Method and device for determining water level of crop area, and storage medium

Abstract

The application relates to the field of agricultural irrigation monitoring, and provides a crop area water level determination method and device and a storage medium. The determination method comprises the following steps: generating a digital elevation model of a crop area, the crop area comprising a plurality of sub-areas; determining the elevation data of each sub-area from the grid data of the digital elevation model based on a pre-defined field boundary vector diagram, so as to obtain the elevation matrix data of each sub-area; performing visual processing on the elevation matrix data of each sub-area to generate an elevation distribution diagram, and marking the pixel points of a preset elevation in the elevation distribution diagram; determining the target installation position of a water level gauge based on the elevation distribution diagram; obtaining the water level data collected by the water level gauge and the elevation data at the target installation position; and determining the water layer coverage area proportion and / or the average water layer height in the crop area based on the digital elevation model, the water level data and the elevation data at the target installation position. The method can provide accurate irrigation decision support for crops.

Description

Technical Field

[0001] This application relates to the field of agricultural irrigation monitoring, specifically to a method, device, and storage medium for determining water levels in crop areas. Background Technology

[0002] Rice is one of my country's most important food crops, playing a crucial role in ensuring food security and national economic development. With the development of agricultural modernization and smart agriculture, precise water resource management during rice cultivation is receiving increasing attention. Traditional paddy field water level monitoring relies mainly on manual observation, which makes continuous and automated monitoring and control difficult. This often leads to low irrigation efficiency, wasting water resources and potentially affecting the normal growth needs of rice at different stages of its development.

[0003] Existing remote online water level monitoring methods typically utilize level sensors combined with data acquisition and IoT transmission technologies, which can meet the needs of real-time monitoring to a certain extent. However, in actual paddy fields, due to the large area of ​​the fields, slight topographical differences, and insufficient flatness, data obtained from only a few fixed-point water level gauges often only reflect local water level conditions and cannot accurately represent the actual water level distribution characteristics of the entire field. When there are elevation fluctuations in different areas of the field, the results of single-point monitoring may deviate significantly from the overall water level, easily leading to improper irrigation control and thus affecting the normal growth and yield formation of rice at different growth stages. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, and storage medium for determining the water level in a crop area.

[0005] To achieve the above objectives, the first aspect of this application provides a method for determining the water level in a crop area, the method comprising:

[0006] Generate a digital elevation model of the crop region, which includes multiple sub-regions;

[0007] Based on predefined field boundary vector maps, the elevation data of each sub-region is determined from the raster data of the digital elevation model to obtain the elevation matrix data of each sub-region;

[0008] The elevation matrix data of each sub-region is visualized to generate an elevation distribution map, and pixels with preset elevations are marked on the elevation distribution map.

[0009] Determine the target installation location of the water level gauge based on the elevation distribution map;

[0010] After the water level gauge is installed at the target installation location, the water level data collected by the water level gauge and the elevation data at the target installation location are obtained.

[0011] The proportion of water-covered area and / or average water height within the crop region are determined based on digital elevation models, water level data, and elevation data at the target installation location.

[0012] In this embodiment, the proportion of water cover area within the crop region is determined according to the following formula:

[0013]

[0014]

[0015]

[0016] Where E_gauge is the target installation elevation of the water level gauge, H_measure is the water level data collected by the water level gauge, and W_water is the absolute elevation of the water surface at the target installation location of the water level gauge. Let i be the elevation of the i-th cell in the raster data of the digital elevation model. Let N_wet be the inferred water layer height of the i-th cell in the raster data of the digital elevation model, and let N_wet be the inferred water layer height in the raster data of the digital elevation model. The number of cells with a height greater than the preset height, N_total is the total number of cells in the raster data of the digital elevation model, and Cover_Ratio is the proportion of water cover area within the crop region.

[0017] In this embodiment, the average water level within the crop area is determined according to the following formula:

[0018]

[0019]

[0020]

[0021]

[0022] Where E_gauge is the target installation elevation of the water level gauge, H_measure is the water level data collected by the water level gauge, and W_water is the absolute elevation of the water surface at the target installation location of the water level gauge. Let i be the elevation of the i-th cell in the raster data of the digital elevation model. Sum_H_effective is the estimated water level of the i-th cell in the raster data of the digital elevation model, Sum_H_effective is the sum of the water level heights of all cells in the raster data of the digital elevation model, W_avg is the average water level height of the field, and N_total is the total number of cells in the raster data of the digital elevation model.

[0023] In this embodiment of the application, the elevation matrix data of each sub-region is visualized to generate an elevation distribution map, and pixels with preset elevations are marked on the elevation distribution map. This includes: obtaining one or more preset elevation quantile values ​​based on the elevation matrix data; and highlighting pixels whose elevation values ​​are within the range of one or more preset elevation quantiles in the generated elevation distribution map using a rendering color different from the background color.

