the slope water absorption rate correction coefficient corresponding to the elevation gradient angle α is 1-0.02α. The actual water absorption rate coefficient refers to the value of the theoretical water absorption rate coefficient corrected according to the actual terrain slope of the farmland, reflecting the actual water absorption capacity of the root system under terrain constraints.

[0087] In an embodiment of the present invention, the elevation gradient slope angle of each coordinate point in the geographic feature association table is read, and the theoretical water absorption rate coefficient is gradient-adjusted according to the slope water absorption rate correction coefficient table (which stores the correspondence between the elevation gradient slope angle and the adjustment ratio of the root water absorption rate, such as for every 5° increase in slope, the shallow root water absorption rate decreases by 10%) to generate the actual water absorption rate coefficient.

[0088] Step 206: Constructing a soil hydrodynamics simulation model in a three-dimensional space coordinate system according to the actual water absorption rate coefficient.

[0089] In this embodiment of the present invention, a soil hydrodynamics simulation model is constructed using a three-dimensional spatial coordinate system (with the X, Y, and Z axes corresponding to geographic coordinates and depth, respectively) and actual water absorption rate coefficients as boundary conditions. This model, combined with soil hydrodynamic equations (such as the Richards equation) and van Genuchten model parameters (such as the relationship between soil matrix suction and water content), uses the finite element method to determine the spatiotemporal distribution of water movement and predicts water infiltration paths, saturation changes, and effective absorption within the root zone under different irrigation strategies, providing a scientific basis for pipe network pressure regulation.

[0090] The embodiment of the present invention accurately determines the crop growth stage and matches root system parameters through morphological feature data; realizes three-dimensional coupled simulation of terrain, root system, and water through geographic coordinate mapping and slope angle correction; and dynamically adjusts pipe network pressure according to the deviation of water migration path to suppress water competition in rotation areas.

[0091] The present invention provides a specific embodiment, step 205, adjusting the theoretical water absorption rate coefficient according to the geographical feature association table and the preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient, specifically comprising the following steps:

[0092] Step 211: extracting the slope angle corresponding to each grid cell from the geographic feature association table;

[0093] In this step, the slope angle refers to the surface inclination angle of high-standard farmland, which is calculated by the elevation difference between adjacent grid cells and reflects the degree of influence of terrain on water migration.

[0094] In this embodiment of the present invention, the slope data for each geographic coordinate grid cell stored in the geographic feature association table is parsed to obtain its corresponding slope angle value. The slope angle is calculated by calculating the elevation difference between adjacent grid cells (the current grid cell elevation minus the elevation of the adjacent grid cell to the east or south) and taking the tangent value in the direction of the maximum difference. For example, if the elevation difference to the east of grid cell G1002 is +0.5 meters and to the south is -0.3 meters, the east difference direction is selected, and the slope angle = arctan(0.5 / 10) = 2.86° (assuming a horizontal spacing of 10 meters).

[0095] Step 212: defining correction coefficients corresponding to different slope angles according to a preset slope water absorption rate correction coefficient;

[0096] In this step, the preset slope water absorption rate correction factor refers to a predefined mapping table between slope angle and water absorption rate attenuation ratio. This is used to quantify the inhibitory effect of slope on root water absorption capacity. The correction factor is the attenuation ratio value (0.0-1.0) obtained by looking up the table based on the slope angle of the current grid cell and is used to adjust the theoretical water absorption rate.

[0097] In this embodiment of the present invention, based on the preset slope water absorption rate correction coefficient, the correction coefficient decreases by 2% for every 1-degree increase in slope angle. For example, a slope angle of 5° corresponds to a correction coefficient of 1-5 × 0.02 = 0.9, and a slope angle of 10° corresponds to a correction coefficient of 1-10 × 0.02 = 0.8. The correction coefficient corresponding to the slope angle of the current grid cell is determined by looking up the table.

[0098] Step 213: generating a first adjusted water absorption rate parameter based on the correction coefficient and the theoretical water absorption rate coefficient;

[0099] In this step, the water absorption rate parameter after the first adjustment refers to a preliminary correction value generated by multiplying the theoretical water absorption rate coefficient by the correction coefficient.

[0100] In this embodiment of the present invention, the theoretical water absorption rate coefficient (e.g., 0.12 cm³ / cm·h for the shallow layer) is multiplied by the correction factor for the corresponding grid cell to generate the first adjusted water absorption rate parameter. For example, a slope angle of 8° corresponds to a correction factor of 0.84, and the adjusted shallow absorption rate parameter = 0.12 × 0.84 = 0.1008 cm³ / cm·h.

[0101] Step 214: if the parameter difference between adjacent soil layers within the same grid cell exceeds a preset layer difference threshold, redistributing the first adjusted water absorption rate parameter according to the root distribution depth interval to obtain a second adjusted water absorption rate parameter;

[0102] In this step, the parameter difference refers to the difference in the water absorption rate parameters after the first adjustment between different soil layers within the same grid cell, which is used to trigger vertical optimization. The preset layer difference threshold is the maximum critical value (e.g., 0.02 cm³ / cm·h) allowed for parameter differences between adjacent soil layers. If exceeded, reallocation is required.

