A water-saving control method, cloud platform and device for agricultural irrigation

Abstract

This application discloses a water-saving control method, cloud platform, and equipment for agricultural irrigation, relating to the field of irrigation water-saving control technology. The method includes: determining the historical rainfall and historical soil moisture parameters of the target farmland's geographical location; determining the farmland's water demand pattern characteristics based on the historical rainfall and soil moisture parameters; constructing a farmland water-saving control model based on the farmland's water demand pattern characteristics; dividing the target farmland into water demand zones based on crop information; obtaining the expected irrigation values ​​for each water demand zone based on the farmland water-saving control model and the soil moisture parameters of each water demand zone; acquiring the real-time irrigation values ​​for each water demand zone; and real-time regulating a preset intelligent irrigation valve within each water demand zone based on the expected and real-time irrigation values. This application can effectively solve the problem of low water resource utilization.

Description

Technical Field

[0001] This application relates to the field of irrigation water-saving control technology, and in particular to a water-saving control method, cloud platform and equipment for agricultural irrigation. Background Technology

[0002] With global climate change and population growth, water scarcity is becoming increasingly prominent. Agriculture, as the largest water user sector, typically accounts for a large proportion of total water consumption. Therefore, improving agricultural water use efficiency and reducing water waste are of great significance in alleviating water shortages.

[0003] Traditional agricultural irrigation typically relies on fixed irrigation plans or human experience to assess soil drought conditions and employs conventional irrigation techniques such as flood irrigation, furrow irrigation, and submerged irrigation. However, traditional irrigation methods often suffer from high water consumption and low water resource utilization. For example, flood irrigation involves introducing large amounts of water into the farmland, allowing it to flow freely and infiltrate the soil to supply the crops with the necessary water. Because significant amounts of water evaporate and are lost during this free diffusion process, the water resource utilization rate is insufficient. Furthermore, flood irrigation also results in uneven irrigation, with some areas receiving excessive water while others remain dry, leading to low water resource utilization.

[0004] There is currently no effective solution to the problem of low water resource utilization in traditional irrigation methods. Summary of the Invention

[0005] This application provides a water-saving control method, cloud platform, and equipment for agricultural irrigation to address the problem of low water resource utilization.

[0006] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0007] Firstly, a water-saving control method for agricultural irrigation, applied to a cloud platform, includes:

[0008] Obtain the geographical location of the target farmland;

[0009] The historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland are determined in the first preset database.

[0010] Based on the historical rainfall and historical soil moisture parameters, the characteristics of farmland water demand patterns of the target farmland are determined;

[0011] Based on the characteristics of farmland water demand patterns, a farmland water-saving control model is constructed.

[0012] Obtain crop information for the target farmland;

[0013] Based on the crop information, the water requirement areas of the target farmland are divided;

[0014] Real-time collection of soil moisture parameters for each water-demanding area;

[0015] Based on the farmland water-saving control model and the soil moisture parameters of each water-demand area, the expected irrigation values ​​for each water-demand area are obtained;

[0016] Obtain real-time irrigation data for each water-demand area;

[0017] Based on the predicted irrigation values ​​and the real-time irrigation values, water valve control commands are generated to control the preset smart irrigation water valves in each water-demand area in real time.

[0018] In one possible implementation of the first aspect, the historical soil moisture parameters include historical soil moisture data, historical soil density data, and historical soil pH data.

[0019] In one possible implementation of the first aspect, determining the farmland water demand pattern characteristics of the target farmland based on the historical rainfall and the historical soil moisture parameters includes:

[0020] Using the historical soil moisture data and a preset soil moisture content formula, the original soil moisture content of the target farmland is calculated.

[0021] Historical farmland soil moisture content and historical artificial irrigation water volume are obtained from the second preset database;

[0022] Using the preset Pearson correlation coefficient formula, the correlation coefficient between the historical farmland soil moisture content and the historical soil pH data is calculated to obtain the soil pH influencing factor;

[0023] The soil pH influencing factor, the original soil moisture content of the farmland, and the historical soil density data are fitted with parameters to obtain the soil saturated moisture content pressure time-varying coefficient. The soil saturated moisture content pressure time-varying coefficient is used to characterize the time-varying nonlinear characteristic parameter of farmland soil under vertical pressure.

[0024] The cumulative irrigation flow is determined by the historical rainfall and the historical artificial irrigation injection.

[0025] By fitting the parameters of the cumulative irrigation flow, the historical artificial irrigation water injection, and the time-varying coefficient of soil saturated moisture content pressure, the characteristic coefficient of farmland water demand pattern is obtained.

[0026] In a pre-defined database of farmland water demand patterns, the time-varying nonlinear characteristics of farmland irrigation water corresponding to the farmland water demand pattern characteristic coefficients of the target farmland are determined. These time-varying nonlinear characteristics of farmland irrigation water are used to characterize the farmland water demand pattern characteristics.

[0027] In one possible implementation of the first aspect, constructing a farmland water-saving control model based on the farmland water demand pattern characteristics includes:

[0028] Based on the characteristics of farmland water demand patterns, the upper and lower limits of irrigation water injection for the target farmland are determined.

[0029] Construct a multi-objective function, which includes a function to minimize irrigation water injection, a function to minimize irrigation cost, and a function to maximize crop yield. The function to minimize irrigation water injection is the primary objective function, and the functions to minimize irrigation cost and maximize crop yield are secondary objective functions.

[0030] The upper limit of irrigation water injection and the lower limit of irrigation water injection are respectively used as the first objective constraint and the second objective constraint of the objective function for minimizing irrigation water injection volume;

[0031] The secondary objective function is used as the third objective constraint condition of the primary objective function;

[0032] A farmland water-saving control model is constructed by combining the first objective constraint, the second objective constraint, the third objective constraint, and the multi-objective function.

[0033] In one possible implementation of the first aspect, determining the upper limit and lower limit of irrigation water injection for the target farmland includes:

[0034] Obtain the number of drought days and average rainfall for farmland crops within a preset time period;

[0035] Obtain the types of crops planted in the target farmland, and determine the growth water requirement coefficient, crop water requirement, and soil water retention of the current crop types in the first preset database;

[0036] The drought impact coefficient is obtained by comparing the average rainfall with the preset daily standard rainfall.

[0037] Multiplying the drought impact coefficient by the number of drought days for crops yields the drought impact index;

[0038] The relative humidity index is calculated using a preset relative humidity index formula based on the crop water requirement, the soil water retention capacity, and the average rainfall.

[0039] The relative humidity index and the drought impact index are added together to obtain the comprehensive water deficit index for crops;

[0040] The lower limit of irrigation water injection is obtained by multiplying the comprehensive index of crop water deficit with the growth water requirement coefficient.

[0041] Obtain the total irrigated area and total available irrigation water of the target farmland;

[0042] The available water volume per unit area is calculated using the total available irrigation water volume and the total irrigated farmland area.

[0043] The higher of the available water per unit area and the water requirement of the crops is taken as the upper limit of irrigation water supply for the target farmland.

[0044] In one possible implementation of the first aspect, the crop information includes crop type and crop growth stage, and the step of dividing the water requirement area of ​​the target farmland based on the crop information includes:

[0045] In a first preset database, crop coefficients corresponding to the crop type and the crop growth stage are determined. The crop coefficients are used to characterize the ratio between the actual water requirement of the crop and the potential evapotranspiration at different growth stages.

[0046] Obtain current environmental and climate parameters;

[0047] Using the aforementioned environmental and climate parameters, the reference crop transpiration rate is obtained through the Penman-Montes formula.

[0048] Multiply the reference crop transpiration rate by the crop coefficient to obtain the actual water requirement of the crop;

[0049] Based on the actual water requirements of the crops, the target farmland is divided into high water requirement areas, medium water requirement areas, and low water requirement areas.

[0050] In one possible implementation of the first aspect, obtaining the expected irrigation values ​​for each water-demand area based on the farmland water-saving control model and soil moisture parameters for each water-demand area includes:

[0051] Based on the soil moisture parameters of each water-demand area, determine the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area;

[0052] The real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area are input into the farmland water-saving control model to obtain the expected irrigation values ​​for each water-demand area.

