An intelligent irrigation system and method for farmland water conservancy projects

Abstract

The application relates to the technical field of intelligent irrigation, in particular to an intelligent irrigation system and method for farmland water conservancy projects, which comprises a DEM modeling module for generating a digital elevation model of farmland; a division module including a terrain division unit, a grid division unit and a regional division unit, which are respectively used for terrain division according to the digital elevation model, division of the farmland into regular grids through a grid method and zoning of the specified farmland according to regional attribute data; a data acquisition module including an attribute data acquisition unit, a meteorological data acquisition unit and a soil data acquisition unit; a crop analysis module for calculating crop water requirements of each farmland region according to crop growth periods and growth states; a data calculation module for calculating expected precipitation and irrigation amounts of each region; and an irrigation strategy generation module for determining highland irrigation points, middle-land irrigation points, low-lying irrigation points and corresponding irrigation amounts. The application improves water resource utilization efficiency by accurately calculating irrigation requirements of each region.

Description

Technical Field

[0001] This invention relates to the field of smart irrigation technology, specifically to a smart irrigation system and method for farmland water conservancy projects. Background Technology

[0002] With the expansion of agricultural production and the increasing scarcity of water resources, traditional farmland irrigation methods are no longer adequate to meet the precise and efficient water demands of modern agriculture. The current state of arable land is complex and varied; even within the same plot, significant differences can exist in soil characteristics, topographic relief, climatic microenvironment, crop growth status, and density across different areas. These differences collectively lead to a high degree of imbalance in irrigation demand, posing a significant challenge to water resource management in farmland irrigation areas.

[0003] Currently, many existing smart irrigation technologies are being applied in farmland management. These technologies typically estimate and determine irrigation amounts using soil moisture sensors, meteorological data, and crop water requirement models. The basic principle of these systems is to combine the ideal water requirement of the crop with the actual soil moisture conditions to calculate when and how much irrigation to provide. Based on this, the collaborative application of technologies such as remote sensing, the Internet of Things (IoT), and big data analytics enables real-time monitoring and control of the water environment in agricultural production, thereby improving irrigation efficiency.

[0004] However, despite the progress made in improving irrigation efficiency, existing technologies still have some significant shortcomings and problems. Most current smart irrigation methods rely on soil moisture and meteorological data to estimate irrigation volume. This estimation method is not comprehensive enough and fails to fully consider the real-time growth status of crops and the dynamic changes in their water requirements. Crops at different growth stages have significantly different water requirements, and existing technologies often cannot adjust irrigation volume in real time to adapt to these varying needs. Secondly, existing technologies do not comprehensively analyze the topography of farmland. Farmland typically has undulating terrain, with water flowing from high to low elevations. This can lead to insufficient water in higher areas and waterlogging in low-lying areas, resulting in an uneven distribution of irrigation volume, which in turn reduces irrigation efficiency and negatively impacts the crop's growing environment.

[0005] Therefore, although existing smart irrigation systems have improved irrigation efficiency to some extent, they still fail to effectively address the complex terrain and soil variations in farmland, the dynamic changes in crop water requirements, and issues such as water evaporation and infiltration, thus failing to achieve truly precise and efficient irrigation. To solve these problems, there is an urgent need for a new type of smart irrigation system capable of real-time monitoring and intelligent adjustment of irrigation volume. This system would enable precise control and dynamic regulation, significantly improving water resource utilization efficiency and ensuring the water needed for crop growth while minimizing waste.

[0006] Therefore, a smart irrigation system and method for farmland water conservancy projects are proposed. Summary of the Invention

[0007] The purpose of this invention is to provide a smart irrigation system and method for farmland water conservancy projects. This system achieves efficient and precise irrigation management through the collaborative work of multiple modules. First, the DEM modeling module generates a digital elevation model of the specified farmland, providing basic data for subsequent farmland division and irrigation strategy formulation. Then, the division module divides the specified farmland into highlands, flat areas, and low-lying areas using terrain division units, further subdividing the farmland into regular grid areas using grid division units, and then partitioning the farmland into K farmland areas using regional division units. The system collects various information, including soil data, crop data, meteorological data, and soil moisture data, through a data acquisition module to ensure comprehensive data support for precise irrigation. Next, the crop analysis module analyzes the growth period and growth status of crops in each area, and then calculates the crop water requirement for each farmland area. Based on this, the data calculation module calculates the expected precipitation based on meteorological forecast data, and combines soil moisture and crop water requirement to calculate the water shortage of crops in the area, thereby determining the irrigation amount for the target area. Finally, the irrigation strategy generation module, based on the digital elevation model and the irrigation volume of the target area, rationally determines the irrigation points and corresponding irrigation volumes for high-altitude, flat, and low-lying areas, thereby achieving precision irrigation. This system can accurately predict farmland irrigation needs, enabling refined and water-saving irrigation management.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A smart irrigation system for farmland water conservancy projects includes:

[0010] The DEM modeling module is used to generate digital elevation models of specified farmland.

[0011] The land division module includes: a terrain division unit, used to divide the designated farmland into highland farmland areas, flat farmland areas, and low-lying farmland areas according to the digital elevation model; and a grid division unit, used to divide the designated farmland into regular grids. A grid area; a region division unit, used to divide the specified farmland into K farmland areas;

[0012] The data acquisition module includes: an attribute data acquisition unit, used to acquire soil and crop data within each grid area, and obtain... Group regional attribute data; meteorological data acquisition unit, used to acquire meteorological forecast data; soil data acquisition unit, used to acquire regional soil moisture of K farmland areas;

[0013] The crop analysis module is used to perform growth period analysis and growth status analysis on crops in K farmland areas to obtain the water requirements of crops in K areas.

[0014] The data calculation module includes: a precipitation calculation unit, used to calculate the expected precipitation within a specified time period based on the meteorological forecast data; and an irrigation demand calculation unit, used to calculate the regional crop water shortage based on the regional crop water demand, the regional soil moisture and the expected precipitation, and to determine the target area irrigation amount based on the regional crop water shortage.