[0024] In this embodiment, determining the target installation location of the water level gauge based on the elevation distribution map includes: marking pixels at a preset elevation on the elevation distribution map, and then obtaining the user-selected preset installation point; selecting an easily identifiable edge of the actual field boundary as a reference edge, and selecting an endpoint on this reference edge as a spatial reference point; determining the rotation angle to rotate the raster image so that the reference edge is horizontal; and determining the relative distance between the preset installation point and the spatial reference point in the horizontal and vertical directions relative to the reference edge based on the spatial resolution of the digital elevation model. The target installation location of the water level gauge is then determined by on-site layout based on the reference edge, the spatial reference point, and the relative distance.

[0025] In this embodiment of the application, generating a digital elevation model of a crop area includes: after the topography of the crop area is stabilized, using a drone equipped with a positioning device to collect orthophotos and multi-view images of the crop area to obtain image data of the crop area; and performing image stitching processing on the image data to obtain a digital elevation model of the crop area.

[0026] In this embodiment of the application, the determination method further includes: outputting the corresponding spatial distribution map or water level spatial inversion result, and making irrigation assessment decisions based on the result.

[0027] In this embodiment of the application, the irrigation assessment decision based on the results includes: comparing the proportion of the water layer coverage area with a first preset threshold and comparing the average water layer height with a second preset threshold; generating a decision instruction to continue irrigation when the proportion of the water layer coverage area is lower than the first preset threshold and / or the average water layer height is lower than the second preset threshold; and generating a decision instruction to stop irrigation when the proportion of the water layer coverage area reaches or exceeds the first preset threshold and the average water layer height reaches or exceeds the second preset threshold.

[0028] A second aspect of this application provides an apparatus for determining the water level of a crop area, comprising: a memory configured to store instructions; a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement any of the aforementioned methods for determining the water level of a crop area.

[0029] A third aspect of this application provides a machine-readable storage medium storing instructions that cause a machine to perform any of the above-described methods for determining the water level in a crop area.

[0030] This application proposes a method for determining water levels in crop areas. Under the premise of fully considering the spatial elevation distribution characteristics within paddy fields, it effectively integrates water level monitoring data from limited points with high-precision topographic information to construct an analytical model that can accurately invert the spatial distribution of water levels throughout the entire field. Based on this model, it provides scientific and precise irrigation decision support for different growth stages of rice, ultimately achieving intelligent paddy field water level management that is water-saving, efficient, and precisely regulated.

[0031] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0032] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0033] Figure 1 The illustration shows a flowchart of a method for determining the water level in a crop area according to an embodiment of this application;

[0034] Figure 2 This schematically illustrates a rendering of the elevation distribution at different quantile points of a field according to an embodiment of this application;

[0035] Figure 3 An example field boundary and its numbering are schematically shown according to an embodiment of this application;

[0036] Figure 4 This schematic diagram illustrates the calculation results of the relative positions of the water level gauge installation points according to an embodiment of this application.

[0037] Figure 5 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0039] Figure 1 The illustration schematically shows a flowchart of a method for determining the water level in a crop area according to an embodiment of this application. Figure 1 As shown in one embodiment of this application, a method for determining the water level in a crop area is provided, comprising the following steps:

[0040] Step 101: Generate a digital elevation model of the crop region, which includes multiple sub-regions;

[0041] Step 102: Based on the predefined field boundary vector map, determine the elevation data of each sub-region from the raster data of the digital elevation model to obtain the elevation matrix data of each sub-region;

[0042] Step 103: Visualize the elevation matrix data of each sub-region to generate an elevation distribution map, and mark the pixels with preset elevations on the elevation distribution map;

[0043] Step 104: Determine the target installation location of the water level gauge based on the elevation distribution map;

[0044] Step 105: After the water level gauge is installed according to the target installation location, acquire the water level data collected by the water level gauge and the elevation data at the target installation location;

[0045] Step 106: Determine the proportion of water layer coverage area and / or average water layer height within the crop area based on the digital elevation model, water level data, and elevation data at the target installation location.

[0046] A crop area refers to the farmland area requiring water level management. After the farmland topography stabilizes, such as after rice sowing and before irrigation, drones equipped with high-precision GPS are used for aerial photography to collect orthophotos and multi-view images of the paddy fields, obtaining high spatial resolution (e.g., 7.5cm) image data. Using image stitching tools, the images collected by the drones are stitched together to generate raster data of a high-precision digital elevation model (DEM) for the entire farm. Elevation, also known as altitude, refers to the vertical distance of a location relative to a recognized reference surface (usually mean sea level). It describes the undulations of ground points and is one of the most fundamental data in topographic surveying. A digital elevation model is a data model that expresses ground elevation information in digital form. In this application, it typically exists in the form of raster data, where the value of each pixel (i.e., raster cell) represents the altitude of the ground at that point. A sub-region refers to a basic unit within the crop area that is independently managed and separated by boundaries such as field ridges; it is usually called a plot of land. Dividing crop areas into sub-regions is to achieve more refined water level management based on individual field plots.