[0053] In one possible implementation of the first aspect, the method further includes:

[0054] For any of the water-required areas, if the real-time soil moisture content is less than the crop wilting critical data, then it is an emergency irrigation state, and all preset smart irrigation valves in the water-required area are opened.

[0055] If the real-time soil moisture content is greater than or equal to the crop wilting critical data and less than or equal to the farmland water holding capacity, then it is in the on-demand irrigation state, and the smart irrigation water valve in the water demand area is opened according to the expected irrigation value of each water demand area.

[0056] If the real-time soil moisture content is greater than or equal to the farmland water holding capacity, then the irrigation is turned off, and all preset smart irrigation valves in the water-required area are closed.

[0057] Secondly, this application provides a cloud platform applied to the aforementioned water-saving control method for agricultural irrigation, comprising:

[0058] The geographic data management module is used to determine the geographic location of the target farmland.

[0059] The data acquisition module is used to determine the historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland in the first preset database.

[0060] The pattern characteristic determination module is used to determine the farmland water demand pattern characteristics of the target farmland based on the historical rainfall and the historical soil moisture parameters;

[0061] The model building module is used to build a farmland water-saving control model based on the characteristics of farmland water demand patterns.

[0062] An information acquisition module is used to acquire crop information of the target farmland;

[0063] The region division module is used to divide the water requirement area of ​​the target farmland based on the crop information;

[0064] The data acquisition module is used to collect soil moisture parameters for each of the water-required areas.

[0065] The irrigation value determination module is used to obtain the expected irrigation value for each water-demand area based on the farmland water-saving control model and the soil moisture parameters of each water-demand area;

[0066] The real-time irrigation data acquisition module is used to acquire real-time irrigation data for each water-demand area.

[0067] The real-time control module is used to adjust the preset smart irrigation valves in each water demand area in real time according to the expected irrigation value and the real-time irrigation value.

[0068] Thirdly, this application provides an electronic device, comprising:

[0069] The memory is configured to store instructions; and

[0070] The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the aforementioned water-saving control method for agricultural irrigation.

[0071] By comprehensively considering the geographical location, historical rainfall, and historical soil moisture parameters of the target farmland, the water demand patterns of the farmland can be accurately determined, thereby constructing a farmland water-saving control model. This makes irrigation more precise and improves water resource utilization. Dividing farmland into water-demand zones based on crop information allows for differentiated irrigation management tailored to the water needs of different crops, improving agricultural irrigation efficiency. Real-time collection of soil moisture parameters for each water-demand zone, combined with the farmland water-saving control model and parameters to obtain predicted irrigation values, enables real-time monitoring of farmland water conditions. Furthermore, by comparing predicted and real-time irrigation values, water valve control commands can be generated to regulate intelligent irrigation valves in real time, ensuring that irrigation volume meets crop needs. This significantly reduces water waste during irrigation, improves irrigation water utilization efficiency, not only helps conserve water resources but also lowers irrigation costs and enhances the economic benefits of agricultural production.

[0072] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0073] Figure 1 A schematic flowchart of a water-saving control method for agricultural irrigation provided in an embodiment of this application;

[0074] Figure 2 This application provides a schematic diagram of the structure of a cloud platform according to an embodiment of the present application.

[0075] Figure 3 This is a schematic diagram of a page for real-time monitoring of soil moisture parameters, provided as an embodiment of this application. Detailed Implementation

[0076] 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.

[0077] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0078] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0079] Figure 1 The illustration schematically shows a flow chart of a water-saving control method for agricultural irrigation according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a water-saving control method for agricultural irrigation, applied to a cloud platform, which may include the following steps.

[0080] S101, Obtain the geographical location of the target farmland;

[0081] S102. Determine the historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland in the first preset database;

[0082] S103. Based on historical rainfall and historical soil moisture parameters, determine the characteristics of farmland water demand patterns in the target farmland;

[0083] S104. Construct a farmland water-saving control model based on the characteristics of farmland water demand patterns;

[0084] S105. Obtain crop information for the target farmland;

[0085] S106. Based on crop information, delineate the water demand areas of the target farmland;

[0086] S107. Real-time collection of soil moisture parameters for each water-demanding area;

[0087] S108. Based on the farmland water-saving control model and the soil moisture parameters of each water-demand area, the expected irrigation values ​​for each water-demand area are obtained;

[0088] S109. Obtain real-time irrigation data for each water-demand area;

[0089] S110. Based on the expected irrigation data and real-time irrigation data, generate water valve control instructions to control the preset smart irrigation water valves in each water demand area in real time.

[0090] First, the geographical location of the target farmland is obtained. In this embodiment, the target farmland can be determined based on the actual situation and can be achieved through satellite remote sensing imagery. Satellite remote sensing technology can capture high-resolution images of the Earth's surface, and these high-resolution images can be used to identify the boundaries, shape, and distribution characteristics of the farmland. In other words, high-resolution images of the farmland are obtained using satellite remote sensing technology. Through image analysis, the boundaries, shape, and distribution characteristics of the farmland are identified. Then, Geographic Information System (GIS) technology is used to process geospatial information, matching the remote sensing images with geographical location information to determine the precise location of the farmland.

[0091] Next, the historical rainfall corresponding to the geographical location of the target farmland, as well as the historical soil moisture parameters of the target farmland, are determined in the first preset database. Soil moisture parameters refer to a series of indicators used to describe and assess soil moisture conditions and their impact on crop growth. Specifically, the geographical location information of the target farmland needs to be found in the first preset database, such as the region where the farmland is located and its latitude and longitude coordinates. After determining the geographical location of the target farmland, historical rainfall data for that region can be searched in the database. Similarly, the historical soil moisture parameters of the target farmland can be searched in the first preset database. Historical soil moisture parameters can include data such as soil moisture content, soil temperature, and soil salinity.

[0092] After determining historical rainfall and soil moisture parameters of the target farmland, the water requirement patterns of the target farmland are determined based on these historical rainfall and soil moisture parameters. In this embodiment, the water requirement pattern refers to the regularity of the water demand and characteristics of crops at each growth stage during their growth period. In other words, by analyzing the relationship between historical rainfall and soil moisture parameters, the impact of rainfall on soil moisture can be understood, such as changes in soil moisture content after rainfall and the correlation between rainfall season and soil moisture. Furthermore, by analyzing the relationship between soil moisture parameters and crop water requirements, the impact of soil moisture content and soil temperature on crop water requirements can be understood, such as the impact of excessive or insufficient soil moisture on crop growth and the irrigation needs of crops under different soil moisture conditions. Based on the historical rainfall and soil moisture parameters, the water demand patterns of the target farmland in different seasons are determined. For example, the water demand of farmland may be less in seasons with abundant rainfall, while it may increase significantly in dry seasons. Based on the changes in soil moisture parameters, the characteristics of the farmland's water demand patterns are determined. For example, timely irrigation is required when soil moisture content is too low, while drainage measures are needed to prevent crop damage when soil moisture content is too high.

[0093] Subsequently, based on the water requirement patterns of farmland, a farmland water-saving control model is constructed. In this embodiment, the water requirement patterns refer to the regular water demand exhibited by crops at each growth stage during their growth period. Specifically, firstly, data can be collected, including meteorological data, soil data, and crop growth data. After data collection, MATLAB software is used to implement a fitting function to analyze the water requirement patterns of crops at different growth stages and determine the critical water requirement period for crops. Then, based on the crop water requirement patterns and local water resource conditions, appropriate water-saving irrigation technologies, such as drip irrigation, seepage irrigation, and sprinkler irrigation, are selected. In this embodiment, drip irrigation is used. Next, mathematical methods, such as multiplication models, addition models, or computer simulation techniques, are used to establish a farmland water-saving control model. This model reflects the relationship between crop growth and water supply, as well as the impact of different irrigation strategies on crop growth and yield.