[0103] In this embodiment of the present invention, the preset layer difference threshold is 0.02 cm³ / cm·h. If the difference of 0.0158 between the shallow layer parameter of 0.1008 and the middle layer parameter of 0.085 exceeds the preset layer difference threshold, the water absorption rate parameter after the first adjustment is redistributed according to the length ratio of the root distribution depth interval to obtain the second adjusted water absorption rate parameter. For example, if the shallow layer is 0-30 cm (length 30 cm) and the middle layer is 30-60 cm (length 30 cm), with a length ratio of 1:1, the adjusted shallow layer parameter = (0.1008 + 0.085) / 2 = 0.0929 cm³ / cm·h.

[0104] Step 215: If the slope angle difference between adjacent grid cells exceeds a preset angle mutation threshold, recalculate the water absorption rate parameter after the second adjustment based on the average value of the correction coefficients of the adjacent grid cells to obtain the actual water absorption rate coefficient corresponding to each grid cell;

[0105] In this step, slope angle difference refers to the absolute difference in slope angles between adjacent grid cells and is used to identify sudden changes in terrain. The preset angle mutation threshold is the maximum allowed slope angle difference between adjacent grid cells (e.g., 5°). Exceeding this threshold triggers spatial smoothing correction. The average correction coefficient is the arithmetic mean of the correction coefficients between adjacent grid cells and is used to optimize spatial consistency.

[0106] In an embodiment of the present invention, the preset angle mutation threshold is 5°. If the slope angle of grid unit G1002 is 8° and the slope angle of adjacent unit G1003 is 14°, and the difference of 6° exceeds the preset angle mutation threshold, the average correction coefficient of the adjacent grid units is taken (e.g., the correction coefficient of G1003 is 0.72, the correction coefficient of G1002 is 0.84, and the average correction coefficient is 0.78), and the actual water absorption rate coefficient is recalculated = the water absorption rate parameter after the second adjustment × 0.78.

[0107] The embodiment of the present invention uses a slope angle-driven correction coefficient to accurately suppress water loss on slopes, thereby improving water-saving efficiency and terrain adaptability; a vertical verification mechanism ensures that the water absorption rate of different soil layers conforms to the root distribution law; and an angle mutation threshold suppresses parameter jumps, thereby improving the stability of pipe network pressure control.

[0108] The present invention provides a specific embodiment, step 103, based on the farmland terrain elevation data and soil porosity parameters, using the soil hydrodynamics simulation model to generate soil water migration parameters, specifically comprising the following steps:

[0109] Step 301: defining the pore connectivity parameters of each soil layer in the high-standard farmland according to the soil porosity parameter;

[0110] In this step, the soil porosity parameter refers to the ratio of pore volume per unit volume of soil. It is obtained through soil sampling and testing and reflects the soil's water permeability. The pore connectivity parameter characterizes the connectivity of pore channels within the soil layer and is generated based on the porosity correction.

[0111] In an embodiment of the present invention, the soil is vertically divided into a shallow layer (0-30 cm), a middle layer (30-60 cm), and a deep layer (60-100 cm). The pore connectivity parameters of each layer are calculated based on the soil porosity parameter. Specifically, the pore connectivity of the shallow layer = porosity × 0.8 (corrected for the compaction coefficient), the middle layer = porosity × 0.6, and the deep layer = porosity × 0.4. For example, the shallow layer connectivity of a soil porosity parameter of 0.35 is 0.35 × 0.8 = 0.28.

[0112] Step 302: Calculate the elevation difference between each grid cell and its adjacent grid cells to obtain an elevation difference set, and use the direction of the maximum elevation difference in the elevation difference set as the initial slope direction;

[0113] In this step, the maximum elevation difference refers to the maximum absolute value of the elevation difference between the current grid cell and its adjacent grid cells to the east and south. This value is used to determine the initial slope direction. The initial slope direction is the initial flow direction determined based on the direction of the maximum elevation difference.

[0114] In this embodiment of the present invention, for each grid cell, the elevation difference between its easterly neighboring grid cell (the current cell elevation minus the easterly neighboring grid cell elevation) and its southerly neighboring grid cell elevation (the current cell elevation minus the southerly neighboring grid cell elevation) are calculated, generating a set of elevation difference values containing both easterly and southerly differences. The absolute values of the two differences are compared, and the direction with the largest absolute value is selected as the initial slope direction. For example, if the easterly difference is +0.5 meters and the southerly difference is -0.3 meters, the initial slope direction is easterly.

[0115] Step 303: Calculating the angle difference between the initial slope direction and the actual slope direction of the adjacent grid cells. If the angle difference exceeds a preset threshold, adjusting the initial slope direction to the arithmetic mean of the actual slope directions to generate a slope parameter set.

[0116] In this step, the actual slope direction refers to the slope direction of adjacent grid cells after verification and adjustment. The angle difference refers to the angle between two slope directions and is used to verify the rationality of the direction. The preset threshold refers to the set angle difference critical value (e.g., 45°); exceeding this threshold triggers a direction adjustment. The slope parameter set refers to the data set that stores the final slope direction of all grid cells.