[0015] The irrigation strategy generation module is used to determine highland irrigation points, mid-land irrigation points, low-lying irrigation points, and corresponding irrigation amounts based on the digital elevation model and the K irrigation amounts for the target areas.

[0016] Furthermore, generating the digital elevation model of the designated farmland includes: acquiring elevation data and surface point cloud data of the designated farmland through a drone, and generating the digital elevation model by combining it with ground control point calibration.

[0017] Further, the topographical division of the designated farmland according to the digital elevation model includes: dividing the designated farmland into candidate high areas, candidate flat areas, and candidate low-lying areas based on the slope data of the digital elevation model; simulating the water flow paths of the candidate high areas, the candidate flat areas, and the candidate low-lying areas in conjunction with flow direction analysis to obtain a first simulated water flow path; and verifying whether the first simulated water flow path meets the expected water flow path.

[0018] If the first simulated water flow path satisfies the expected water flow path, then the candidate high area, the candidate flat area, and the candidate low-lying area are respectively designated as the highland farmland area, the flat farmland area, and the low-lying farmland area.

[0019] If the first simulated water flow path does not meet the expected water flow path, the designated farmland is re-divided by adjusting the threshold of the slope data division into adjusted high areas, adjusted flat areas, and adjusted low-lying areas. The water flow paths of the adjusted high areas, the adjusted flat areas, and the adjusted low-lying areas are re-verified by combining flow direction analysis to obtain a second simulated water flow path. This process continues until the second simulated water flow path meets the expected water flow path, resulting in the highland farmland area, the flat farmland area, and the low-lying farmland area.

[0020] Furthermore, the expected water flow path specifically requires that the water flow from the highland farmland area to the flat farmland area, and then from the flat farmland area to the lowland farmland area, and that the expected water flow path remains continuous between the highland farmland area, the flat farmland area, and the lowland farmland area, without any backflow or stagnation.

[0021] Furthermore, the specific methods for dividing the designated farmland into zones include:

[0022] Based on the elevation data of the designated farmland and The specified farmland is divided into zones based on the area attribute data.

[0023] The regional attribute data includes regional soil data and regional crop data; the regional soil data includes soil temperature, soil pH, and soil nutrient content; the regional crop data includes crop type and crop sowing time; the elevation data of the designated farmland is divided into grids according to the grid method. For each grid region, regional elevation data is calculated, where the regional elevation data is the average of all elevation data within the corresponding grid region. The regional attribute data, regional elevation data, and spatial location data of each grid region are integrated to obtain a regional feature vector. The regional feature vector is then standardized to obtain a standard regional feature vector for each grid region. Finally, the standard regional feature vector is clustered using a K-means clustering algorithm to obtain K farmland regions.

[0024] Furthermore, the growth period analysis of the crops in the K farmland areas includes: obtaining the regional crop growth stages of the K farmland areas based on crop type, crop sowing time, local historical climate data, and expert experience.

[0025] Furthermore, the analysis of crop growth status in the K farmland areas includes: acquiring remote sensing images of farmland in each grid area using a drone, and obtaining... Remote sensing images of farmland in grid-like areas; The remote sensing images of farmland in the grid area described above are divided into K groups, resulting in K groups of farmland remote sensing images. Through image analysis methods, the image values ​​of each farmland remote sensing image in each group are calculated, including NDVI value, weed rate, and crop wilt index. The mean of all image values ​​in each group is calculated to obtain the average NDVI value, average weed rate, and average crop wilt index within each group.

[0026] Further, calculating the regional crop water shortage based on the regional crop water requirement, the regional soil moisture, and the expected precipitation, and determining the irrigation amount for the target region based on the regional crop water shortage includes: uniformly converting the units of the regional crop water requirement, the regional soil moisture, and the expected precipitation to obtain the regional crop water requirement in millimeters, the regional soil moisture in millimeters, and the expected precipitation in millimeters; and calculating the regional crop water shortage based on the regional crop water requirement in millimeters, the regional soil moisture in millimeters, and the expected precipitation in millimeters.

[0027] Furthermore, determining the highland irrigation point, the mid-land irrigation point, the low-lying irrigation point, and the corresponding irrigation amount based on the digital elevation model and the K target area irrigation amounts includes: determining the irrigation amount constraints for the farmland area and determining the optimization target;

[0028] Water flow simulation is performed using a genetic algorithm combined with the digital elevation model to solve for the total irrigation amount that satisfies all the irrigation amount constraints and minimizes the total irrigation amount of the specified farmland; the highland irrigation point, the mid-land irrigation point, the low-lying irrigation point, and the corresponding irrigation amount are obtained through multi-generation iterative optimization.

[0029] A smart irrigation method for farmland water conservancy projects includes the following steps:

[0030] Generate a digital elevation model of the specified farmland;

[0031] The designated farmland is divided into regular grids using a grid method. Divide the data into grid regions; collect soil and crop data within each grid region to obtain... Group region attribute data;

[0032] Based on the elevation data of the designated farmland and The specified farmland is divided into K farmland regions by using the regional attribute data of the group;

[0033] The growth period and growth status of crops in the K farmland areas were analyzed to obtain the water requirements of crops in the K areas.