[0094] After constructing a farmland water-saving control model, crop information of the target farmland can be obtained through agricultural remote sensing. Agricultural remote sensing is an efficient and accurate means of acquiring farmland information. It acquires remote sensing image data of farmland through remote sensing platforms such as satellites or drones, and uses image processing technology and machine learning algorithms to automatically classify and interpret the images, thereby identifying key information such as vegetation type and crop growth. In this embodiment, the machine learning algorithm can be a method such as support vector machine, random forest, or K-nearest neighbors.

[0095] Based on crop information, the water requirement zones of the target farmland are delineated. In this embodiment, the crop information includes crop species and crop growth stage. Different types of crops have different water requirements; for example, some crops may be more drought-tolerant, while others are more sensitive to water. The water requirements of the same crop also differ at different growth stages; for example, crops may require more water during the growing and fruiting stages. Therefore, by analyzing crop species and crop growth stages, the water requirement zones of the target farmland are delineated. In other words, irrigation requirements are determined based on crop species and crop growth stages, and farmland is divided into different irrigation requirement levels based on these requirements. Irrigation requirement levels can be determined comprehensively based on factors such as crop transpiration and evaporation, soil moisture status, and crop water use efficiency.

[0096] After determining the water-required areas of the target farmland, real-time soil moisture parameters for each area are collected. This can be achieved using soil moisture sensors, such as soil moisture sensors (e.g., capacitive, TDR sensors), temperature sensors, conductivity sensors, and pH electrodes. These sensors measure key parameters in the soil, including moisture content, temperature, salinity (reflected by conductivity), and pH. In other words, real-time data on soil moisture, temperature, and pH values ​​are collected for each water-required area using soil moisture sensors (e.g., capacitive, TDR sensors), temperature sensors, conductivity sensors, and pH electrodes.

[0097] Subsequently, based on the farmland water-saving control model and soil moisture parameters for each water-demand area, the predicted irrigation values ​​for each area are obtained. Specifically, firstly, soil moisture sensors are used to collect parameters such as soil moisture, temperature, heat flux, water potential, and electrical conductivity in real time for each water-demand area. Secondly, the real-time collected soil moisture parameters are input into the previously constructed farmland water-saving control model. Using the farmland water-saving control model, based on the input soil moisture parameters and crop growth data, the predicted irrigation values ​​for each water-demand area are obtained. The predicted irrigation values ​​can include information such as irrigation amount, irrigation time, and irrigation frequency.

[0098] After obtaining the estimated irrigation values ​​for each water-demand area, the real-time irrigation values ​​for each water-demand area can be acquired. This can be done by using smart irrigation equipment (such as smart irrigation controllers and flow meters) installed in the farmland to collect irrigation data in real time. By acquiring the real-time irrigation values ​​for each water-demand area, information such as irrigation volume, irrigation time, and irrigation speed for each water-demand area can be accurately recorded.

[0099] Based on predicted and real-time irrigation data, water valve control commands are generated to regulate the pre-set smart irrigation valves in each water-demand area in real time. This involves comparing the real-time and predicted irrigation data and analyzing the differences. If the real-time irrigation data is lower than the predicted data, the irrigation volume needs to be increased. If the real-time irrigation data is higher than the predicted data, the irrigation volume may need to be reduced or irrigation may need to be stopped. Next, based on the comparison results, corresponding water valve control commands are generated and sent to the smart irrigation valves in each water-demand area via wireless communication technology. The smart irrigation valves will automatically adjust their irrigation status according to the received commands to achieve precise irrigation control. After executing the control commands, the irrigation status of each water-demand area can continue to be monitored, and necessary adjustments can be made as needed based on the actual situation.

[0100] By comprehensively considering the geographical location, historical rainfall, and historical soil moisture parameters of the target farmland, the water demand patterns of the farmland can be accurately determined, thereby constructing a farmland water-saving control model. This makes irrigation more precise and improves water resource utilization. Dividing farmland into water-demand zones based on crop information allows for differentiated irrigation management tailored to the water needs of different crops, improving agricultural irrigation efficiency. Real-time collection of soil moisture parameters for each water-demand zone, combined with the farmland water-saving control model and parameters to obtain predicted irrigation values, enables real-time monitoring of farmland water conditions. Furthermore, by comparing predicted and real-time irrigation values, water valve control commands can be generated, allowing for real-time adjustment of intelligent irrigation valves to ensure that irrigation volume meets crop needs. This significantly reduces water waste during irrigation, improves irrigation water utilization efficiency, not only helps conserve water resources but also lowers irrigation costs and enhances the economic benefits of agricultural production.

[0101] In one embodiment of this example, the water demand pattern characteristics of the target farmland are determined based on historical rainfall and historical soil moisture parameters, including:

[0102] S210. Using historical soil moisture data and a preset soil moisture content formula, calculate the original soil moisture content of the target farmland.

[0103] S220. Obtain historical farmland soil moisture content and historical artificial irrigation water volume from the second preset database;

[0104] S230. Using the preset Pearson correlation coefficient formula, calculate the correlation coefficient between historical farmland soil moisture content and historical soil pH data to obtain the soil pH influencing factor.

[0105] S240. By fitting parameters to soil pH influencing factors, original soil moisture content and historical soil density data, the soil saturated moisture content pressure time-varying coefficient is obtained. The soil saturated moisture content pressure time-varying coefficient is used to characterize the time-varying nonlinear characteristic parameter of farmland soil under vertical pressure.

[0106] S250. Determine the cumulative irrigation flow by using historical rainfall and historical artificial irrigation injection.

[0107] S260. The cumulative irrigation flow, historical artificial irrigation water injection, and soil saturation moisture content pressure time-varying coefficient are fitted to obtain the characteristic coefficient of farmland water demand pattern.

[0108] S270. In the preset farmland water demand pattern characteristic database, determine the time-varying nonlinear characteristics of farmland irrigation water use corresponding to the farmland water demand pattern characteristic coefficient of the target farmland. The time-varying nonlinear characteristics of farmland irrigation water use are used to characterize the farmland water demand pattern characteristics.

[0109] In this embodiment, historical soil moisture parameters include historical soil moisture data, historical soil density data, and historical soil pH data. Figure 3 This application provides a schematic diagram of a page for real-time monitoring of soil moisture parameters, as shown in the embodiments of this application. Figure 3 As shown, soil moisture parameters can be monitored in real time through electronic devices, and parameters such as soil temperature, soil humidity, and light intensity can be obtained.

[0110] In this embodiment, the electronic device can be a tablet computer, desktop computer, laptop computer, handheld computer, wearable device, laptop computer, ultra-mobile personal computer (UMPC), netbook, or other device with a processor. Of course, the electronic device can also be a server. This application embodiment does not impose any special limitations on the specific form of the electronic device.

[0111] First, using historical soil moisture data and a preset soil moisture content formula, the original soil moisture content of the target farmland is calculated. In other words, the pre-processed historical soil moisture data is input into the preset soil moisture content formula to calculate the soil moisture content at each time point. In this embodiment, the preset soil moisture content formula is as follows:

[0112] Soil moisture content (wt%) = (Weight of water / Dry weight of soil) × 100%

[0113] Specifically, in the preset soil moisture content formula, the water weight can be obtained by subtracting the oven-dried soil weight from the original soil weight. The original soil weight refers to the weight of the soil sample before drying. The oven-dried soil weight refers to the weight of the soil sample after drying, at which point the moisture in the soil has been removed. For example, suppose a soil sample has an original soil weight of 150 grams, and after drying, its oven-dried soil weight is 120 grams. Then, calculate the moisture content of this soil sample:

[0114] Water weight = 150g - 120g = 30g; Soil moisture content (weight %) = 30g / 120g × 100% = 25%;

[0115] Therefore, the moisture content of the soil sample is 25%.