[0117] In this embodiment of the present invention, the angle difference between the initial slope direction of the current grid cell (e.g., 30° east by north) and the actual slope directions of the adjacent grid cells to the east and south (e.g., 15° east by south for the east grid cell and 45° south by east for the south grid cell) is calculated. If the angle between the actual slope direction of any adjacent cell and the initial slope direction exceeds a preset threshold, the initial slope direction is adjusted to the arithmetic average of the actual slope directions of the adjacent grid cells. For example, the average slope direction of the 15° slope of the east grid cell and the 45° slope of the south grid cell is 30°. The adjusted slope direction is generated and stored in the slope parameter set.

[0118] Step 304: Based on the slope parameter set, a slope direction weight coefficient is assigned to each soil layer, and the slope direction weight coefficient is superimposed with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell;

[0119] In this step, soil stratification refers to the soil layers divided by vertical depth (shallow, middle, and deep). The slope direction weight coefficient is the weight assigned to the slope angle and used for priority calculation. The water flow direction priority parameter is the water migration tendency value that combines the slope direction weight coefficient and the pore connectivity parameter.

[0120] In this embodiment of the present invention, based on the slope direction of each grid cell in the slope parameter set, a weight coefficient is assigned according to the slope angle (e.g., a slope angle of 10° corresponds to a weight of 0.7, and a slope angle of 5° corresponds to 0.5). This weight coefficient is then added to the pore connectivity parameter of the soil layer (e.g., 0.6 for the shallow layer and 0.4 for the middle layer) in a preset ratio (slope weight 70% + pore weight 30%) to generate a water flow direction priority parameter. For example, a slope weight of 0.7 × 70% + a pore weight of 0.6 × 30% = 0.67.

[0121] Step 305: Calculate the seepage resistance coefficient corresponding to each soil layer in each grid cell according to the inverse relationship between the pore connectivity parameter and the preset resistance base value;

[0122] In this step, the preset base resistance value refers to a baseline resistance value set based on the soil type (e.g., 1.2 for sandy loam and 2.5 for clay). This value is used to calculate the permeability resistance coefficient. The permeability resistance coefficient quantifies the resistance encountered by water as it penetrates the soil layer and is inversely proportional to pore connectivity.

[0123] In this embodiment of the present invention, the permeability resistance coefficient = the preset resistance base value / the pore connectivity parameter. For example, a shallow pore connectivity of 0.28 corresponds to a resistance coefficient of 1.2 / 0.28 ≈ 4.29. This formula indicates that the higher the pore connectivity, the lower the permeability resistance and the smoother the water flow.

[0124] Step 306: Input the water flow direction priority parameter and the penetration resistance coefficient into the soil hydrodynamics simulation model to calculate the water migration amount and migration direction data between adjacent grid cells, and combine the water migration amount and migration direction data to generate soil water migration parameters.

[0125] In this step, the amount of water migration refers to the volume of water transferred between adjacent grid cells per unit time. The migration direction data refers to the dominant direction of water migration (e.g., 30° east by north).

[0126] In an embodiment of the present invention, the water flow direction priority parameter and the infiltration resistance coefficient are input into the soil hydrodynamics simulation model. By solving the Richards equation, the water migration amount (such as calculating the flow rate through a differential equation) and migration direction (such as selecting a dominant direction based on the water flow direction priority parameter, such as 70% to the east and 30% to the south) between adjacent grid cells are calculated. The migration directions and water migration amounts of all grid cells are summarized, and finally the soil water migration parameters are generated to guide irrigation optimization.

[0127] The embodiment of the present invention solves the parameter fragmentation problem of traditional models through gridded terrain-soil parameter coupling (asymmetric superposition of slope direction and pore connectivity); the migration allocation ratio driven by priority parameters improves the path simulation accuracy.

[0128] The present invention provides a specific embodiment, step 305, assigning a slope direction weight coefficient to each soil layer based on the slope parameter set, and superimposing the slope direction weight coefficient with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell, specifically comprising the following steps:

[0129] Step 311: extracting the final slope direction of each grid cell from the slope parameter set, and calculating the slope direction weight coefficient according to the angle between the final slope direction and the true north direction of the geographic coordinate system;

[0130] In this step, the final slope direction refers to the slope direction after adjustment using the angle difference calibration, reflecting the dominant influence of terrain on water flow. The geographic north direction refers to the true north direction defined by the WGS84 geographic coordinate system, which is independent of magnetic north and serves as a unified angle calculation benchmark. The included angle value refers to the clockwise rotation angle between the final slope direction and the geographic north direction, quantifying the geographic orientation of the slope direction. The slope direction weight coefficient is a weighted value generated by the ratio of the included angle value to the maximum slope angle, representing the intensity of the slope's influence on water flow.

[0131] In an embodiment of the present invention, the final slope direction of each grid cell (e.g., 25° east of south) is obtained through a slope parameter set, and the north direction of the geographic coordinate system (the north reference of the WGS84 coordinate system) is taken as the 0° reference, and the angle between the final slope direction and the north direction is measured clockwise (e.g., 25° east of south corresponds to 155°); the slope direction weight coefficient is calculated by dividing the angle value by a preset maximum slope angle (e.g., 90°), and if the calculated result exceeds 1.0, it is truncated to 1.0; for example, when the angle value is 120°, the slope direction weight coefficient = 120 / 90 = 1.33, which is truncated to 1.0.