[0034] Obtain meteorological forecast data and calculate the expected precipitation within a specified time period; obtain the regional soil moisture of K farmland areas; determine the regional crop water shortage based on the regional crop water requirement, the regional soil moisture, and the expected precipitation; determine the irrigation amount for the target area based on the regional crop water shortage;

[0035] The designated farmland is divided into highland farmland area, flat farmland area and lowland farmland area according to the digital elevation model; the highland irrigation point, midland irrigation point, lowland irrigation point and corresponding irrigation amount are determined according to the digital elevation model and K irrigation amounts of the target area.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] 1. This invention proposes a terrain division method for a smart irrigation system for farmland water conservancy projects based on a digital elevation model (DEM). By analyzing the slope data from the DEM, the designated farmland is initially divided into candidate high-lying areas, candidate flat areas, and candidate low-lying areas. The water flow path in each area is then simulated using flow direction analysis. This method can verify and adjust the simulated water flow path, ensuring a smooth flow from high-lying areas to flat areas and then to low-lying areas, while avoiding backflow or stagnation. By adjusting the threshold for slope data division, the regional division can be optimized, ensuring that the water flow path meets the expected requirements. This results in a reasonable division of high-lying, flat, and low-lying farmland areas, effectively improving the rationality of water flow distribution, avoiding water stagnation or waste, and ensuring precise control of irrigation volume. This provides a scientific basis for the subsequent precise selection of irrigation points, rational allocation of irrigation volume, and smooth water flow. This division method ensures more targeted selection of irrigation points, more rational water flow paths, and significantly improves the intelligence of the irrigation system and the efficiency of water resource utilization.

[0038] 2. This invention proposes a farmland zoning method based on digital elevation models and regional attribute data. By combining regional soil data, crop data, and elevation data, it utilizes the K-means clustering algorithm to intelligently divide farmland. This method integrates soil moisture, temperature, pH, nutrient content, crop type, and sowing time from different regions, accurately reflecting the characteristics of farmland in each area. Different regions within farmland have different soil types, crop types, topographic features, and water requirements. Therefore, by zoning farmland, refined management and irrigation control can be implemented according to the specific needs of each region, avoiding indiscriminate and uniform irrigation. Through cluster analysis, reasonable farmland zoning can be achieved, ensuring that each farmland area is classified into the most suitable type based on its specific environment and crop needs, thus providing a foundation for subsequent precision irrigation. This zoning method can improve the accuracy and efficiency of farmland water conservancy projects, ensure the optimal use of water resources, and effectively avoid resource waste.

[0039] 3. This invention proposes a smart irrigation system based on crop growth stage analysis, remote sensing image analysis, and precise water requirement calculation. By combining crop type, sowing time, historical climate data, and expert experience, the system analyzes the crop growth stages in farmland areas to ensure that irrigation plans are precisely matched to crop growth needs. Furthermore, using UAV remote sensing imagery and image analysis methods, real-time data on farmland growth status, such as NDVI values, weed rate, and crop wilt index, is acquired to more accurately assess crop water requirements and growth status. This data, combined with soil moisture and precipitation information, is used to determine the accurate regional crop water deficit through standardized unit conversion and calculation. Based on this deficit, the irrigation amount for the target area is precisely calculated, thereby optimizing irrigation strategies. This system effectively enables dynamic adjustment of irrigation amounts, avoiding water waste caused by over-irrigation while ensuring crop growth needs are met, ultimately improving water resource utilization efficiency.

[0040] 4. This invention proposes a solution method based on genetic algorithm optimization. By combining a digital elevation model (DEM) with the target area's irrigation volume, it accurately determines the irrigation points and their irrigation volumes for high-altitude, mid-altitude, and low-lying areas. The system sets irrigation volume constraints and utilizes a genetic algorithm combined with a DEM for water flow simulation and multi-generational iterative optimization. While ensuring the irrigation needs of each area, it minimizes the total irrigation volume for farmland, thus achieving the optimal irrigation scheme. This method not only ensures that each farmland area receives the necessary water, avoiding the risk of waterlogging and root suffocation due to over-irrigation, but also efficiently allocates irrigation points, preventing water waste. By precisely controlling the irrigation volume at each point, water resource utilization is optimized, and farmland irrigation efficiency is improved. Attached Figure Description

[0041] Figure 1 A flowchart of a smart irrigation method for farmland water conservancy projects provided in this embodiment of the invention;

[0042] Figure 2 A structural diagram of a smart irrigation system for farmland water conservancy projects provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the process of dividing designated farmland into terrains according to an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of farmland grid area division and coordinate system provided in an embodiment of the present invention;

[0045] Figure 5 This is a schematic diagram of the grid region partitioning results provided in an embodiment of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Please see Figures 1 to 5 This invention provides a smart irrigation system and method for farmland water conservancy projects, the technical solution of which is as follows:

[0048] Example 1:

[0049] In this embodiment, the intelligent irrigation process for farmland is described in detail using the method and system proposed in this invention. It is known that, in this embodiment, intelligent irrigation management targets a rectangular farmland A located in the suburbs. The farmland covers approximately 500 mu (about 33 hectares) and is divided into several adjacent cultivation areas. The farmland has a regular geometric shape and clear boundaries; farmland A is suitable for flood irrigation. Flood irrigation, as a traditional irrigation method, evenly irrigates the farmland through naturally flowing water. This method is suitable for large areas of flat farmland and is relatively simple. However, in the traditional flood irrigation method for farmland A, water flow has long been difficult to precisely distribute. This leads to over-irrigation in some areas, wasting water resources, while other areas may suffer from insufficient water, affecting crop growth and overall farmland yield. Therefore, how to accurately control irrigation water volume and rationally deploy irrigation points has become crucial for improving water resource utilization efficiency and ensuring healthy crop growth.