[0116] After obtaining the original soil moisture content of the target farmland, historical farmland soil moisture content and historical artificial irrigation water injection volume are retrieved from a second preset database. In this embodiment, historical farmland soil moisture content refers to the water content in the farmland soil over a past period. Historical artificial irrigation water injection volume refers to the amount of water artificially injected into the farmland through the irrigation system over a past period. In specific implementation, a query can be entered into the second preset database to extract the required historical farmland soil moisture content and historical artificial irrigation water injection volume data.

[0117] Subsequently, using the pre-defined Pearson correlation coefficient formula, the correlation coefficient between historical farmland soil moisture content and historical soil pH data is calculated to obtain the soil pH influencing factor. In other words, the collected data is substituted into the Pearson correlation coefficient formula to determine the correlation coefficient between historical farmland soil moisture content and historical soil pH data, and this correlation coefficient is used as the soil pH influencing factor. In this embodiment, the soil pH influencing factor is the influence of soil pH on historical farmland soil moisture content. The pre-defined Pearson correlation coefficient formula is shown below:

[0118]

[0119] Where r represents the Pearson correlation coefficient; n represents the number of data points; x i and y i In this embodiment, x represents the two variable values ​​of the i-th data point. i Represents historical farmland soil moisture content, y i Represents historical soil pH value; and This represents the mean of two variables.

[0120] By fitting parameters to soil pH influencing factors, original soil moisture content, and historical soil density data, a time-varying coefficient for soil saturated moisture content pressure is obtained. In this embodiment, the time-varying coefficient of soil saturated moisture content pressure is used to characterize the time-varying nonlinear characteristic parameter of farmland soil under vertical pressure. In other words, the time-varying relationship between farmland soil pH influencing factors, original soil moisture content, and historical soil density data is fitted using parameter fitting methods. The parameter fitting method can be linear regression fitting. Through linear regression, the fitting formula for farmland soil pH influencing factors, original soil moisture content, and historical soil density data is obtained, as shown below:

[0121]

[0122] Where w represents the time-varying coefficient of soil saturated moisture content pressure; a represents the soil pH value influencing factor; σ represents the vertical pressure on the soil; w0 represents the original moisture content of farmland soil; and ρ represents historical soil density data.

[0123] After obtaining the time-varying coefficient of soil saturated moisture content pressure, the cumulative irrigation flow is determined using historical rainfall and historical artificial irrigation injection. In this embodiment, historical artificial irrigation injection refers to the amount of irrigation water artificially introduced to meet the needs of crop growth over a past period. The cumulative irrigation flow refers to the total irrigation water volume within a certain period, including both natural rainfall and artificial irrigation. In other words, the historical rainfall and historical artificial irrigation injection within the same time period are directly added together to obtain the cumulative irrigation flow for that period, as shown in the formula below:

[0124] Cumulative irrigation water volume = Historical rainfall + Historical artificial irrigation water injection

[0125] Subsequently, the cumulative irrigation flow, historical artificial irrigation volume, and soil saturated moisture content pressure time-varying coefficient are fitted with parameters to obtain the characteristic coefficient of farmland water demand. In this embodiment, the soil saturated moisture content pressure time-varying coefficient refers to the coefficient of soil saturated moisture content changing over time when the soil is under pressure; it is the characteristic coefficient of farmland water demand. In other words, the cumulative irrigation flow, historical artificial irrigation volume, and soil saturated moisture content pressure time-varying coefficient are fitted with a time-varying relationship using parameter fitting. The parameter fitting method can be linear regression fitting. Through linear regression, the fitting formula for the cumulative irrigation flow, historical artificial irrigation volume, and soil saturated moisture content pressure time-varying coefficient is obtained, as shown below:

[0126]

[0127] Where μ0 represents the characteristic coefficient of farmland water demand pattern, w represents the time-varying coefficient of soil saturated moisture content pressure; μ represents the cumulative irrigation flow; d represents the historical artificial irrigation volume; and m0 represents the upper limit of water demand for the entire growth period of crops.

[0128] After obtaining the characteristic coefficients of farmland water demand patterns, the time-varying nonlinear characteristics of farmland irrigation water use corresponding to the characteristic coefficients of farmland water demand patterns in a preset farmland water demand pattern characteristic database are determined. In this embodiment, the time-varying nonlinear characteristics of farmland irrigation water use refer to the nonlinear variation of farmland irrigation water volume over time. That is, in the preset farmland water demand pattern characteristic database, based on the characteristic coefficients of farmland water demand patterns, the time-varying nonlinear characteristics of farmland irrigation water use corresponding to the characteristic coefficients are selected to determine the differences in water requirements at different growth stages of crops. For example, when the characteristic coefficients of farmland water demand patterns are within a specific threshold, the time-varying nonlinear characteristics of farmland irrigation water use are obtained by determining the characteristics of the current farmland irrigation water use changing over time within the current specific threshold.

[0129] By identifying the water demand patterns of target farmland, we can better understand the overall trends and distribution patterns of farmland irrigation water use, providing a scientific basis for water resource management and allocation, ensuring the rational allocation and effective use of water resources, avoiding over-irrigation or under-irrigation, and improving the efficiency of irrigation water use.

[0130] In one embodiment of this invention, a farmland water-saving control model is constructed based on the characteristics of farmland water demand patterns, including:

[0131] S310. Based on the characteristics of farmland water demand patterns, determine the upper and lower limits of irrigation water injection for the target farmland;

[0132] S320. Construct a multi-objective function, which includes a function to minimize irrigation water injection, a function to minimize irrigation cost, and a function to maximize crop yield. Among these, the function to minimize irrigation water injection is the primary objective function, while the functions to minimize irrigation cost and maximize crop yield are secondary objective functions.

[0133] S330. The upper limit of irrigation water injection and the lower limit of irrigation water injection are respectively used as the first objective constraint and the second objective constraint of the objective function for minimizing irrigation water injection volume.

[0134] S340. Treat the secondary objective function as the third objective constraint of the primary objective function;

[0135] S350. Combining the first objective constraint, the second objective constraint, the third objective constraint, and the multi-objective function, a farmland water-saving control model is constructed.

[0136] By analyzing the water requirement patterns of farmland, the upper and lower limits of irrigation water injection for the target farmland are determined. In this embodiment, the upper limit of irrigation water injection refers to the level at which soil moisture content reaches or exceeds the specified level during irrigation, at which point the crops will no longer require additional irrigation water. The lower limit of irrigation water injection refers to the level at which soil moisture content drops during irrigation, at which point the crops will begin to suffer from drought stress and require immediate irrigation to replenish water. Specifically, firstly, it is necessary to understand the water requirement patterns of the crops planted in the target farmland, including water requirements at different growth stages and water-sensitive periods, which can be obtained by consulting relevant literature. Subsequently, the soil moisture retention capacity of the target farmland needs to be considered, including soil texture, structure, and water retention capacity, as soil moisture retention capacity affects the soil's ability to absorb, store, and release water, thereby affecting the water supply to crops. Climatic conditions are also an important factor in determining the upper and lower limits of irrigation water injection. Climatic factors such as precipitation, temperature, and wind speed will affect crop transpiration, soil moisture evaporation, and crop water requirements. Finally, based on the determination of crop water requirements, soil moisture retention capacity, and consideration of climatic conditions, a comprehensive decision can be made regarding the upper and lower limits of irrigation water injection for the target farmland. For example, by obtaining historical information about the target farmland within a preset time period and determining the monthly water requirements patterns, such as the monthly irrigation water injection values, the maximum and minimum values ​​of irrigation water injection within the preset time period can be obtained. The maximum value can be used as the upper limit of irrigation water injection, and the minimum value as the lower limit of irrigation water injection.

[0137] After determining the upper and lower limits of irrigation water injection for the target farmland, a multi-objective function needs to be constructed. This multi-objective function includes minimizing irrigation water injection, minimizing irrigation costs, and maximizing crop yield. In this embodiment, minimizing irrigation water injection is the primary objective function, meaning that among all irrigation schemes, reducing irrigation water usage should be prioritized. Minimizing irrigation costs and maximizing crop yield are secondary objective functions, aiming to increase crop yield and reduce irrigation costs. Specifically, the objective function for minimizing irrigation water injection can be expressed as:

[0138] f1(W) = W + h

[0139] Where f1(W) represents the minimum irrigation water injection; W represents the irrigation water injection; and h represents the real-time soil moisture content.