[0047] Field boundary vector map data is a type of geographic information data that uses vector elements such as points, lines, and polygons to accurately describe the boundaries of each field. It can be digitally drawn manually in geographic information system software or automatically extracted using image recognition algorithms. Elevation matrix data refers to the elevation data of individual fields cut out from the digital elevation model of the entire crop area based on the field boundary vector map. This data can be represented as a two-dimensional matrix in a computer, where each element corresponds to a raster cell within the field, and its value is the elevation value of that cell. Tools are used to process the raster data, utilizing predefined field boundary vector maps to cut out the elevation data of individual fields one by one from the overall digital elevation model, obtaining the elevation matrix data for each independent field.

[0048] Visualization processing refers to using computer graphics technology to render elevation matrix data into a color image, i.e., an elevation distribution map. This map typically uses different colors or color bands to represent different elevation ranges, making the micro-topographical undulations within the field clearly visible. Preset elevation pixels refer to the locations corresponding to specific elevation values ​​selected in advance based on the statistical distribution characteristics of field elevations. Preset elevations are specific elevation quantiles. For example, the 90% quantile means that 90% of the area in the field has an elevation below this value; this point represents a relatively high point within the field. The 50% quantile, or median, represents the relatively middle point within the field. The 10% quantile means that 10% of the area in the field has an elevation below this value; this point represents a relatively low point within the field. In the generated elevation distribution map, specific colors can be used to highlight the pixel areas containing these quantiles. Figure 2 As shown, red indicates the 90% quantile, yellow indicates the 50% quantile, and green indicates the 10% quantile.

[0049] After marking the pixels at the preset elevation on the visualization map, users can interactively select one of these representative points as the preset installation point for the water level gauge on the elevation distribution map. The system can select the 50th percentile as the target installation location because the elevation value of this point is at the middle level of the field, and its water level reading best represents the average condition of the entire field.

[0050] After the water level gauge is installed at the target location, the water level data collected by the gauge and the elevation data at the target installation location are acquired. The water level data, denoted as H_measure, is the water depth measured and uploaded in real time by the water level gauge installed at the target location. In one embodiment, the tubular water level gauge typically has a 0-degree mark. When the gauge is inserted into the farmland, the 0-degree mark is aligned with the soil surface. The distance between the 0-degree mark and the probe is fixed. This fixed distance minus the distance from the water surface to the probe gives the water depth. The elevation data at the target installation location is the elevation value of the corresponding raster cell from the elevation matrix data of the field, denoted as E_gauge.

[0051] Based on a digital elevation model, water level data, and elevation data at the target installation location, the proportion of water cover and / or average water height within the crop area is determined. First, a global water level datum is established. The system reads real-time water level data collected by the water level gauge installed at the target location and extracts the ground elevation value at the water level gauge installation point from the field's elevation matrix data. Based on the reasonable physical assumption that "the irrigation water surface can be considered a horizontal plane within the field area," the two values ​​are added to calculate the absolute elevation datum of the entire field's water surface. Next, field water depth inversion is performed. The system traverses each grid cell in the field's digital elevation model, subtracting the current grid cell's own ground elevation from the global water level datum elevation calculated in the previous step, thereby dynamically calculating the theoretical water depth at that cell location. Then, the proportion of water cover is calculated. Based on the needs of rice growth, the system presets a minimum effective water depth threshold (e.g., 1 cm). Subsequently, the system automatically counts the number of grid cells in the water depth distribution map whose predicted water depth values ​​exceed this threshold, and compares this number with the total number of grid cells in the field to calculate the percentage. This percentage visually quantifies the uniformity of irrigation; for example, a percentage of 95% indicates that 95% of the area in the field has reached or exceeded the minimum effective water depth, while 5% of the higher ground has not been adequately irrigated. Optionally, the system also calculates the average water level height of the field. The system integrates and calculates the predicted water depth values ​​of all grid cells in the field. Specifically, it first sums the water depth values ​​of all cells with positive values, while cells with calculated water depth values ​​of zero or negative (i.e., dry land where the ground is above the water surface) are not counted. Then, this total water depth is averaged with the total number of grid cells in the field to obtain the average water level height for the entire field. Ultimately, the system's output indicators of water coverage area percentage and average water level height together constitute a reliable data foundation for precision irrigation decisions.

[0052] This method generates a visualized elevation distribution map based on high-precision topographic data, achieves representative deployment of water level gauges through elevation quantile analysis, and constructs a point-to-area water level inversion capability by integrating single-point water level and topographic data. It also innovatively proposes a dual-indicator evaluation system of "water layer coverage area ratio" and "average water layer height," enabling simultaneous quantitative control of irrigation uniformity and water quantity. While significantly improving irrigation uniformity and water resource utilization, it creates an optimal water environment for crop growth, achieving comprehensive benefits of water conservation and increased yield.