[0050] The following is based on Figure 1 and Figure 2 The content describes the process of smart irrigation in farmland; among which... Figure 1 The specific process of the method proposed in this invention includes: S1. Generating a digital elevation model of a specified farmland; S2. Dividing the specified farmland into regular grids using a grid method. S3. Collect soil and crop data within each grid area to obtain... Group area attribute data; S4. Based on the digital elevation model and S5. Using the regional attribute data, the designated farmland is divided into K farmland regions, each farmland region including at least one grid region; S6. Growing season and growth status analysis is performed on the crops in the K farmland regions to obtain the crop water requirements of the K regions; S7. Weather forecast data is obtained, and the expected precipitation within a specified time period is calculated; S8. The regional soil moisture of the K farmland regions is obtained; S9. Based on the regional crop water requirements, the regional soil moisture, and the expected precipitation, the regional... S9. Determine the irrigation amount for the target area based on the crop water shortage in the region; S10. Divide the designated farmland into highland farmland areas, flat farmland areas, and lowland farmland areas based on the digital elevation model; S11. Determine the highland irrigation point, midland irrigation point, and lowland irrigation point and the corresponding irrigation amount based on the digital elevation model and K irrigation amounts for the target area; the highland irrigation point is located in the highland farmland area, the midland irrigation point is located in the flat farmland area, and the lowland irrigation point is located in the lowland farmland area. Figure 2 The system structure diagram proposed in this invention includes: a DEM modeling module, a data acquisition module, a region division module, a crop analysis module, an irrigation demand calculation module, and an irrigation strategy generation module; combined with Figure 1 and Figure 2 The following explanation is provided regarding the content:

[0051] A rectangular farmland A utilizes a smart irrigation system for farmland water conservancy projects, such as... Figure 2 As shown, it includes:

[0052] The DEM modeling module is used to generate digital elevation models of specified farmland.

[0053] The land division module includes: a terrain division unit, used to divide the designated farmland into highland farmland areas, flat farmland areas, and low-lying farmland areas according to the digital elevation model; and a grid division unit, used to divide the designated farmland into regular grids. A grid area; a region division unit, used to divide the specified farmland into K farmland areas;

[0054] The data acquisition module includes: an attribute data acquisition unit, used to acquire soil and crop data within each grid area, and obtain... Group regional attribute data; meteorological data acquisition unit, used to acquire meteorological forecast data; soil data acquisition unit, used to acquire regional soil moisture of K farmland areas;

[0055] The crop analysis module is used to perform growth period analysis and growth status analysis on crops in K farmland areas to obtain the water requirements of crops in K areas.

[0056] The data calculation module includes: a precipitation calculation unit, used to calculate the expected precipitation within a specified time period based on the meteorological forecast data; and an irrigation demand calculation unit, used to calculate the regional crop water shortage based on the regional crop water demand, the regional soil moisture and the expected precipitation, and to determine the target area irrigation amount based on the regional crop water shortage.

[0057] An irrigation strategy generation module is used to determine highland irrigation points, mid-land irrigation points, low-lying irrigation points, and corresponding irrigation amounts based on the digital elevation model and K irrigation amounts for the target area; the highland irrigation points are located in the highland farmland area, the mid-land irrigation points are located in the flat farmland area, and the low-lying irrigation points are located in the low-lying farmland area.

[0058] Furthermore, generating the digital elevation model (DEM) of the designated farmland includes: acquiring elevation data and surface point cloud data of the designated farmland using a drone, and combining this data with ground control point calibration to generate the DEM. This method can quickly and accurately acquire farmland topographic information without the need for traditional manual measurement, improving efficiency and accuracy. It is particularly suitable for farmland scenarios with complex terrain or large areas. The generated DEM provides accurate data support for subsequent farmland topographic delineation and irrigation strategy formulation, contributing to more scientific farmland management and precision irrigation, thereby optimizing resource utilization.

[0059] Further, the topographical division of the designated farmland according to the digital elevation model includes: dividing the designated farmland into candidate high areas, candidate flat areas, and candidate low-lying areas based on the slope data of the digital elevation model; simulating the water flow paths of the candidate high areas, the candidate flat areas, and the candidate low-lying areas in conjunction with flow direction analysis to obtain a first simulated water flow path; and verifying whether the first simulated water flow path meets the expected water flow path.

[0060] If the first simulated water flow path satisfies the expected water flow path, then the candidate high area, the candidate flat area, and the candidate low-lying area are respectively designated as the highland farmland area, the flat farmland area, and the low-lying farmland area.

[0061] If the first simulated water flow path does not meet the expected water flow path, the designated farmland is re-divided by adjusting the threshold of the slope data division into adjusted high areas, adjusted flat areas, and adjusted low-lying areas. The water flow paths of the adjusted high areas, the adjusted flat areas, and the adjusted low-lying areas are re-verified by combining flow direction analysis to obtain a second simulated water flow path. This process continues until the second simulated water flow path meets the expected water flow path, resulting in the highland farmland area, the flat farmland area, and the low-lying farmland area.

[0062] Figure 3This embodiment details the process of topographically dividing a designated farmland using a digital elevation model (DEM). The proposed DEM-based topographic division method, combined with flow direction analysis and simulated water flow paths, accurately delineates high, flat, and low-lying areas of farmland, ensuring that water flow distribution conforms to the expected flow sequence. Relying solely on slope data for area division may fail to accurately distinguish between high, flat, and low-lying areas, leading to unreasonable irrigation point placement, affecting the correct flow direction, and failing to ensure effective water coverage of the entire farmland area. It may even cause water stagnation or inaccessibility in some areas. This process provides a scientific basis for subsequent irrigation point selection, ensuring a rational layout and precise configuration of irrigation points, and avoiding uneven irrigation or water waste caused by improper water flow distribution. By optimizing the matching of topographic division and water flow paths, this invention effectively improves the overall efficiency of farmland irrigation and lays a solid foundation for efficient and sustainable water resource management.

[0063] Furthermore, the expected water flow path specifically requires that the water flow from the highland farmland area to the flat farmland area, and then from the flat farmland area to the lowland farmland area, and that the expected water flow path remains continuous between the highland farmland area, the flat farmland area, and the lowland farmland area, without any backflow or stagnation.

[0064] This provides a validation basis for the results of water flow simulation, effectively avoiding misjudgments caused by inaccurate flow direction analysis and ensuring the reasonable division of high, flat, and low-lying areas. This standard enables precise evaluation of whether the water flow path within a designated farmland meets expectations, thus laying the foundation for selecting irrigation points and optimizing irrigation strategies. It improves the accuracy and efficiency of the irrigation system, making the water flow simulation results more accurate in subsequent optimization processes, and providing a solid foundation for irrigation operations.