[0140] The objective function for minimizing irrigation costs can be expressed as:

[0141] f2(C) = kW + b

[0142] Where f2(C) represents minimizing irrigation cost; C represents irrigation cost; k represents the cost coefficient per unit of irrigation water injection; and b represents fixed costs (such as equipment maintenance fees).

[0143] The objective function for maximizing crop yield can be expressed as:

[0144] f3(Y)=-(aW 2 +bW+c)

[0145] Where f3(Y) represents maximizing crop yield; Y represents crop yield; W represents irrigation water volume; a and b represent the correlation coefficients of irrigation water volume, and a<0 (because yield usually increases with the increase of irrigation water volume, but will decrease due to excessive moisture after a certain level); c represents the critical data for crop wilting.

[0146] Subsequently, a multi-objective function is constructed using the weighted sum method. The weighted sum method adds multiple objective functions by assigning different weight values, forming a single objective function. The multi-objective function can be expressed as:

[0147] F(W)=λ1f1(W)+λ2f2(W)+λ3f3(Y(W))

[0148] Wherein, F(W) represents a multi-objective function; λ1, λ2 and λ3 represent non-negative weights; f1(W) represents minimizing irrigation water injection; f3(Y) represents maximizing crop yield; in this embodiment, the non-negative weights can be determined according to the actual situation.

[0149] Next, the upper and lower limits of irrigation water injection are used as the first and second objective constraints of the objective function for minimizing irrigation water injection, respectively. The upper limit of irrigation water injection refers to the maximum allowable irrigation water volume, which is determined based on the water requirements of crops, soil type, climate conditions, and experience in agricultural practice. The first objective constraint can be expressed as:

[0150] W≤W max

[0151] Where W represents the actual irrigation water volume, W max This indicates the upper limit of the irrigation water volume.

[0152] The lower limit of irrigation water supply refers to the amount of irrigation water required to ensure crops receive sufficient moisture for normal growth and development. It is determined based on factors such as the crop's water deficit sensitivity, growth stage, and soil moisture retention capacity. If the irrigation water supply falls below this lower limit, it may lead to reduced crop yields or even crop death. The second objective constraint can be expressed as:

[0153] W≥W min

[0154] Where W represents the actual irrigation water volume, W min This indicates the lower limit of the irrigation water volume.

[0155] After determining the first and second objective constraints, the secondary objective functions are used as the third objective constraints of the primary objective function. In other words, the objective functions for minimizing irrigation costs and maximizing crop yield are used as the third objective constraints. Specifically, the objective functions for minimizing irrigation costs and maximizing crop yield can be transformed into third objective constraints, which can be expressed as follows:

[0156] C(x)≤C max ;Y(x)≥Y min

[0157] Where C(x) represents the irrigation cost function; C max Y(x) represents the maximum acceptable irrigation cost; Y(x) represents the crop yield function; Y min This indicates the minimum acceptable output.

[0158] Another constraint in this embodiment is:

[0159] S+I≥D (to ensure that the soil moisture content after irrigation meets the crop's water requirements);

[0160] S+I≤H (to ensure that the soil moisture content after irrigation does not exceed the farmland water holding capacity);

[0161] Among them, the real-time soil moisture content is S; the farmland water holding capacity is H; the crop water requirement is D; and the minimum irrigation amount is I.

[0162] Another constraint is used to ensure that the soil moisture content after irrigation meets the water requirements of crops without exceeding the farmland water holding capacity.

[0163] Subsequently, combining the first, second, and third objective constraints with a multi-objective function, a farmland water-saving control model is constructed. In other words, a multi-objective optimization model is built using the aforementioned constraints and multi-objective function, which characterizes the farmland water-saving control model. Through this model, the operational scheme that minimizes agricultural irrigation is found.

[0164] By constructing a farmland water-saving control model, the optimal irrigation strategy can be determined, guiding agricultural producers to carry out precise irrigation management. It can also optimize the crop growth environment, thereby improving crop yield and quality and increasing farmers' income.

[0165] In one embodiment of this invention, determining the upper limit and lower limit of irrigation water injection for the target farmland includes:

[0166] S401. Obtain the number of drought days and average rainfall for farmland crops within a preset time period;

[0167] S402. Obtain the types of crops planted in the target farmland, and determine the growth water requirement coefficient, crop water requirement and soil water retention of the current crop types in the first preset database.

[0168] S403. The drought impact coefficient is obtained by comparing the average rainfall with the preset daily standard rainfall.

[0169] S404. Multiply the drought impact coefficient by the number of drought days for crops to obtain the drought impact index;

[0170] S405. Calculate the relative humidity index using a preset relative humidity index formula based on crop water requirements, soil water retention, and average rainfall.

[0171] S406. Add the relative humidity index and the drought impact index to obtain the comprehensive water deficit index for crops;

[0172] S407. Multiply the comprehensive water deficit index of crops by the growth water requirement coefficient to obtain the lower limit of irrigation water injection;

[0173] S408. Obtain the total irrigated area and total available irrigation water of the target farmland;

[0174] S409. Calculate the available water volume per unit area using the total available irrigation water volume and the total irrigated farmland area;

[0175] S410. The higher of the available water per unit area and the water requirement of crops shall be used as the upper limit of irrigation water supply for the target farmland.

[0176] First, obtain the number of drought days and average rainfall for crops in the target field within a preset time period. This can be done by accessing the official website of the local meteorological department, or by collecting daily rainfall data for the target area within the preset time period. Then, calculate the average of these data to obtain the average rainfall. Next, determine the types of crops planted in the target farmland. This can be done through on-site investigation of the target farmland to identify the types of crops planted.

[0177] After determining the current crop type, the water requirement coefficient, crop water requirement, and soil water retention capacity of the current crop type are determined in a first preset database. In this embodiment, the water requirement coefficient of the crop type refers to the degree of water demand of the crop at different growth stages and is one of the key factors in determining the minimum water consumption for farmland irrigation; the crop water requirement refers to the total amount of water required by the crop during its growth; and the soil water retention capacity refers to the amount of water that the soil can hold. That is, the corresponding water requirement coefficient is searched in the first preset database based on the crop type planted in the target farmland. And the crop water requirement and soil water retention capacity are determined in the first preset database based on the crop type planted in the target farmland and its water requirement coefficient.

[0178] Secondly, the drought impact coefficient is obtained by comparing the average rainfall with a preset daily standard rainfall. In this embodiment, the preset daily standard rainfall is a pre-defined value used to reflect the region's daily rainfall demand under normal conditions. Then, the following formula is used:

[0179] Drought impact coefficient = Average rainfall / Standard daily rainfall

[0180] The drought impact coefficient is calculated using a formula. If the ratio is less than 1, it indicates that the actual rainfall is lower than the standard rainfall, and there is a risk of drought; the smaller the ratio, the more severe the drought. If the ratio is greater than or equal to 1, it indicates that the actual rainfall meets or exceeds the standard rainfall, and the risk of drought is low or non-existent.

[0181] After obtaining the drought impact coefficient, it is multiplied by the number of drought days for crops to obtain the drought impact index. In this embodiment, the drought impact index is a comprehensive quantitative indicator used to assess the overall impact of drought on crop growth and yield. By multiplying the drought impact coefficient (a quantitative indicator reflecting the degree of drought) by the number of drought days for crops (a quantitative indicator reflecting the duration of drought), a comprehensive value is obtained, thus more comprehensively reflecting the impact of drought on crops. In other words, the drought impact index is calculated using the following formula:

[0182] Drought Impact Index = Drought Impact Coefficient × Number of Drought Days for Crops

[0183] The drought impact index is obtained by multiplying the drought impact coefficient by the number of drought days for crops, which can reflect the overall impact of drought on crops.