[0053] In one embodiment, the proportion of water cover area within the crop region is determined according to the following formula:

[0054]

[0055]

[0056]

[0057] Where E_gauge is the target installation elevation of the water level gauge, H_measure is the water level data collected by the water level gauge, and W_water is the absolute elevation of the water surface at the target installation location of the water level gauge. Let i be the elevation of the i-th cell in the raster data of the digital elevation model. Let N_wet be the inferred water layer height of the i-th cell in the raster data of the digital elevation model, and let N_wet be the inferred water layer height in the raster data of the digital elevation model. The system calculates the water level using the formula W_water = E_gauge + H_measure. N_total represents the total number of cells in the digital elevation model's raster data, and Cover_Ratio represents the proportion of water coverage within the crop area. E_gauge (the target installation location elevation of the water level gauge) is a fixed value directly extracted from the field's elevation matrix data, representing the absolute elevation of the ground at the water level gauge installation point. Its unit is typically meters (m). H_measure is the water level data collected by the water level gauge. The unit of water level data can be centimeters (cm) or millimeters (mm). In one embodiment, the water depth ranges from 0 to 15 cm, generally not exceeding 20 cm. W_water (the absolute elevation of the water surface at the target installation location of the water level gauge) is the core intermediate variable in the calculation. It transforms the water depth at a point into a spatial reference, representing the absolute elevation of the entire field's water surface at the current water level. Based on the physical principle that "a still water surface is horizontal," this value applies to every location within the field. The system iterates through each raster cell in the digital elevation model (DEM) and calculates using the formula H_celli = W_water - E_celli. E_celli (the elevation of the i-th cell in the DEM raster data) represents the absolute elevation of the ground at the i-th raster cell within the field. It is the basic building block of the DEM, recording detailed micro-topographic information within the field. H_celli (the estimated water depth of the i-th cell in the DEM raster data) is the calculated theoretical water depth at the i-th raster cell within the field. A positive result indicates that the cell is covered by water; a zero or negative result indicates that the ground is above the water level, either not covered or just exposed. Finally, irrigation uniformity is quantified. Based on the globally derived water depth data, the system calculates the final decision index using the formula Cover_Ratio = (N_wet / N_total) × 100%. N_wet (the number of cells in the digital elevation model's raster data where the inferred water layer H_celli is greater than the preset height) counts the total number of units within the field that have achieved effective irrigation. "Preset height" is a minimum effective water depth threshold set according to requirements, such as 1 cm. This threshold is used to determine whether an area has been adequately irrigated. N_total (the total number of cells in the digital elevation model's raster data) represents the total number of spatial units after discretizing the field and is the denominator in the calculated ratio. Cover_Ratio (the percentage of the crop area covered by the water layer) is the final output metric, visually reflecting the uniformity of the current irrigation water layer's spatial coverage within the field as a percentage.For example, Cover_Ratio = 95% means that 95% of the field has reached the effective irrigation water depth, while the remaining 5% (usually high ground) still needs irrigation. In summary, this embodiment, through the above formula, transforms water level data obtained from a single location into a quantitative indicator that can scientifically assess the uniformity of irrigation across the entire field using high-precision topographic information, providing data support for precise irrigation decisions.

[0058] In one embodiment, the average water level within the crop area is determined according to the following formula:

[0059]

[0060]

[0061]

[0062]