[0065] Specifically, the designated farmland is divided into regular grids using a grid method. Each grid region includes:

[0066] A two-dimensional coordinate system is established based on the boundaries of the designated farmland, where the X-axis represents the horizontal direction (east-west) and the Y-axis represents the vertical direction (south-north); the farmland is divided using a grid method as follows: Figure 4 As shown, in this embodiment, farmland A ( Figure 4 The largest rectangular area in the middle is divided into regular... A regular grid area.

[0067] Among them, using and Indicates the first The center point coordinates of each grid region Indicates the first The x-coordinate of the center point of each grid region Indicates the first The ordinate of the center point of each grid region.

[0068] At the same time, it should be ensured K represents the number of farmland areas obtained after subsequent clustering analysis using the K-means algorithm.

[0069] Furthermore, the specific methods for dividing the designated farmland into zones include:

[0070] Based on the elevation data of the designated farmland and The specified farmland is divided into zones based on the area attribute data.

[0071] The regional attribute data includes regional soil data and regional crop data; the regional soil data includes: soil temperature, soil pH, and soil nutrient content; the regional crop data includes: crop type and crop sowing time.

[0072] The elevation data of the designated farmland is divided into grids according to the grid method. For each grid region, the elevation data of the region is calculated, where the elevation data of the region is the average value of all the elevation data within the corresponding grid region;

[0073] Specifically, the elevation data of the designated farmland is divided into several grids according to the grid method. (Number) small areas, the elevation data of each area is calculated from the data of multiple measurement points in the area, and the average value of the elevation data of all measurement points in the area is taken.

[0074] The regional attribute data, regional elevation data, and spatial location data of each grid region are integrated to obtain a regional feature vector; the regional feature vector includes soil moisture, soil temperature, soil pH, soil nutrient content, crop type, crop sowing time, regional elevation data, spatial x-coordinate, and spatial y-coordinate;

[0075] The region feature vectors are standardized to obtain standard region feature vectors for each grid region.

[0076] The K-means clustering algorithm is used to perform cluster analysis on the feature vector of the standard region to obtain K farmland regions. Each grid region is assigned a corresponding farmland region number to generate a grid-farmland region mapping table, as shown in Table 1. In this embodiment, K is 9.

[0077] Table 1. Grid-Farmland Area Mapping Table

[0078]

[0079] The division of farmland areas is based on cluster analysis of the standardized feature vectors of each grid area. For example, the first column of the first row is labeled "Farmland Area 1", meaning that the area located at this grid position is classified as Farmland Area 1. Similarly, other grid areas are assigned to different farmland area numbers (such as Farmland Area 2, Farmland Area 3, etc.).

[0080] By clustering multidimensional data (such as soil temperature, pH, nutrient content, crop type, and sowing time) of farmland areas, grid regions with similar environmental characteristics can be grouped. This allows the system to more accurately analyze crop growth status, soil conditions, and irrigation needs for each region. While irrigation needs vary across regions, this method ensures that irrigation strategies for each region are tailored to its specific conditions. The clustering results not only provide a clear zoning basis for subsequent irrigation decisions but also offer zoning criteria for image acquisition and dynamic monitoring of crop growth. This method avoids the limitations of a single strategy, enabling real-time adjustments to irrigation plans and achieving more efficient and precise irrigation management.

[0081] Furthermore, the growth period analysis of the crops in the K farmland areas includes: obtaining the regional crop growth stages of the K farmland areas based on crop type, crop sowing time, local historical climate data, and expert experience.

[0082] In this embodiment, the local historical climate data refers to the climate data of the area where farmland A is located from the beginning of spring this year to the present, including temperature, precipitation, humidity, wind speed, light intensity and sunshine duration.

[0083] Precise analysis of the growth stages of crops in K farmland regions allows for accurate understanding of the water requirements of crops at different growth stages in each region. By combining crop type, sowing time, and local climate data, it is possible to scientifically predict changes in water demand for each region. This analysis helps determine the water requirements of each region at different growth stages, providing a basis for accurate calculation of subsequent irrigation amounts.

[0084] Furthermore, the analysis of crop growth status in the K farmland areas includes: acquiring remote sensing images of farmland in each grid area using a drone, and obtaining... Zhang grid area farmland remote sensing image; based on the grid-farmland area mapping table, The farmland remote sensing images described above are divided into K groups, resulting in K groups of farmland remote sensing images. Image analysis methods are used to calculate the image values ​​of each image within each group, including NDVI value, weed rate, and crop wilt index. The average values ​​of all images within each group are then calculated to obtain the group-wide average NDVI value, average weed rate, and average crop wilt index. By acquiring farmland remote sensing images using drones and performing image analysis, the crop growth status of each farmland area can be accurately assessed, providing crucial data for predicting regional crop water requirements. Calculating the NDVI value, weed rate, and crop wilt index of each image group allows for real-time monitoring of crop health. This precise growth status analysis helps calculate reasonable irrigation needs for each area based on actual conditions, avoiding over- or under-irrigation, effectively conserving water resources, and ensuring healthy crop growth. Combining the regional growth stage, climate data, and remote sensing image analysis results, the system can provide customized irrigation strategies for each area.

[0085] Figure 5 This embodiment provides the following: This is a schematic diagram of the grid area, in which different types of farmland areas are distinguished by different markings. This schematic diagram corresponds to Table 1.

[0086] Specifically, by performing the growth period analysis and growth status analysis on crops in the K farmland areas, the water requirements of crops in the K areas are obtained, including:

[0087] Given the regional crop growth stage and regional crop growth status (including the average NDVI value, average weed rate, and average crop wilt index within the group), the calculation of the regional crop water requirement includes the following steps:

[0088] Based on historical crop growth data, the area of ​​the j-th farmland region is used to obtain the basic water requirement of the region corresponding to the crop growth stage.