[0132] Step 312: assigning a pore connectivity weight coefficient to each soil layer according to the pore connectivity parameter;

[0133] In this step, the pore connectivity weight coefficient refers to the weight value generated according to the pore connectivity parameter of the soil stratification and the stratification correction coefficient, which reflects the water infiltration capacity of different soil layers.

[0134] In this embodiment of the present invention, the pore connectivity parameters for the shallow, middle, and deep soil layers (e.g., 0.35 for the shallow layer, 0.25 for the middle layer, and 0.15 for the deep layer) are multiplied by a preset layer correction factor (0.8 for the shallow layer, 0.6 for the middle layer, and 0.4 for the deep layer) to generate a pore connectivity weight coefficient. For example, the pore connectivity weight coefficient for the shallow layer is 0.35 × 0.8 = 0.28, for the middle layer it is 0.25 × 0.6 = 0.15, and for the deep layer it is 0.15 × 0.4 = 0.06.

[0135] Step 313: superimposing the slope direction weight coefficient and the pore connectivity weight coefficient of the corresponding soil layer to generate an initial water flow direction priority parameter;

[0136] In this step, the initial water flow direction priority parameter refers to the preliminary priority parameter generated by superimposing the slope direction weight coefficient and the pore connectivity weight coefficient, and has not yet undergone vertical fusion and smoothing verification.

[0137] In this embodiment of the present invention, the slope direction weight coefficient (70%) and the pore connectivity weight coefficient of the corresponding soil layer (30%) are superimposed according to a preset ratio. For example, if the slope direction weight coefficient is 1.0 and the shallow pore weight is 0.28, the shallow priority parameter = 1.0 × 0.7 + 0.28 × 0.3 = 0.7 + 0.084 = 0.784.

[0138] Step 314: performing vertical weighted fusion on the initial water flow direction priority parameters corresponding to each soil layer within the same grid cell to generate a water flow direction priority parameter to be verified;

[0139] In this step, the water flow direction priority parameter to be verified refers to the intermediate priority parameter that has been vertically weighted fused but not verified with adjacent units.

[0140] In this embodiment of the present invention, the initial water flow priority parameters for each soil layer are weighted and summed according to the vertical layer weight. For example, if the shallow layer weight is 0.784, the middle layer weight is 0.15, and the deep layer weight is 0.06, then the overall priority = 0.784 × 0.6 + 0.15 × 0.3 + 0.06 × 0.1 = 0.470 + 0.045 + 0.006 = 0.521.

[0141] Step 315: Correcting the water flow direction priority parameter to be verified for the target grid cell so that the difference in priority parameter between the target grid cell and adjacent grid cells does not exceed a preset smoothing threshold, and finally generating a water flow direction priority parameter corresponding to each grid cell;

[0142] In this step, the priority parameter difference refers to the absolute difference in the priority parameters between adjacent grid cells and is used to determine whether smoothing correction is required. The preset smoothing threshold refers to the maximum critical value (such as 0.1) allowed for the difference in priority parameters between adjacent grid cells. If exceeded, correction is triggered.

[0143] In this embodiment of the present invention, the priority parameter difference between the target grid cell and its adjacent cells to the east and south is calculated (e.g., if the target grid cell is 0.521 and the east grid cell is 0.48, the priority parameter difference is 0.041). If the priority parameter difference exceeds a preset smoothing threshold (e.g., 0.1), the target grid cell's water flow direction priority parameter to be verified is adjusted to the moving average of the adjacent grid cells' water flow direction priority parameters to be verified (e.g., if the target grid cell is 0.521, it corresponds to (0.521 + 0.48) / 2 = 0.5005). Finally, the smoothed and verified water flow direction priority parameter corresponding to each grid cell is generated.

[0144] The embodiment of the present invention improves the accuracy of water migration paths through the dynamic coupling of slope direction and pore connectivity, achieving terrain-soil coordinated optimization; the shallow dominant weight distribution conforms to the water absorption law of crop roots; the preset smoothing threshold suppresses parameter mutations and reduces the instability of simulation results.

[0145] The present invention provides a specific embodiment, step 104, generating a pipe network pressure control instruction based on the soil moisture migration parameter and the preset irrigation strategy, specifically comprising the following steps:

[0146] Step 401: extracting the water migration amount and dominant migration direction of each grid cell from the soil water migration parameters;

[0147] In this step, water migration refers to the volume of water transferred between adjacent grid cells per unit time (cm³ / day), reflecting the intensity of water migration. The dominant migration direction, defined as the direction of maximum water migration, is determined by analyzing the distribution of water migration between adjacent grid cells (e.g., 30° east by south).

[0148] In an embodiment of the present invention, by analyzing the water migration parameters, the water migration amount (such as an average daily migration amount of 15 cm³) and the dominant migration direction (such as 30° east-southeast) of each grid cell are extracted.

[0149] Step 402: Calculate the absolute difference between the water migration amount and the target migration amount corresponding to the preset irrigation strategy to generate a migration amount deviation parameter;

[0150] In this step, the preset irrigation strategy refers to a set of target irrigation parameters pre-set based on crop water requirements and soil characteristics. The target migration rate refers to the target water migration rate specified in the preset irrigation strategy (e.g., 20 cm³ / day). The migration rate deviation parameter refers to the percentage deviation between the water migration rate and the target migration rate (5 / 20 × 100% = 25%).