[0063] Where E_gauge is the target installation elevation of the water level gauge, H_measure is the water level data collected by the water level gauge, and W_water is the absolute elevation of the water surface at the target installation location of the water level gauge. Let i be the elevation of the i-th cell in the raster data of the digital elevation model. Here, W_water represents the estimated water level height of the i-th cell in the raster data of the digital elevation model (DEM), Sum_H_effective is the sum of the water level heights of all cells in the DEM raster data, W_avg is the average water level height of the field, and N_total is the total number of cells in the DEM raster data. A global water level benchmark is established using the formula W_water = E_gauge + H_measure. E_gauge (the target installation location elevation of the water level gauge) is a fixed value directly extracted from the elevation matrix data of the field, representing the absolute elevation of the ground at the water level gauge installation point. Its unit is usually meters (m). H_measure is the water level data collected by the water level gauge. The unit of water level data can be centimeters (cm) or millimeters (mm). In one embodiment, the water depth ranges from 0 to 15 cm, generally not exceeding 20 cm. W_water (the absolute elevation of the water surface at the target installation location of the water level gauge) is the core intermediate variable calculated, transforming the water depth at a point into a spatial benchmark, representing the absolute elevation of the entire field's water surface at the current water level. The system iterates through every raster cell in the digital elevation model (DEM) and calculates using the formula H_celli = W_water - E_celli. E_celli (the elevation of the i-th cell in the DEM raster data) represents the absolute elevation of the ground at the i-th raster cell within the field. H_celli (the inferred water depth of the i-th cell in the DEM raster data) is the calculated theoretical water depth at the i-th raster cell within the field. Then, the effective water depth is calculated. The system conditionally sums the inferred water depths of all raster cells, i.e., Sum_H_effective = ΣH_celli (when H_celli > 0). Sum_H_effective (the sum of water depths in all cells of the DEM raster data) is another core intermediate result. Its calculation follows a key principle: only cells with positive water depths are summed, while cells with zero or negative water depths (i.e., exposed ground or above the water surface) have a water depth contribution of 0. This processing method ensures that the summation result accurately reflects the total water storage volume of the water-covered area within the field, avoiding the bias caused by including dry land areas in the average calculation. Finally, the average water level height of the field is calculated using the formula W_avg = Sum_H_effective / N_total. N_total (the total number of cells in the raster data of the digital elevation model) represents the total number of spatial units after discretizing the field, which is the total area of ​​the entire field reflected in the raster data. W_avg (average water level height of the field) differs from the single-point water level reading H_measure; W_avg is a comprehensive and statistical indicator that is area-weighted and takes into account topographic relief.It represents the water depth achievable if the total water storage capacity of all areas within a field were evenly distributed across the entire field area. This indicator more accurately reflects the overall water storage status and total irrigation volume of the field, providing a scientific basis for comparison with irrigation planning targets. In summary, this embodiment, through the above formula, transforms single-point water level monitoring data into an average water layer height indicator that comprehensively reflects the overall water volume of the field, effectively overcoming the problem of insufficient representativeness of single-point data caused by uneven field terrain, and providing a crucial basis for total quantity control to achieve precise irrigation on demand.

[0064] In one embodiment, the elevation matrix data of each sub-region is visualized to generate an elevation distribution map, and pixels with preset elevations are marked on the elevation distribution map. This includes: obtaining one or more preset elevation quantile values ​​based on the elevation matrix data; and highlighting pixels whose elevation values ​​fall within the range of one or more preset elevation quantiles in the generated elevation distribution map using a rendering color different from the background color. The elevation matrix data refers to the elevation data of a single field plot obtained in the aforementioned steps and stored in a two-dimensional matrix format. The value of each element in the matrix represents the altitude of a specific raster cell. Elevation quantiles are used to describe specific locations within the dataset. In this application, it refers to the value at a specific percentage position after all raster cell elevation values ​​within the field are sorted from smallest to largest. For example, the 90% quantile indicates that 90% of the elevation values ​​of all raster cells in the field are below this value. The area corresponding to this quantile represents a relatively high area within the field. The 50% quantile indicates that 50% of the elevation values ​​are below this value. The region corresponding to this quantile represents the central trend of field elevation and is a key location reflecting the overall average elevation level of the field. The 10% quantile indicates that 10% of the elevation values ​​are below this value. The region corresponding to this quantile represents the relatively low-lying area within the field. The elevation matrix data is rendered into a color image using computer graphics techniques (e.g., using Python's Matplotlib library, GDAL library, etc.). In this image, gradient color bands are typically used to represent different elevation ranges. For example, as shown... Figure 2 As shown, red indicates the 90% quantile area, yellow indicates the 50% quantile area, and green indicates the 10% quantile area. This visual enhancement makes high, medium, and low quantile points clearly distinguishable on the map. This embodiment combines statistical quantile analysis with data visualization technology to achieve automatic identification and intuitive presentation of key topographic features of the field. This allows users to directly select the most globally representative point (such as the medium point) from the map as the optimal installation location for the water level gauge, ensuring the accuracy and reliability of subsequent monitoring data.

[0065] In one embodiment, determining the target installation location of the water level gauge based on an elevation distribution map includes: selecting a preset installation point of the water level gauge through a human-computer interaction method on an elevation layer that has been visualized and rendered. Subsequently, according to... Figure 3 The field boundary numbering map shown selects a clearly identifiable field ridge or edge as a reference edge. An endpoint on this reference edge is selected as a spatial reference point, marked as point R. Based on the selected reference edge, the system uses Python tools to calculate the required rotation angle, rotating the raster image until the reference edge is horizontal, and using the reference edge as the X-axis. Subsequently, combining the spatial resolution of the digital elevation model, the system calculates the pixel offset between the preset installation point and the spatial reference point, converts it into actual distance, and thus determines the relative distance between the two in the horizontal and vertical directions relative to the reference edge. Figure 4 The calculation results show that the elevation of the installation point is 37.285 meters, the horizontal distance from the spatial reference point R to the installation point is -10.92 meters, and the vertical distance is 1.89 meters. Based on the calculated relative distances, combined with the identified reference edges and points, on-site layout is carried out in the actual field. This embodiment proposes a high-precision on-site deployment method based on relative coordinates, transforming scientific point selection on digital maps into high-precision locations on the ground, ensuring that the theoretically optimal solution can be accurately implemented in practice.