[0089] Then, the regional basic water requirement is adjusted based on the average NDVI value, average weed rate, and average crop wilt index within the group to obtain the regional crop water requirement.

[0090] Specifically, the adjustment method is based on the regional basic water requirement, and on this basis, it is adjusted by the ratio of the current average NDVI value of the crop to the maximum NDVI value. At the same time, the impact of weeds on crop water requirement is considered, that is, by adjusting by the product of an empirical adjustment coefficient and water requirement, as well as the impact of wilt index on water requirement.

[0091] Specifically, obtaining weather forecast data and calculating the expected precipitation for a specified time period includes the following steps:

[0092] Obtain the precipitation amount for a specified time period provided by the weather forecast system; assuming the forecast precipitation amount is... (Unit: mm)

[0093] The effective precipitation rate (ER) is preset according to different farmland areas. The effective precipitation rate is between 0 and 1, which represents the actual effective infiltration of precipitation into the soil. It is determined by factors such as the elevation data (topography), crop type and soil type of the farmland area.

[0094] ;

[0095] In this embodiment, the weather forecast indicates that the rainfall in the farmland area will be 5 mm in the next day. The effective rainfall rate for farmland area 1 is 80%, therefore the expected rainfall for farmland area 1 is:

[0096] ;

[0097] Further, the water shortage of crops in the region is calculated based on the regional crop water requirement, the regional soil moisture, and the expected precipitation. The irrigation amount for the target region is determined based on the regional crop water shortage, including:

[0098] The units of the regional crop water requirement, the regional soil moisture, and the expected precipitation are uniformly converted to obtain the regional crop water requirement in millimeters, the regional soil moisture in millimeters, and the expected precipitation in millimeters.

[0099] The crop water shortage in the region is calculated based on the crop water requirement in the millimeter region, the soil moisture in the millimeter region, and the expected precipitation in the millimeter region.

[0100] Specifically, the total available water in a region consists of two parts: regional soil moisture and expected precipitation. If the water required by crops exceeds the total available water, then the difference between the two is the regional crop water shortage; otherwise, if the available water is sufficient to meet or exceed the crop's needs, then the water shortage is zero.

[0101] Based on the regional crop water shortage, the target regional irrigation amount is determined. The target regional irrigation amount is calculated by multiplying the regional crop water shortage by an adjustment coefficient determined according to the soil type and crop type of the regional farmland, and then by a coefficient reflecting the efficiency of the irrigation method used.

[0102] Further calculations of regional crop water deficit based on crop water requirements, soil moisture, and expected rainfall, along with determination of target irrigation amounts, enable precision irrigation. This ensures sufficient water support for crops in each region while avoiding over-irrigation or water waste. By standardizing the conversion to millimeters and comprehensively considering the impact of crop water requirements, soil moisture, and expected rainfall, this method accurately calculates crop water deficits and allows for personalized adjustments to different regions through coefficient adjustments. This process not only considers regional soil type, crop variety, and irrigation method efficiency but also optimizes irrigation amounts based on specific farmland characteristics, ensuring the efficient operation of the irrigation system.

[0103] This data-accurate irrigation calculation avoids the problems of insufficient or excessive irrigation caused by empirical estimations or single-factor influences in traditional irrigation, thus improving the efficiency of agricultural water resource utilization. Through such precise regulation, not only is water waste reduced, but the growth needs of crops are also met, further enhancing the sustainability and efficiency of agricultural production.

[0104] Further, determining the highland irrigation point, the mid-land irrigation point, the low-lying irrigation point, and the corresponding irrigation amount based on the digital elevation model and the K irrigation amounts for the target area includes:

[0105] The irrigation constraints for the j-th farmland region are determined. For each farmland region, the total irrigation water it receives must meet two conditions: firstly, the total water volume must not be less than the target irrigation volume required by the farmland region; secondly, the total water volume must not exceed the maximum irrigation volume that the farmland region can withstand. The total irrigation water volume refers to the sum of the water volume provided by all irrigation points to the farmland region. The optimization objective is determined to be minimizing the total irrigation volume of the specified farmland region.

[0106] Water flow simulation is performed using a genetic algorithm combined with the digital elevation model to solve for the total irrigation amount that satisfies all the irrigation amount constraints and minimizes the total irrigation amount of the specified farmland; the highland irrigation point, the mid-land irrigation point, the low-lying irrigation point, and the corresponding irrigation amount are obtained through multi-generation iterative optimization.

[0107] The combination of genetic algorithms and water flow simulation can efficiently solve the problem of optimizing irrigation point distribution and irrigation volume. Specifically, the genetic algorithm first randomly generates irrigation point locations and initial irrigation volumes, then uses water flow simulation to verify whether these initial solutions meet irrigation constraints. If the initial solutions do not meet the constraints, the genetic algorithm continuously adjusts the irrigation points and volumes through mechanisms such as natural selection, crossover, and mutation until it finds an optimal solution that satisfies all constraints. Water flow simulation plays a crucial role in this process; it not only verifies the feasibility of the irrigation scheme but also judges the rationality of irrigation points based on farmland elevation data and terrain features. In this way, the genetic algorithm fully considers water flow paths and water volume allocation during the optimization process, thus ensuring the practicality and accuracy of the optimization results. Ultimately, the solution process combining genetic algorithms and water flow simulation not only ensures precise allocation of irrigation volume, avoiding over-irrigation or under-irrigation, but also achieves efficient water resource utilization under complex terrain conditions.

[0108] This invention relates to a smart irrigation system for farmland water conservancy projects. By combining precise digital elevation models and regional attribute data, it achieves refined zoning management of farmland. The system can intelligently determine irrigation strategies for each farmland area based on its terrain features, soil data, and crop needs, ensuring that the water requirements of each area are adequately met. By collecting and analyzing crop growth data, meteorological data, and soil moisture, the system can calculate crop water shortages in real time, effectively preventing water waste or over-irrigation and avoiding damage to crop roots. The rational planning and precise control of irrigation points make water resource utilization more efficient, improving the precision and efficiency of farmland irrigation, ensuring healthy crop growth, and promoting sustainable agricultural development. This system not only improves agricultural production efficiency but also provides feasible technical support for precision agriculture.