[0151] In this embodiment of the present invention, the difference between the water migration amount (15 cm³) and the target migration amount (20 cm³) in the preset irrigation strategy is calculated. The migration amount deviation parameter = |15 - 20| / 20 × 100% = 25%. The target migration amount is calculated based on the crop water requirement and the soil water holding capacity.

[0152] Step 403: Calculating a direction deviation parameter based on the angle difference between the dominant migration direction and the target migration direction in the preset irrigation strategy;

[0153] In this step, the target migration direction refers to the water migration direction specified in the pre-set irrigation strategy (e.g., due east). The angle difference refers to the minimum angle between the dominant migration direction and the target migration direction (30°). The directional deviation parameter, which quantifies the degree of directional deviation, is the ratio of the angle difference to 180° (30 / 180 ≈ 0.167).

[0154] In this embodiment of the present invention, the dominant migration direction is 30° east-southeast, and the preset target migration direction is due east (0°). The angular difference is 30°. The directional deviation parameter is 30° / 180° = 0.167, which reflects the degree to which the water migration direction deviates from the target migration direction.

[0155] Step 404: performing weighted fusion on the migration deviation parameter and the direction deviation parameter to generate a comprehensive deviation index;

[0156] In this step, the comprehensive deviation index refers to the weighted fusion value (0.225) of the migration deviation parameter and the direction deviation parameter, which is used for pressure regulation decision-making.

[0157] In the embodiment of the present invention, the weight of the migration deviation parameter accounts for 70% (0.25×0.7=0.175), and the weight of the direction deviation parameter accounts for 30% (0.167×0.3≈0.05). The calculated comprehensive deviation index is 0.175+0.05=0.225.

[0158] Step 405: Determine the pressure adjustment amplitude and pressure adjustment direction corresponding to the comprehensive deviation index according to a preset pressure control mapping table;

[0159] In this step, the preset pressure control mapping table defines the relationship between the comprehensive deviation index and the pressure adjustment parameter (e.g., 0.2 corresponds to +5kPa). The pressure adjustment amplitude indicates the pressure value to be adjusted at the outlet (e.g., +5kPa). The pressure adjustment direction refers to the spatial direction of the pressure adjustment (opposite to the direction of water migration).

[0160] In an embodiment of the present invention, a preset pressure control mapping table is queried to obtain a comprehensive deviation index of 0.225 corresponding to a pressure adjustment amplitude of +5 kPa, and the pressure adjustment direction is opposite to the dominant migration direction (e.g., a pressure adjustment direction of 30° east-southeast corresponds to a dominant migration direction of 30° west-northeast).

[0161] Step 406: Based on the pressure adjustment amplitude and pressure adjustment direction, a local pressure control instruction corresponding to each network unit is generated. If the pressure adjustment direction angle of adjacent grid units exceeds a preset conflict threshold, the pressure adjustment amplitudes of adjacent grid units are redistributed according to the moisture migration amount to optimize the local pressure control instruction and generate a pipeline network pressure control instruction.

[0162] In this step, the local pressure control instruction refers to the pressure adjustment parameters for a single grid cell (e.g., +5 kPa at 30° northwest). The preset conflict threshold refers to the maximum angle allowed between the pressure adjustment directions of adjacent grid cells (e.g., 15°). If exceeded, the pressure adjustment must be reallocated.

[0163] In this embodiment, the pressure of adjacent grid cells A is adjusted 30° northwest, and the pressure of cell B is adjusted 10° northwest. The angle of 20° is greater than the preset conflict threshold of 15°. The pressure increase is redistributed based on the proportion of water migration (cell A accounts for 60% and cell B accounts for 40%): cell A's pressure adjustment is +5kPa × 60% = +3kPa, and cell B's adjustment is +5kPa × 40% = +2kPa.

[0164] The embodiment of the present invention improves irrigation efficiency by fusing the two-dimensional deviation of water migration amount and dominant migration direction; the pressure adjustment direction is designed inversely with water migration to suppress water loss on slopes; and the preset conflict threshold verification ensures a smooth transition of pipe network pressure and reduces equipment loss.

[0165] The present invention provides a specific embodiment, in step 105: generating irrigation control instructions at the boundary of the crop rotation zone according to the adjusted outlet pressure distribution, specifically comprising the following steps:

[0166] Step 501: extracting adjusted outlet pressure distributions of grid cells corresponding to adjacent crop planting areas at the boundary of the crop rotation area, wherein the adjusted outlet pressure distributions include pressure values of grid cells on both sides of the boundary of the crop rotation area;

[0167] In this step, the pressure value refers to the pressure value (unit: kPa) of the adjusted outlet pressure distribution, which reflects the driving force of the pipeline network on water migration.

[0168] In an embodiment of the present invention, the geographic coordinate grid cells of the crop rotation area boundary are located through a geographic information system (such as grid G2001 for a corn field and grid G2002 for a soybean field), and the pressure values of the grid cells on both sides of the boundary (such as G2001 pressure 120 kPa and G2002 pressure 105 kPa) and the water migration direction (such as water migration east-southeast in corn fields and east-northeast in soybean fields) are extracted from the adjusted outlet pressure distribution to generate the adjusted outlet pressure distribution.