[0066] In one embodiment, generating a digital elevation model (DEM) of a crop area includes: after the crop area's terrain has stabilized, using a drone equipped with a positioning device to collect orthophotos and multi-view images of the crop area to obtain image data; and performing image stitching processing on the image data to obtain a DEM of the crop area. This is performed after the farmland has been leveled and after rice planting, but before the first irrigation. Stable crop area terrain means that there are no crops or the crop seedlings are very low in the field at this stage, which will not obstruct the terrain measurement. At the same time, no agricultural operations that would alter the terrain, such as tilling, are being carried out, thus ensuring that the acquired elevation data stably represents the terrain conditions of the current growing season. The drone can be equipped with a high-precision global positioning system (such as a real-time dynamic differential positioning (RTK) module). Orthophotos are geometrically corrected images that eliminate distortions caused by camera tilt and terrain undulations and have a uniform scale. They are like precise maps, with each point on the image strictly corresponding to its actual position on the ground. Multi-view images refer to multiple overlapping images of the same feature taken by the drone from different positions and angles. By acquiring these images with high overlap rates, sufficient parallax information can be provided for subsequent 3D modeling. The crop area image data refers to the original image set containing location information, acquired through the aforementioned UAV aerial photography, covering the entire target farmland area. Image stitching processing utilizes computer vision techniques (such as the Structure for Motion Recovery (SFM) algorithm). First, feature point matching is performed on the acquired multi-view images to automatically identify corresponding points, then high-precision exterior orientation elements (position and attitude) of each image are calculated, finally generating a dense 3D point cloud. A Digital Elevation Model (DEM) is a data model that uses a numerical array of regular grid points to represent ground elevation. In this application, high spatial resolution (e.g., 7.5 cm) raster data is generated, where the value of each pixel represents the elevation of the ground at that point. This model accurately and comprehensively records the micro-topographic undulations within the field, serving as the core basis for water level spatial inversion and analysis. This embodiment efficiently acquires high-precision topographic data of a large area of ​​farmland through UAV remote sensing and 3D reconstruction technology. Compared with traditional manual measurement, this method has significant advantages in terms of high efficiency, low cost, and comprehensive data, providing reliable spatial data support for building a precise smart agricultural water level management system.

[0067] In one embodiment, the determination method further includes: outputting a corresponding spatial distribution map or water level spatial inversion result, and making irrigation assessment decisions based on the results. The spatial distribution map refers to a graphical product generated based on the calculation process of the water layer coverage area ratio and the average water layer height. Specifically, the system uses color rendering (e.g., using a blue gradient to represent water depth, from light blue to dark blue corresponding to water depth from shallow to deep) to generate a color map that visually displays the spatial differences in water depth within the field. This map allows users to easily identify dry areas (colorless or light-colored) and waterlogged areas (dark-colored) in the field. The water level spatial inversion result includes not only the aforementioned spatial distribution map but also calculated specific quantitative indicator data, such as the percentage value of the water layer coverage area ratio (Cover_Ratio), the centimeter value of the average water layer height (W_avg), and the estimated total water storage of the entire field. Based on the output spatial distribution map and quantitative indicators, the system or user assesses the current irrigation status and generates corresponding management decisions. For example, the system compares the calculated Cover_Ratio (e.g., 85%) with a preset uniformity target threshold (e.g., 95%); simultaneously, it compares W_avg (e.g., 4.2 cm) with a preset target average water depth (e.g., 5 cm). If either Cover_Ratio or W_avg (or both simultaneously) is below its target threshold, the assessment conclusion is "insufficient irrigation," and the system can generate a "continue irrigation" decision instruction or warning message. If both Cover_Ratio and W_avg reach or exceed their target thresholds, the assessment conclusion is "irrigation meets standards," and the system can generate a "stop irrigation" decision instruction. This embodiment, by outputting intuitive visualization results and precise quantitative indicators, and establishing threshold-based decision logic, reduces the technical threshold and decision-making difficulty for users to conduct precise irrigation management, and further realizes a complete closed loop from data perception to intelligent decision-making, ultimately ensuring the scientific, accurate, and efficient nature of irrigation operations.