[0184] Next, the relative humidity index is calculated using a preset formula based on crop water requirement, soil water retention capacity, and average rainfall. In this embodiment, the relative humidity index is an indicator reflecting the relationship between soil moisture status and crop water requirement, and can be obtained by combining rainfall, crop water requirement, and soil water retention capacity. Specifically, firstly, the crop water requirement is determined based on factors such as crop growth stage, soil type, and climate conditions. This can be obtained by consulting relevant literature, using crop water requirement models, or conducting field monitoring. Soil water retention capacity refers to the maximum amount of water that the soil can hold, and can be obtained from a first preset database. The relative humidity index is calculated using the following formula based on crop water requirement, soil water retention capacity, and average rainfall:

[0185] Relative humidity index = (average rainfall - crop water requirement + soil water retention capacity) / soil water retention capacity

[0186] The relative humidity index and the drought impact index are added together to obtain the comprehensive crop water deficit index. In this embodiment, the comprehensive crop water deficit index is a comprehensive quantitative indicator used to comprehensively assess the impact of water deficit on crops within a specific time period. The index combines the relative humidity index (reflecting the soil moisture balance) and the drought impact index (reflecting the overall impact of drought on crops), and the two are added together using a specific calculation method to obtain a comprehensive value. That is, the comprehensive crop water deficit index is obtained by adding the relative humidity index and the drought impact index. For example, if the average rainfall R = 50 mm in a certain period, the preset daily standard rainfall R1 = 100 mm, the crop water requirement = 40 mm, and the soil water retention capacity = 30 mm, then the drought impact index is calculated.

[0187] Drought impact coefficient K = 0.5; Number of drought days for crops D = 10 days;

[0188] Then calculate the drought impact index:

[0189] Drought impact index = 0.5 × 10 = 5;

[0190] Next, calculate the relative humidity index:

[0191] Relative humidity index = (50mm - 40mm + 30mm) / 30mm ≈ 1.33;

[0192] Finally, calculate the comprehensive index of crop water deficit:

[0193] The comprehensive water deficit index for crops = 1.33 + 5 = 6.33;

[0194] Therefore, the comprehensive index of crop water deficit is 6.33, which fully reflects the water deficit status of crops in a specific period of time.

[0195] After obtaining the comprehensive water deficit index for crops, the index is multiplied by the growth water requirement coefficient to arrive at the lower limit of irrigation. In this embodiment, the growth water requirement coefficient refers to the coefficient of water demand of crops at different growth stages. Different crops and different growth stages have different water requirements. In other words, the process of multiplying the comprehensive water deficit index for crops by the growth water requirement coefficient to obtain the lower limit of irrigation is actually determining a reasonable irrigation amount based on a comprehensive consideration of the current water status and growth needs of the crops. This can more accurately reflect the actual water needs of crops and improve the precision and efficiency of irrigation. If the comprehensive water deficit index for crops is high, it indicates that the current water deficit of crops is severe, and the irrigation amount needs to be increased; similarly, if the growth water requirement coefficient is high, it indicates that the current growth stage of crops has a greater water demand, and the irrigation amount also needs to be increased. By multiplying to obtain the lower limit of irrigation, it can be ensured that both the water deficit and growth needs of crops are fully considered and met.

[0196] To determine the upper limit of irrigation water supply for the target farmland, firstly, obtain the total irrigated area and the total available irrigation water volume of the target farmland. This can be done by consulting official statistics, accessing the statistics section of the official website, and finding information on the irrigated area and the total available irrigation water volume.

[0197] Subsequently, the available water volume per unit area is calculated using the total available irrigation water volume and the total irrigated farmland area. In other words, the total available irrigation water volume is evenly distributed across each unit of farmland area, thus obtaining the water available per unit area. The higher of the available water volume per unit area and the crop's water requirement is used as the upper limit for irrigation of the target farmland. That is, by comparing the available water volume per unit area with the crop's water requirement, the higher of the two values ​​is set as the upper limit for irrigation of the target farmland. If the upper limit is set at the higher of the two values, it ensures that the crops receive sufficient water during their growth to meet their physiological needs and development. If the available water volume per unit area is higher than the crop's water requirement, setting the upper limit as the available water volume may lead to unnecessary waste of water resources. Therefore, choosing the higher of the two values ​​as the upper limit can avoid this situation to some extent.

[0198] By determining the upper and lower limits of irrigation water injection for target farmland, it is possible to ensure that farmland receives adequate water when needed, avoiding over-irrigation or under-irrigation, thereby improving the efficiency of irrigation water use. It can also achieve multiple effects such as precision irrigation management, promoting the sustainable use of water resources, and improving agricultural production efficiency, which helps to improve farmland water use efficiency and ensure crop growth and yield.

[0199] In one embodiment of this invention, crop information includes crop type and crop growth stage. Based on the crop information, the water requirement area of ​​the target farmland is divided, including:

[0200] S510. Determine the crop coefficients corresponding to crop types and crop growth stages in the first preset database. The crop coefficients are used to characterize the ratio between the actual water demand of crops and potential evapotranspiration at different growth stages.

[0201] S520: Obtain current environmental and climate parameters;

[0202] S530. Using environmental climate parameters and the Penman-Montes formula, the reference crop transpiration rate is obtained.

[0203] S540. Multiply the reference crop transpiration rate by the crop coefficient to obtain the actual water requirement of the crop.

[0204] S550. Based on the actual water requirements of crops, the target farmland is divided into high water requirement areas, medium water requirement areas, and low water requirement areas.

[0205] First, crop coefficients corresponding to crop types and growth stages are determined in a first preset database. These crop coefficients characterize the ratio between the actual water requirement and potential evapotranspiration of a crop at different growth stages. In this embodiment, the crop coefficient is a parameter representing the degree of water use by the crop, describing the ratio of water requirement to potential evapotranspiration at different developmental stages. That is, by querying the crop types in the first preset database, the crop coefficients corresponding to the crop types and growth stages are determined. Since different crops have different water requirements, it is necessary to query the corresponding crop coefficient based on the crop type. Furthermore, the water requirement of crops changes at different growth stages, so it is necessary to query the corresponding crop coefficient based on the crop's growth stage.

[0206] Secondly, the current environmental climate parameters are obtained. In this embodiment, these parameters can include net radiation, soil heat flux, wet / dry constant, average temperature, wind speed, saturated vapor pressure, and actual vapor pressure. These parameters can be obtained from databases and official meteorological websites. Subsequently, using these environmental climate parameters, the Penman-Montes formula is employed to obtain the reference crop evapotranspiration. The Penman-Montes formula is a widely used formula for calculating reference crop evapotranspiration. Reference crop evapotranspiration refers to the evapotranspiration of a specific reference crop under ideal conditions. The Penman-Montes formula is shown below:

[0207]

[0208] Where ET0 is the reference crop evapotranspiration; Δ is the slope of the saturated vapor pressure curve; R nNet radiation; G is soil heat flux; γ is wet / dry surface constant; T is average air temperature; u2 is wind speed at 2 meters; e s e is the saturated vapor pressure; a This is the actual water vapor pressure;

[0209] By substituting multiple environmental and climatic parameters into the Penman-Montes formula, the reference crop transpiration rate is obtained.

[0210] Next, the reference crop transpiration rate is multiplied by the crop coefficient to obtain the actual water requirement of the crop. That is, the reference crop transpiration rate (ET0) is calculated using the Penman-Montes formula based on current environmental climate parameters. The crop coefficient (Kc) is then retrieved or calculated from relevant databases or literature based on the crop type and current growth stage. ET0 is then multiplied by Kc to obtain the actual water requirement of the crop. For example, suppose the ET0 for a certain day has been calculated to be 5 mm / day, and for a certain crop at its current growth stage, its Kc is 0.8.

[0211] Therefore, the actual water requirement ETC of the crop is:

[0212] ETc = 5 mm / day × 0.8 = 4 mm / day

[0213] This indicates that under these environmental conditions, the actual daily water requirement for this crop is 4 millimeters of water depth.