[0169] Step 502: Calculate the pressure difference between the grid cells on both sides of the boundary based on the adjusted outlet pressure distribution, and calculate the boundary irrigation correction value on both sides of the boundary based on the actual water absorption rate coefficient and soil porosity ratio of the crop planting areas on both sides of the boundary. The boundary irrigation correction value includes an irrigation duration correction coefficient and a water flow rate correction coefficient.

[0170] In this step, the pressure difference refers to the absolute difference in pressure values between grid cells on both sides of the boundary (e.g., 15 kPa) and is used to quantify the intensity of irrigation parameter adjustments. The soil porosity ratio refers to the ratio of soil porosity parameters between crop-growing areas on both sides of the boundary (corn field / soybean field = 1.4), reflecting differences in soil permeability. The boundary irrigation correction refers to the adjustment value calculated based on the pressure difference, the actual water absorption rate coefficient, and the soil porosity parameter, including duration and water flow rate correction factors. The irrigation duration correction factor refers to the percentage of irrigation time that needs to be adjusted, calculated based on the ratio of the pressure difference to the actual water absorption rate coefficient. The water flow rate correction factor refers to the percentage of water flow rate that needs to be adjusted, calculated based on the pressure difference and the soil porosity ratio.

[0171] In this embodiment of the present invention, the pressure difference across the boundary (120-105=15 kPa) is calculated. Combined with the ratio of the actual water absorption rate coefficient of the corn field (0.18 cm³ / cm·h) to the soybean field (0.12 cm³ / cm·h) (0.18 / 0.12=1.5), and the soil porosity ratio (0.35 for the corn field / 0.25 for the soybean field=1.4), a boundary irrigation correction is generated. For example, the irrigation duration correction factor = (pressure difference 15 kPa / preset baseline pressure 100 kPa) × the ratio of the actual water absorption rate coefficient (1.5) = 0.15 × 1.5 = 0.225; the water flow rate correction factor = (15 / 100) × the soil porosity ratio (1.4) = 0.15 × 1.4 = 0.21. The output results show that the corn field needs to reduce the duration by 22.5% and the water flow by 21%, while the soybean field needs to increase the corresponding ratios.

[0172] Step 503: If there is a direction conflict between the boundary irrigation correction values on both sides of the boundary, the boundary irrigation correction values on both sides of the boundary are recalculated according to the preset priority weights of the crop growth stages on both sides of the boundary to generate a target boundary irrigation correction value, and an irrigation control instruction at the boundary of the crop rotation area is generated according to the target boundary irrigation correction value, wherein the preset priority weights are set according to the importance level of the critical crop growth period;

[0173] In this step, directional conflicts occur when the boundary irrigation corrections on either side of the boundary are adjusted in opposite directions (e.g., increasing time on one side and decreasing time on the other). Preset priority weights refer to weight ratios set based on critical crop growth periods (e.g., 70% for tasseling and 30% for flowering) and are used to resolve conflicts. The target boundary irrigation correction refers to the final correction value after the preset priority weights are assigned, which directly drives the irrigation equipment. Critical crop growth periods refer to the growth stages when crops are most sensitive to water (e.g., tasseling and flowering), which determine the priority of regulation. Importance levels refer to the critical period levels (e.g., 1 being the highest) set based on the knowledge of agricultural experts and used for weight allocation.

[0174] In an embodiment of the present invention, if the irrigation time of a corn field needs to be reduced and that of a soybean field needs to be increased, the irrigation time is allocated according to the preset priority weights (70% during the tasseling period of corn and 30% during the flowering period of soybean): for example, the target boundary irrigation correction amount for the corn field: target irrigation time correction coefficient = -22.5% × 70% ≈ -15.75%, target water flow rate correction coefficient = -21% × 70% ≈ -14.7%; the target boundary irrigation correction amount for the soybean field: target irrigation time correction coefficient = +22.5% × 30% ≈ +6.75%, target water flow rate correction coefficient = +21% × 30% ≈ +6.3%.

[0175] The embodiment of the present invention dynamically corrects the irrigation amount through pressure difference and crop and soil parameters to reduce water competition in the rotation area; preset priority weights ensure the irrigation priority of staple crops and realize intelligent conflict resolution.

[0176] Figure 2 The present invention provides a schematic structural diagram of an intelligent irrigation control system for high-standard farmland. Figure 2 As shown, the system includes:

[0177] An acquisition module 21 is used to acquire crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland;

[0178] A construction module 22 is configured to determine the crop growth stage based on the morphological feature data in the crop canopy image data, and to construct a soil hydrodynamics simulation model according to the root distribution depth interval and theoretical water absorption rate coefficient corresponding to the crop growth stage;

[0179] A first generating module 23 is configured to generate soil water migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters;

[0180] A second generating module 24 is configured to generate a pipe network pressure control instruction based on the soil moisture migration parameter and a preset irrigation strategy;

[0181] The adjustment module 25 is used to adjust the outlet pressure distribution of the intelligent irrigation network according to the pipe network pressure control instruction, obtain the adjusted outlet pressure distribution, and generate irrigation control instructions at the boundary of the crop rotation area according to the adjusted outlet pressure distribution.