[0068] In one embodiment, the irrigation assessment decision based on the results includes: comparing the water layer coverage area ratio with a first preset threshold and comparing the average water layer height with a second preset threshold; generating a decision instruction to continue irrigation when the water layer coverage area ratio is lower than the first preset threshold and / or the average water layer height is lower than the second preset threshold; and generating a decision instruction to stop irrigation when the water layer coverage area ratio reaches or exceeds the first preset threshold and the average water layer height reaches or exceeds the second preset threshold. The system determines that the current irrigation has not yet met the target and generates a "continue irrigation" instruction when any one or both of the following conditions are met: Condition 1: Water layer coverage area ratio < first preset threshold. This condition indicates that there is a large area of ​​insufficiently irrigated land (high ground) in the field, and the irrigation uniformity is not met. Condition 2: Average water layer height < second preset threshold. This condition indicates that even if the water layer coverage is acceptable, the overall water volume is insufficient. The system determines that the irrigation target has been achieved and generates a "stop irrigation" instruction when and only when both of the following conditions are met simultaneously: Condition 1: Water layer coverage area ratio ≥ first preset threshold (e.g., ≥95%). Condition 2: Average water level height ≥ second preset threshold (e.g., ≥ 3 cm). This dual constraint ensures that when irrigation stops, the field not only achieves a highly uniform water distribution but also reaches an appropriate total water volume, creating an optimal water environment for crop growth. This embodiment simultaneously considers the uniformity and sufficiency of irrigation, overcoming the inherent limitation of single-point water level monitoring in assessing irrigation uniformity, thereby maximizing irrigation water utilization efficiency while ensuring crop water needs are met.

[0069] Figure 1 This is a flowchart illustrating a method for determining the water level in a crop area in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0070] In one embodiment, after rice sowing and before irrigation, when the field topography is stable, a drone equipped with a high-precision positioning system is used to conduct aerial photography of the target farmland area. The drone flies along a preset route, collecting high-overlap orthophotos and multi-view images covering the entire farmland area. Subsequently, computer software is used to stitch these image data together to generate a high spatial resolution digital elevation model (DEM) for the entire farmland area. A pre-drawn field boundary vector map is loaded into the geographic information system software. Using this vector map, the elevation data of each individual field is cropped from the DEM raster data of the entire farmland area generated in the first step, thus obtaining independent elevation matrix data for each field. By calling data processing and drawing libraries through a programming language, the elevation matrix data of a specific field is visualized to generate an elevation distribution map of that field. The system automatically calculates the elevation quantiles of the field, obtaining the specific elevation values ​​of its 10% (low quantile), 50% (middle quantile), and 90% (high quantile) points. Figure 2As shown, in the elevation distribution map, green highlights the pixel area within the 10% quantile, yellow highlights the pixel area within the 50% quantile, and red highlights the pixel area within the 90% quantile. The system or technicians can decide to install the water level gauge within the most globally representative yellow area (50% quantile, i.e., the median), and select a specific preset installation point within this area. The system then performs high-precision field deployment calculations. Based on the field conditions, the operators select a straight, sturdy main ridge from the field boundary as a reference edge, and a prominent corner of this ridge as a spatial reference point. The system calculates a rotation angle based on the direction of the reference edge in the DEM and rotates the raster image so that the reference edge is horizontal in the rotated coordinate system. Then, combining the spatial resolution of the DEM (7.5 cm / pixel), the system accurately calculates the relative distance between the preset installation point and the spatial reference point: -10.92 meters along the reference edge direction and 1.89 meters perpendicular to the reference edge direction. The operators located the defined reference edges and spatial reference points, and based on the calculated relative distances, conducted on-site layout to determine the target installation location of the water level gauge with centimeter-level precision, and then completed the installation of the water level gauge. During irrigation, the water level gauge began operating, collecting real-time water level data H_measure at its installation point. Simultaneously, the system obtained the elevation data E_gauge of the water level gauge installation point from the field's DEM. The system calculated the water level reference surface: W_water = E_gauge + H_measure = 10.00 + 0.05 = 10.05 meters. The system then traversed every grid cell of the field's DEM, calculating the predicted water layer height for each cell H_celli = 10.05 - E_celli. Based on the inversion results, the system calculates two key decision indicators: the water cover ratio (Cover_Ratio). The system counts the number N_wet of all cells where H_celli is greater than a preset height (1 cm), and then calculates the current irrigation coverage ratio as 88% using the formula Cover_Ratio = (N_wet / N_total) × 100%. The average water layer height (W_avg) is calculated by summing the H_celli values ​​of all cells where H_celli is greater than 0 to obtain Sum_H_effective, and then calculating the current average water layer height as 4.2 cm using the formula W_avg = Sum_H_effective / N_total. The system outputs a water level spatial inversion result including a water depth distribution map, coverage ratio, and average water depth, and makes irrigation assessment decisions based on this result. The system's preset first threshold (coverage ratio threshold) is 95%, and the second preset threshold (average water depth threshold) is 5 cm.The current coverage rate (88%) is less than 95%, and the average water depth (4.2 cm) is less than 5 cm. Therefore, the system automatically generates a "continue irrigation" decision command and sends this command to the alarm interface of the irrigation control system, prompting the administrator that the current irrigation standard has not been met and irrigation needs to continue. This solution effectively solves the problem of uneven irrigation caused by the micro-topography of the field, significantly improving water resource utilization efficiency and the level of intelligent agricultural management while ensuring the crop growth needs.