[0109] The intelligent irrigation system for farmland water conservancy projects of this invention can effectively cope with complex farmland conditions, and is especially suitable for farmland with multiple crops or large undulations. By combining digital elevation models, soil data, and crop demand analysis, the system can intelligently and accurately divide farmland into zones, and formulate personalized irrigation plans based on the characteristics of different areas (such as highlands, plains, and low-lying areas) and the differences in crop water requirements. For farmland with multiple crops, the system can meet the irrigation needs of different crops separately, avoiding over-irrigation or insufficient water, and ensuring that each crop receives appropriate water. For farmland with complex terrain, the system optimizes water flow distribution by rationally planning irrigation points in highlands, mediumlands, and low-lying areas, effectively solving irrigation problems in undulating areas and preventing waterlogging and water waste.

[0110] Example 2:

[0111] In Example 1, the method and system proposed in this invention successfully implemented the irrigation management and control process for farmland A. To further verify the effectiveness of this invention, an application experiment was also conducted on another square farmland B in this embodiment. Farmland B was initially planted with two crops: wheat and corn. The two crops were planted at the same time, but their water requirements and growth cycles were different.

[0112] To better facilitate subsequent precision irrigation and farmland management, farmland B applied a smart irrigation method for farmland water conservancy projects, including the following steps:

[0113] Generate a digital elevation model of the specified farmland (Farmland B);

[0114] The designated farmland (farmland B) is divided into regular grids using a grid method. Divide the data into grid regions; collect soil and crop data within each grid region to obtain... Group area attribute data; in this embodiment, the specified farmland is divided into regular grids using a grid method. Each grid area.

[0115] According to the digital elevation model and The region attribute data is used to divide the designated farmland into K farmland regions, each of which includes at least one grid region; in this embodiment, K is 10.

[0116] The growth period and growth status of crops in the K farmland areas were analyzed to obtain the water requirements of crops in the K areas.

[0117] Obtain meteorological forecast data and calculate the expected precipitation within a specified time period; obtain the regional soil moisture of K farmland areas; determine the regional crop water shortage based on the regional crop water requirement, the regional soil moisture, and the expected precipitation; determine the irrigation amount for the target area based on the regional crop water shortage;

[0118] The designated farmland is divided into three terrain areas: highland farmland, flat farmland, and lowland farmland, based on the digital elevation model. Highland irrigation points, mid-land irrigation points, and lowland irrigation points, along with their corresponding irrigation amounts, are determined based on the digital elevation model and K irrigation volumes for the target area. The highland irrigation points are located within the highland farmland area, the mid-land irrigation points are located within the flat farmland area, and the lowland irrigation points are located within the lowland farmland area.

[0119] Table 2 Irrigation Strategy Table

[0120]

[0121] The resulting irrigation strategies are shown in Table 2. Low-lying irrigation points serve as a supplementary and safeguard measure, ensuring that irrigation needs are met in low-lying areas under various possible farmland conditions (such as insufficient water demand, uneven distribution, or extreme weather). The locations of each irrigation point are represented by coordinates indicating its actual geographical location.

[0122] Flood irrigation was carried out on farmland B according to the irrigation strategy in Table 2.

[0123] To verify the practical effectiveness of the present invention, a set of comparative experiments were conducted. The experimental group used a smart irrigation method for farmland water conservancy projects provided by the present invention, such as... Figure 1 As shown in Table 3. The control group used multiple sensors deployed in the field to monitor soil and meteorological data in real time. Artificial intelligence and big data analysis were used to generate predictive models and provide irrigation suggestions, which were then implemented through automated control equipment. Both the experimental and control groups were tested on the same farmland at different times. The experimental results are shown in Table 3.

[0124] Table 3 Comparative Experimental Results Data Table

[0125]

[0126] By comparing the experimental data, the experimental group outperformed the control group in both crop mortality rate and crop waterlogging rate.

[0127] To further verify the water-saving effect and irrigation efficiency of the present invention, the irrigation scheme of the control group was deployed to the same farmland as the experimental group, and a comparative analysis was conducted using an automated irrigation volume calculation model.

[0128] Table 4 Comparison of Theoretical Irrigation Volume Data

[0129]

[0130] Referring to Table 4, theoretical calculations show that the irrigation demand of the control group was significantly higher than that of the experimental group during the same period. The experimental group, through water flow simulation and the rational layout of irrigation points, reduced unnecessary water retention and leakage, thereby further improving water resource utilization efficiency.

[0131] Through precise farmland zoning and crop demand analysis in this embodiment, the system can accurately predict the irrigation needs of different areas of farmland B, ensuring that the water requirements of wheat and corn are met and avoiding over-irrigation and water waste. Combining digital elevation models and meteorological data, the system rationally plans irrigation strategies and optimizes water allocation in each area, thereby improving overall irrigation efficiency. This intelligent zoning management method not only effectively improves crop growth health but also avoids root damage caused by over-irrigation, ensuring the sustainable development of agricultural production.