[0182] Figure 2 The intelligent irrigation control system for high-standard farmland can be implemented Figure 1The implementation principles and technical effects of the intelligent irrigation control method for high-standard farmland described in the illustrated embodiment are not further elaborated. The specific manner in which the various modules and units perform operations in the intelligent irrigation control system for high-standard farmland in the above embodiment have been described in detail in the relevant embodiments of the method and will not be elaborated on here.

[0183] In one possible design, Figure 2 The intelligent irrigation control system for high-standard farmland in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0184] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0185] The processing component 32 is used to: obtain crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland; determine the crop growth stage based on the morphological feature data in the crop canopy image data, and construct a soil hydrodynamics simulation model according to the root distribution depth range and theoretical water absorption rate coefficient corresponding to the crop growth stage; generate soil moisture migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters; generate pipe network pressure control instructions based on the soil moisture migration parameters and preset irrigation strategies; adjust the outlet pressure distribution of the intelligent irrigation pipe network according to the pipe network pressure control instructions to obtain the adjusted outlet pressure distribution, and generate irrigation control instructions at the boundary of the crop rotation area according to the adjusted outlet pressure distribution.

[0186] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0187] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0188] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0189] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0190] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0191] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0192] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The embodiment shown is an intelligent irrigation control method for high-standard farmland.

[0193] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0194] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0195] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0196] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent irrigation control method for high-standard farmland, characterized in that: include: Obtain crop canopy image data and farmland terrain elevation data for different crop planting areas in high-standard farmland; Extracting a color distribution matrix, texture density parameters, and structural profile parameters of the crop canopy from each image frame of the crop canopy image data to generate morphological feature data of the crop canopy; matching a preset crop growth stage mapping relationship based on an expansion rate of the structural profile parameters and a dominant wavelength offset of the color distribution matrix in the morphological feature data to determine the crop growth stage; selecting a root distribution depth interval and a theoretical water absorption rate coefficient per unit root length corresponding to the crop growth stage from a pre-stored crop root parameter database; dividing the farmland terrain elevation data into a plurality of grid cells; binding the root distribution depth interval and elevation values to corresponding grid cells to generate a geographic feature association table; adjusting the theoretical water absorption rate coefficient based on the geographic feature association table and a preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient; and constructing a soil water dynamics simulation model in a three-dimensional spatial coordinate system based on the actual water absorption rate coefficient; Based on the farmland terrain elevation data and soil porosity parameters, soil water migration parameters are generated using the soil hydrodynamics simulation model; generating a pipe network pressure control instruction based on the soil moisture migration parameters and a preset irrigation strategy; According to the pipe network pressure control instruction, the outlet pressure distribution of the intelligent irrigation pipe network is adjusted to obtain the adjusted outlet pressure distribution, and according to the adjusted outlet pressure distribution, the irrigation control instruction at the boundary of the crop rotation area is generated.

2. The method according to claim 1, characterized in that According to the geographical feature association table and the preset slope water absorption rate correction coefficient, the theoretical water absorption rate coefficient is adjusted to generate an actual water absorption rate coefficient, including: Extracting the slope angle corresponding to each grid cell from the geographic feature association table; According to the preset slope water absorption rate correction coefficient, define the correction coefficient corresponding to different slope angles; generating a first adjusted water absorption rate parameter based on the correction coefficient and the theoretical water absorption rate coefficient; If the parameter difference between adjacent soil layers in the same grid unit exceeds a preset layer difference threshold, the water absorption rate parameter adjusted for the first time is redistributed according to the root distribution depth interval to obtain the water absorption rate parameter adjusted for the second time; If the slope angle difference between adjacent grid cells exceeds a preset angle mutation threshold, the water absorption rate parameter after the second adjustment is recalculated according to the average value of the correction coefficients of the adjacent grid cells to obtain the actual water absorption rate coefficient corresponding to each grid cell.

3. The method according to claim 1, characterized in that Based on the farmland terrain elevation data and soil porosity parameters, soil water migration parameters are generated using the soil hydrodynamics simulation model, including: Defining the pore connectivity parameters of each soil layer in the high-standard farmland according to the soil porosity parameter; Calculating the elevation difference between each grid cell and its adjacent grid cells to obtain an elevation difference set, and taking the direction of the maximum elevation difference in the elevation difference set as the initial slope direction; Calculating an angle difference between the initial slope direction and the actual slope direction of adjacent grid cells; if the angle difference exceeds a preset threshold, adjusting the initial slope direction to the arithmetic mean of the actual slope directions to generate a slope parameter set; Based on the slope parameter set, a slope direction weight coefficient is assigned to each soil layer, and the slope direction weight coefficient is superimposed with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell; Calculate the seepage resistance coefficient corresponding to each soil layer in each grid cell based on the inverse relationship between the pore connectivity parameter and the preset resistance base value; The water flow direction priority parameter and the penetration resistance coefficient are input into the soil hydrodynamics simulation model to calculate the water migration amount and migration direction data between adjacent grid cells, and the soil water migration parameters are generated by combining the water migration amount and migration direction data.