[0214] After obtaining the actual water requirements of crops, the target farmland is divided into high-water-requirement, medium-water-requirement, and low-water-requirement areas. In other words, statistical analysis of the actual crop water requirements data is used to understand the overall distribution and trends. Based on the crop's water demand characteristics and the actual conditions of the farmland, a reasonable water requirement zoning is established, dividing the farmland into high-water-requirement, medium-water-requirement, and low-water-requirement areas. High-water-requirement areas indicate areas where irrigation water supply should be prioritized; medium-water-requirement areas indicate areas where irrigation time and amount should be rationally arranged based on the actual crop water requirements and soil moisture; and low-water-requirement areas indicate areas where irrigation frequency and amount can be appropriately reduced to avoid water waste caused by over-irrigation.

[0215] By dividing target farmland into water-demand zones, precise irrigation can be implemented based on the actual needs of crops in different areas, avoiding over-irrigation or under-irrigation and thus improving irrigation efficiency. It also allows for the optimization of irrigation strategies, reducing water consumption, mitigating the negative environmental impact of agriculture, and contributing to sustainable agricultural development.

[0216] In one embodiment of this example, based on the farmland water-saving control model and the soil moisture parameters of each water-demand area, the expected irrigation values ​​for each water-demand area are obtained, including:

[0217] S610. Based on the soil moisture parameters of each water-demand area, determine the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area.

[0218] S620. Input the real-time soil moisture content, farmland water holding capacity and crop wilting threshold data of each water-demand area into the farmland water-saving control model to obtain the expected irrigation values ​​for each water-demand area.

[0219] First, based on the soil moisture parameters of each water-demand area, the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each area are determined. In this embodiment, the crop wilting threshold data refers to the critical water content at which crops begin to show wilting symptoms when soil moisture is insufficient to a certain extent. In other words, by regularly monitoring and comprehensively analyzing the soil moisture parameters of each water-demand area, the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data can be determined. Another implementation method for determining the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area in this embodiment is to acquire the real-time soil moisture content of each area using a soil moisture sensor; farmland water holding capacity can be measured by simulating different soil moisture conditions to measure the soil's ability to retain moisture. Crop wilting threshold data can be determined by observing changes in crop physiological indicators (such as leaf water potential and stomatal conductance) in conjunction with soil moisture content.

[0220] Subsequently, the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area are input into the farmland water-saving control model to obtain the expected irrigation values ​​for each water-demand area. In this embodiment, the expected irrigation values ​​refer to the amount of water needed for irrigation in each water-demand area within a specific time period, calculated based on the farmland water-saving control model. In other words, by inputting key parameters such as real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data, combined with information such as crop growth stage, soil type, and climate conditions, the expected irrigation values ​​for each water-demand area can be obtained through the farmland water-saving control model.

[0221] By obtaining the projected irrigation values ​​for each water-demand area, irrigation plans can be dynamically adjusted based on real-time data to achieve precision irrigation. This not only improves irrigation efficiency and reduces water waste, but also promotes healthy crop growth and increases yield and quality.

[0222] In one embodiment of this invention, the method further includes:

[0223] S710. For any water-required area, if the real-time soil moisture content is less than the critical data for crop wilting, then it is in emergency irrigation mode, and all preset smart irrigation valves in the water-required area are opened.

[0224] S720. If the real-time soil moisture content is greater than or equal to the crop wilting critical data and less than or equal to the farmland water holding capacity, then it is in the on-demand irrigation state. Based on the expected irrigation value of each water demand area, the smart irrigation water valve in the water demand area is opened.

[0225] S730 If the real-time soil moisture content is greater than or equal to the farmland water holding capacity, then the irrigation is turned off, and all preset smart irrigation valves in the water-required area are closed.

[0226] For any water-demand area, if the real-time soil moisture content is lower than the crop wilting threshold, it is considered an emergency irrigation state. All preset smart irrigation valves within the water-demand area will be activated. In other words, when the real-time soil moisture content is below the crop wilting threshold, it means the crop is in a state of severe water shortage. If irrigation is not carried out in time, it may lead to stunted growth or even death. Therefore, this area is considered to be in an emergency irrigation state. Once an area is determined to be in an emergency irrigation state, immediate irrigation measures are required. In this case, all preset smart irrigation valves within the area can be activated. A smart irrigation valve is an irrigation device that can automatically open or close according to preset conditions. It can achieve remote control and precise irrigation through wireless communication with a cloud platform.

[0227] Subsequently, if the real-time soil moisture content is greater than or equal to the crop wilting threshold but less than or equal to the farmland water holding capacity, it enters the on-demand irrigation state. Based on the projected irrigation values ​​for each water-demand area, the smart irrigation valves in that area are activated. In other words, when the real-time soil moisture content is greater than or equal to the crop wilting threshold, it means the soil moisture is sufficient to meet the basic needs of the crop, and the crop will not show wilting symptoms due to water shortage. When the real-time soil moisture content is less than or equal to the farmland water holding capacity, it means the soil has not yet reached its maximum water retention capacity and still has room to absorb and store more water. When the real-time soil moisture content is between the crop wilting threshold and the farmland water holding capacity, the farmland is in on-demand irrigation mode. This means that although the crop will not be immediately damaged by water shortage, depending on the crop's growth stage, climate conditions, and projected evapotranspiration, the farmland may still require appropriate irrigation to maintain optimal soil moisture. Based on the projected irrigation values, the smart irrigation valves in the water-demand area can be remotely controlled to irrigate according to the predetermined irrigation plan and amount.

[0228] If the real-time soil moisture content is greater than or equal to the farmland water holding capacity, irrigation is shut off, and all preset smart irrigation valves in the water-required area are closed. This means that when the real-time soil moisture content reaches or exceeds the farmland water holding capacity, the soil has already absorbed water within its maximum water-holding capacity range. Continuing irrigation at this point will result in water overflow and waste. When the real-time soil moisture content is greater than or equal to the farmland water holding capacity, the farmland is in a shut-off irrigation state. This means that the soil already contains enough moisture to meet the crop's needs, and the soil's water retention capacity has reached its limit, unable to absorb any more water. If irrigation continues at this time, the water will not be effectively absorbed by the soil but will flow out of the farmland, resulting in water waste. In the shut-off irrigation state, all preset smart irrigation valves in the water-required area should be closed. Smart irrigation systems are typically equipped with sensors and controllers that can monitor soil moisture conditions in real time and automatically adjust the irrigation plan according to preset conditions. When the real-time soil moisture content reaches or exceeds the farmland water holding capacity, the smart irrigation system should automatically close the irrigation valves and stop irrigation operations.

[0229] By determining the irrigation status of water-demanding areas, irrigation volume and timing can be controlled more precisely, thereby optimizing water resource utilization, reducing water waste during irrigation, and improving irrigation water use efficiency. It can also meet the water needs of crops at different growth stages, contributing to improved crop yield and quality.

[0230] This application provides a cloud platform. Figure 2 This application provides a schematic diagram of the structure of a cloud platform according to an embodiment of the present application. Figure 2 As shown, water-saving control methods applied to agricultural irrigation include:

[0231] 01 Geographic Data Management Module, used to determine the geographical location of the target farmland;

[0232] 02 Data acquisition module, used to determine the historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland in the first preset database;

[0233] The 03 pattern characteristic determination module is used to determine the farmland water demand pattern characteristics of the target farmland based on historical rainfall and historical soil moisture parameters;

[0234] 04 Model building module, used to build a farmland water-saving control model based on the characteristics of farmland water demand patterns;

[0235] 05 Information Acquisition Module, used to acquire crop information of the target farmland;

[0236] 06. The region division module is used to divide the water requirement areas of the target farmland based on crop information;

[0237] 07 Data Acquisition Module: This module is used to collect soil moisture parameters for each water-required area.

[0238] The 08 Irrigation Value Determination Module is used to obtain the expected irrigation values ​​for each water-demand area based on the farmland water-saving control model and the soil moisture parameters of each water-demand area.