[0132] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart irrigation system for farmland water conservancy projects, characterized in that, include: Farmland is irrigated using flood irrigation. The DEM modeling module is used to generate digital elevation models of specified farmland. The classification module includes: a terrain classification unit, used to classify the designated farmland into candidate highlands, candidate flatlands, and candidate lowlands based on the slope data of the digital elevation model; to simulate the water flow paths of the candidate highlands, candidate flatlands, and candidate lowlands in conjunction with flow direction analysis to obtain a first simulated water flow path; to verify whether the first simulated water flow path meets the expected water flow path; if the first simulated water flow path meets the expected water flow path, then the candidate highlands, candidate flatlands, and candidate lowlands are respectively designated as highland farmland, flat farmland, and lowland farmland; if the first simulated water flow path does not meet the expected water flow path, then the designated farmland is reclassified by adjusting the threshold of the slope data classification. The newly defined areas are high-lying areas, flat-lying areas, and low-lying areas. The flow paths in these areas are re-verified using flow direction analysis to obtain a second simulated flow path. This process continues until the second simulated flow path meets the expected flow path, resulting in the high-lying farmland area, the flat-lying farmland area, and the low-lying farmland area. The expected flow path requires the water to flow from the high-lying farmland area to the flat-lying farmland area, and then from the flat-lying farmland area to the low-lying farmland area. The expected flow path must remain continuous among these three areas, without any backflow or stagnation. A grid division unit is used to divide the designated farmland into regular grids. A grid area; an area division unit, based on the elevation data of the specified farmland and... The specified farmland is divided into K farmland regions based on the group region attribute data. The data acquisition module includes: an attribute data acquisition unit, used to acquire soil and crop data within each grid area, and obtain... Group regional attribute data; meteorological data acquisition unit, used to acquire meteorological forecast data; soil data acquisition unit, used to acquire regional soil moisture of K farmland areas; The crop analysis module is used to perform growth period analysis and growth status analysis on crops in K farmland areas to obtain the water requirements of crops in K areas. The data calculation module includes: a precipitation calculation unit, used to calculate the expected precipitation within a specified time period based on the meteorological forecast data; and an irrigation demand calculation unit, used to calculate the regional crop water shortage based on the regional crop water demand, the regional soil moisture and the expected precipitation, and to determine the target area irrigation amount based on the regional crop water shortage. The irrigation strategy generation module is used to perform water flow simulation by combining the digital elevation model and the K irrigation amounts of the target area with the digital elevation model through a genetic algorithm, so as to solve the problem of satisfying all irrigation amount constraints and minimizing the total irrigation amount of the specified farmland, and determine the highland irrigation point, midland irrigation point, lowland irrigation point and the corresponding irrigation amount.

2. The intelligent irrigation system for farmland water conservancy projects according to claim 1, characterized in that, Generating the digital elevation model of the designated farmland includes: acquiring elevation data and surface point cloud data of the designated farmland through a UAV, and generating the digital elevation model by combining it with ground control point calibration.

3. The intelligent irrigation system for farmland water conservancy projects according to claim 1, characterized in that, The specific method for dividing the designated farmland into zones includes: based on the elevation data of the designated farmland and The specified farmland is divided into zones based on the area attribute data. The regional attribute data includes regional soil data and regional crop data; the regional soil data includes soil temperature, soil pH, and soil nutrient content; the regional crop data includes crop type and crop sowing time; the elevation data of the designated farmland is divided into grids according to a grid method. For each grid region, regional elevation data is calculated, where the regional elevation data is the average of all elevation data within the corresponding grid region. The regional attribute data, regional elevation data, and spatial location data of each grid region are integrated to obtain a regional feature vector. The regional feature vector is then standardized to obtain a standard regional feature vector for each grid region. Finally, the standard regional feature vector is clustered using a K-means clustering algorithm to obtain K farmland regions.

4. The intelligent irrigation system for farmland water conservancy projects according to claim 1, characterized in that, The growth period analysis of the crops in the K farmland areas includes: obtaining the regional crop growth stage of the K farmland areas based on crop type, crop sowing time, local historical climate data, and expert experience.

5. The intelligent irrigation system for farmland water conservancy projects according to claim 1, characterized in that, The analysis of crop growth status in the K farmland areas includes: acquiring remote sensing images of farmland in each grid area using a drone, and obtaining... Remote sensing images of farmland in grid-like areas; The remote sensing images of farmland in the grid area described above are divided into K groups, resulting in K groups of farmland remote sensing images. Through image analysis methods, the image values ​​of each farmland remote sensing image in each group are calculated, including NDVI value, weed rate, and crop wilt index. The mean of all image values ​​in each group is calculated to obtain the average NDVI value, average weed rate, and average crop wilt index within each group.

6. The intelligent irrigation system for farmland water conservancy projects according to claim 1, characterized in that, The calculation of the regional crop water shortage based on the regional crop water requirement, the regional soil moisture, and the expected precipitation, and the determination of the irrigation amount for the target area based on the regional crop water shortage, include: unifying the units of the regional crop water requirement, the regional soil moisture, and the expected precipitation to obtain the regional crop water requirement in millimeters, the regional soil moisture in millimeters, and the expected precipitation in millimeters; and calculating the regional crop water shortage based on the regional crop water requirement in millimeters, the regional soil moisture in millimeters, and the expected precipitation in millimeters.

7. A smart irrigation method for farmland water conservancy projects, characterized in that, To implement the intelligent irrigation system for farmland water conservancy projects according to any one of claims 1 to 6, the following steps are included: Generate a digital elevation model of the specified farmland; The designated farmland is divided into regular grids using a grid method. Divide the data into grid regions; collect soil and crop data within each grid region to obtain... Group region attribute data; Based on the elevation data of the designated farmland and The specified farmland is divided into K farmland regions by using the regional attribute data of the group; The growth period and growth status of crops in the K farmland areas were analyzed to obtain the water requirements of crops in the K areas. Obtain meteorological forecast data and calculate the expected precipitation within a specified time period; obtain the regional soil moisture of K farmland areas; determine the regional crop water shortage based on the regional crop water requirement, the regional soil moisture, and the expected precipitation; determine the irrigation amount for the target area based on the regional crop water shortage; The designated farmland is divided into highland farmland area, flat farmland area and lowland farmland area according to the digital elevation model; the highland irrigation point, midland irrigation point, lowland irrigation point and corresponding irrigation amount are determined according to the digital elevation model and K irrigation amounts of the target area.

Images