4. The method according to claim 3, characterized in that Based on the slope parameter set, a slope direction weight coefficient is assigned to each soil layer, and the slope direction weight coefficient is superimposed with the pore connectivity parameter of the corresponding soil layer to generate a water flow direction priority parameter corresponding to each grid cell, including: Extracting the final slope direction of each grid cell from the slope parameter set, and calculating a slope direction weight coefficient according to an angle between the final slope direction and the true north direction of the geographic coordinate system; Assigning a pore connectivity weight coefficient to each soil layer according to the pore connectivity parameter; The slope direction weight coefficient is superimposed with the pore connectivity weight coefficient of the corresponding soil layer to generate an initial water flow direction priority parameter; The initial water flow direction priority parameters corresponding to each soil layer in the same grid cell are vertically weighted and fused to generate the water flow direction priority parameters to be verified; The water flow direction priority parameter to be verified of the target grid cell is corrected so that the priority parameter difference between the target grid cell and the adjacent grid cells does not exceed a preset smoothing threshold, and finally the water flow direction priority parameter corresponding to each grid cell is generated.

5. The method according to claim 1, wherein Based on the soil moisture migration parameters and the preset irrigation strategy, a pipe network pressure control instruction is generated, including: Extracting the water migration amount and dominant migration direction of each grid cell from the soil water migration parameters; Calculating the absolute difference between the water migration amount and the target migration amount corresponding to the preset irrigation strategy to generate a migration amount deviation parameter; Calculating a direction deviation parameter according to an angular difference between the dominant migration direction and a target migration direction in a preset irrigation strategy; Performing weighted fusion on the migration deviation parameter and the direction deviation parameter to generate a comprehensive deviation index; Determining the pressure adjustment amplitude and pressure adjustment direction corresponding to the comprehensive deviation index according to a preset pressure control mapping table; Based on the pressure adjustment amplitude and pressure adjustment direction, a local pressure control instruction corresponding to each network unit is generated. If the pressure adjustment direction angle of adjacent grid units exceeds a preset conflict threshold, the pressure adjustment amplitudes of adjacent grid units are redistributed according to the moisture migration amount to optimize the local pressure control instruction and generate a pipeline network pressure control instruction.

6. The method according to claim 1, characterized in that Generating irrigation control instructions at the boundary of the crop rotation zone according to the adjusted outlet pressure distribution, including: At the boundary of the crop rotation area, extracting the adjusted outlet pressure distribution of the grid cells corresponding to the adjacent crop planting area, the adjusted outlet pressure distribution including the pressure values of the grid cells on both sides of the boundary of the crop rotation area; Calculating the pressure difference between the grid cells on both sides of the boundary based on the adjusted outlet pressure distribution, and calculating the boundary irrigation correction amount on both sides of the boundary in combination with the actual water absorption rate coefficient and soil porosity ratio of the crop planting areas on both sides of the boundary, wherein the boundary irrigation correction amount includes an irrigation duration correction coefficient and a water flow rate correction coefficient; If there is a directional conflict between the boundary irrigation correction amounts on both sides of the boundary, the boundary irrigation correction amounts on both sides of the boundary are recalculated according to the preset priority weights of the crop growth stages on both sides of the boundary to generate a target boundary irrigation correction amount, so as to generate an irrigation control instruction at the boundary of the crop rotation area according to the target boundary irrigation correction amount, and the preset priority weight is set according to the importance level of the critical period of crop growth.

7. An intelligent irrigation control system for high-standard farmland, characterized in that: include: An acquisition module is used to obtain crop canopy image data and farmland terrain elevation data of different crop planting areas in high-standard farmland; a construction module for extracting a color distribution matrix, texture density parameters, and structural profile parameters of a crop canopy from each image frame of the crop canopy image data to generate morphological feature data of the crop canopy; matching a preset crop growth stage mapping relationship based on an expansion rate of the structural profile parameters and a dominant wavelength offset of the color distribution matrix in the morphological feature data to determine the crop growth stage; selecting a root distribution depth interval and a theoretical water absorption rate coefficient per unit root length corresponding to the crop growth stage from a pre-stored crop root parameter database; dividing the farmland terrain elevation data into a plurality of grid cells; binding the root distribution depth interval and elevation values to corresponding grid cells to generate a geographic feature association table; adjusting the theoretical water absorption rate coefficient based on the geographic feature association table and a preset slope water absorption rate correction coefficient to generate an actual water absorption rate coefficient; and constructing a soil water dynamics simulation model in a three-dimensional spatial coordinate system based on the actual water absorption rate coefficient; A first generating module is configured to generate soil water migration parameters using the soil hydrodynamics simulation model based on the farmland terrain elevation data and soil porosity parameters; A second generating module is configured to generate a pipe network pressure control instruction based on the soil moisture migration parameter and a preset irrigation strategy; The adjustment module is used to adjust the outlet pressure distribution of the intelligent irrigation network according to the pipe network pressure control instruction, obtain the adjusted outlet pressure distribution, and generate irrigation control instructions at the boundary of the crop rotation area according to the adjusted outlet pressure distribution.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent irrigation control method for high-standard farmland as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, an intelligent irrigation control method for high-standard farmland as described in any one of claims 1 to 6 is implemented.

Images