[0239] 09 Real-time irrigation data acquisition module, used to acquire real-time irrigation data for each water-demand area;

[0240] The 10 real-time control module is used to adjust the preset smart irrigation valves in each water demand area in real time based on the expected irrigation values ​​and the real-time irrigation values.

[0241] This application also provides an electronic device, including:

[0242] The memory is configured to store instructions; and

[0243] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned water-saving control method for agricultural irrigation.

[0244] 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.

[0245] 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, as well as 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 flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0246] 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.

[0247] 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.

[0248] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0249] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0250] 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 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.

[0251] 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. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0252] 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 water-saving control method for agricultural irrigation, characterized in that, Applied to a cloud platform, the method includes: Obtain the geographical location of the target farmland; The historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland are determined in the first preset database. The historical soil moisture parameters include historical soil moisture data, historical soil density data and historical soil pH data. Based on the historical rainfall and historical soil moisture parameters, the characteristics of the farmland water demand pattern of the target farmland are determined, including: Using the historical soil moisture data and a preset soil moisture content formula, the original soil moisture content of the target farmland is calculated. Historical farmland soil moisture content and historical artificial irrigation water volume are obtained from the second preset database; Using the preset Pearson correlation coefficient formula, the correlation coefficient between the historical farmland soil moisture content and the historical soil pH data is calculated to obtain the soil pH influencing factor; The soil pH influencing factor, the original soil moisture content of the farmland, and the historical soil density data are fitted with parameters to obtain the soil saturated moisture content pressure time-varying coefficient. The soil saturated moisture content pressure time-varying coefficient is used to characterize the time-varying nonlinear characteristic parameter of farmland soil under vertical pressure. The cumulative irrigation water volume is determined by the historical rainfall and the historical artificial irrigation water injection volume; By fitting the parameters of the cumulative irrigation flow, the historical artificial irrigation water injection, and the time-varying coefficient of soil saturated moisture content pressure, the characteristic coefficient of farmland water demand pattern is obtained. In a pre-defined database of farmland water demand patterns, the time-varying nonlinear characteristics of farmland irrigation water corresponding to the farmland water demand pattern characteristic coefficients of the target farmland are determined. The time-varying nonlinear characteristics of farmland irrigation water are used to characterize the farmland water demand pattern characteristics. Based on the characteristics of farmland water demand patterns, a farmland water-saving control model is constructed. Obtain crop information for the target farmland; Based on the crop information, the water requirement areas of the target farmland are divided; Real-time collection of soil moisture parameters for each water-required area; Based on the farmland water-saving control model and the soil moisture parameters of each water-demand area, the expected irrigation values ​​for each water-demand area are obtained; Obtain real-time irrigation data for each water-demand area; Based on the predicted irrigation values ​​and the real-time irrigation values, water valve control commands are generated to control the preset smart irrigation water valves in each water-demand area in real time.

2. The method according to claim 1, characterized in that, The step of constructing a farmland water-saving control model based on the characteristics of farmland water demand patterns includes: Based on the characteristics of farmland water demand patterns, the upper and lower limits of irrigation water injection for the target farmland are determined. Construct a multi-objective function, which includes a function to minimize irrigation water injection, a function to minimize irrigation cost, and a function to maximize crop yield. The function to minimize irrigation water injection is the primary objective function, and the functions to minimize irrigation cost and maximize crop yield are secondary objective functions. The upper limit of irrigation water injection and the lower limit of irrigation water injection are respectively used as the first objective constraint and the second objective constraint of the objective function for minimizing irrigation water injection volume; The secondary objective function is used as the third objective constraint condition of the primary objective function; A farmland water-saving control model is constructed by combining the first objective constraint, the second objective constraint, the third objective constraint, and the multi-objective function.

3. The method according to claim 2, characterized in that, Determining the upper and lower limits of irrigation water injection for the target farmland includes: Obtain the number of drought days and average rainfall for farmland crops within a preset time period; Obtain the types of crops planted in the target farmland, and determine the growth water requirement coefficient, crop water requirement, and soil water retention of the current crop types in the first preset database; The drought impact coefficient is obtained by comparing the average rainfall with the preset daily standard rainfall. Multiplying the drought impact coefficient by the number of drought days for crops yields the drought impact index; The relative humidity index is calculated using a preset relative humidity index formula based on the crop water requirement, the soil water retention capacity, and the average rainfall. The relative humidity index and the drought impact index are added together to obtain the comprehensive water deficit index for crops; The lower limit of irrigation water injection is obtained by multiplying the comprehensive index of crop water deficit with the growth water requirement coefficient. Obtain the total irrigated area and total available irrigation water of the target farmland; The available water volume per unit area is calculated using the total available irrigation water volume and the total irrigated farmland area. The higher of the available water per unit area and the water requirement of the crops is taken as the upper limit of irrigation water supply for the target farmland.

4. The method according to claim 1, characterized in that, The crop information includes crop type and crop growth stage. The step of dividing the target farmland into water requirement zones based on the crop information includes: In a first preset database, crop coefficients corresponding to the crop type and the crop growth stage are determined. The crop coefficients are used to characterize the ratio between the actual water requirement of the crop and the potential evapotranspiration at different growth stages. Obtain current environmental and climate parameters; Using the aforementioned environmental and climate parameters, the reference crop transpiration rate is obtained through the Penman-Montes formula. Multiply the reference crop transpiration rate by the crop coefficient to obtain the actual water requirement of the crop; Based on the actual water requirements of the crops, the target farmland is divided into high water requirement areas, medium water requirement areas, and low water requirement areas.

5. The method according to claim 1, characterized in that, The method for obtaining the predicted irrigation values ​​for each water-demand area based on the farmland water-saving control model and the soil moisture parameters of each water-demand area includes: Based on the soil moisture parameters of each water-demand area, determine the real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data for each water-demand area; The real-time soil moisture content, farmland water holding capacity, and crop wilting threshold data of each water-demand area are input into the farmland water-saving control model to obtain the expected irrigation values ​​for each water-demand area.

6. The method according to claim 5, characterized in that, The method further includes: For any of the water-required areas, if the real-time soil moisture content is less than the crop wilting critical data, then it is an emergency irrigation state, and all preset smart irrigation valves in the water-required area are opened. If the real-time soil moisture content is greater than or equal to the crop wilting critical data and less than or equal to the farmland water holding capacity, then it is in the on-demand irrigation state, and the smart irrigation water valve in the water demand area is opened according to the expected irrigation value of each water demand area. If the real-time soil moisture content is greater than or equal to the farmland water holding capacity, then the irrigation is turned off, and all preset smart irrigation valves in the water-required area are closed.

7. A cloud platform, characterized in that, The water-saving control method for agricultural irrigation according to any one of claims 1-6 includes: The geographic data management module is used to determine the geographic location of the target farmland. The data acquisition module is used to determine the historical rainfall corresponding to the geographical location of the target farmland and the historical soil moisture parameters of the target farmland in the first preset database. The pattern characteristic determination module is used to determine the farmland water demand pattern characteristics of the target farmland based on the historical rainfall and the historical soil moisture parameters; The model building module is used to build a farmland water-saving control model based on the characteristics of farmland water demand patterns. An information acquisition module is used to acquire crop information of the target farmland; The region division module is used to divide the water requirement area of ​​the target farmland based on the crop information; The data acquisition module is used to collect soil moisture parameters for each of the water-required areas. The irrigation value determination module is used to obtain the expected irrigation value for each water-demand area based on the farmland water-saving control model and the soil moisture parameters of each water-demand area; The real-time irrigation data acquisition module is used to acquire real-time irrigation data for each water-demand area. The real-time control module is used to adjust the preset smart irrigation valves in each water demand area in real time according to the expected irrigation value and the real-time irrigation value.

8. An electronic device, characterized in that, Deploying the cloud platform as described in claim 7, comprising: The memory is configured to store instructions; and The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the water-saving control method for agricultural irrigation according to any one of claims 1 to 6.

Images