[0071] In one embodiment, a device for determining the water level in a crop area (not shown in the figure) is provided, comprising:

[0072] The memory is configured to store instructions;

[0073] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement any of the aforementioned methods for determining the water level in the crop region.

[0074] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the method for determining the water level in the crop area is implemented by adjusting the kernel parameters.

[0075] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0076] This application provides a storage medium storing a program that, when executed by a processor, implements the method for determining the water level in the crop area described above.

[0077] This application provides a processor for running a program, wherein the program executes the method for determining the water level in the crop area.

[0078] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a method for determining the water level of a crop area.

[0079] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0080] This application provides a computer (electronic) device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the above methods for determining the water level of a crop area.

[0081] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of a method for initializing the determination of water levels in a crop-grown area.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0087] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0088] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0089] It should also be noted that the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0090] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the water level in a crop area, characterized in that, The determination method includes: Generate a digital elevation model of a crop region, which includes multiple sub-regions; Based on a predefined field boundary vector map, the elevation data of each sub-region is determined from the raster data of the digital elevation model to obtain the elevation matrix data of each sub-region; The elevation matrix data of each sub-region is visualized to generate an elevation distribution map, and pixels with preset elevations are marked on the elevation distribution map. The target installation location of the water level gauge is determined based on the elevation distribution map. After the water level gauge is installed at the target installation location, the water level data collected by the water level gauge and the elevation data at the target installation location are obtained. Based on the digital elevation model, the water level data, and the elevation data at the target installation location, determine the proportion of water layer coverage area and / or the average water layer height within the crop area; The proportion of water cover area within the crop region is determined according to the following formula: Where E_gauge is the target installation elevation of the water level gauge, H_measure is the water level data collected by the water level gauge, and W_water is the absolute elevation of the water surface at the target installation location of the water level gauge. The elevation of the i-th cell in the raster data of the digital elevation model. The inferred water layer height is the i-th cell in the raster data of the digital elevation model. Inferring water layers from the raster data of the digital elevation model. The number of cells with a height greater than the preset height, N_total is the total number of cells in the raster data of the digital elevation model, and Cover_Ratio is the proportion of water coverage area within the crop area; The average water level within the crop area is determined using the following formula: Wherein, Sum_H_effective is the sum of the water layer heights of all cells in the raster data of the digital elevation model, and W_avg is the average water layer height of the field. The determination of the target installation location of the water level gauge based on the elevation distribution map includes: After marking the pixels at the preset elevation on the elevation distribution map, the preset installation point selected by the user is obtained; Select an easily identifiable edge of the actual field from the field boundary as a reference edge, and select an endpoint on the reference edge as a spatial reference point; Determine the rotation angle that makes the reference edge horizontal to rotate the raster image; Based on the spatial resolution of the digital elevation model, the relative distances between the preset installation point and the spatial reference point in the horizontal and vertical directions relative to the reference edge are determined. Based on the reference edge, the spatial reference point, and the relative distance, on-site layout is performed to determine the target installation location of the water level gauge.

2. The determination method according to claim 1, characterized in that, The process of visualizing the elevation matrix data of each sub-region to generate an elevation distribution map, and marking pixels with preset elevations on the elevation distribution map, includes: Based on the elevation matrix data, obtain one or more preset elevation quantile values; In the generated elevation distribution map, pixels whose elevation values ​​fall within the range of one or more preset elevation quantiles are highlighted using a rendering color that is different from the background color.

3. The determination method according to claim 1, characterized in that, The digital elevation model for the generated crop area includes: After the terrain of the crop area is stabilized, a drone equipped with a positioning device is used to collect orthophotos and multi-view images of the crop area to obtain image data of the crop area. The image data is stitched together to obtain a digital elevation model of the crop area.

4. The determination method according to claim 1, characterized in that, The determination method further includes: Output the corresponding spatial distribution map or water level spatial inversion results, and make irrigation assessment decisions based on the results.

5. The determination method according to claim 4, characterized in that, The irrigation assessment and decision-making based on the results includes: The proportion of the water layer coverage area is compared with a first preset threshold, and the average water layer height is compared with a second preset threshold. If the proportion of the water layer coverage area is lower than the first preset threshold, and / or the average water layer height is lower than the second preset threshold, a decision instruction to continue irrigation is generated. When the proportion of the water layer coverage area reaches or exceeds the first preset threshold, and the average water layer height reaches or exceeds the second preset threshold, a decision instruction to stop irrigation is generated.

6. A device for determining the water level in a crop area, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for determining the water level of the crop area according to any one of claims 1 to 5.

7. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method for determining the water level in the crop area according to any one of claims 1 to 5.

Images