Wheat automatic irrigation control system and method based on Internet of Things

Abstract

The invention relates to the technical field of irrigation control, in particular to an automatic wheat irrigation control system and method based on the Internet of Things, and the method comprises the steps: obtaining wheat canopy parameters of a plurality of preset collection points in a target area, the water content distribution conditions of soil at different depths, the growth conditions of wheat roots, and environment parameters in a future preset time period; determining an irrigation trend characterization value based on the wheat canopy parameters of the first preset acquisition points and the environmental parameters in the future preset time period; and determining an irrigation demand mode of the target area based on the irrigation trend characterization value, the irrigation demand mode including a waiting irrigation mode, a weak demand irrigation mode and a strong demand irrigation mode. According to the invention, the irrigation mode can be dynamically adjusted according to wheat growth requirements, and the accuracy of wheat irrigation process control is improved.

Description

Technical Field

[0001] This invention relates to the field of irrigation control technology, and in particular to an automatic irrigation control system and method for wheat based on the Internet of Things. Background Technology

[0002] With the intensification of global climate change and the increasing scarcity of water resources, agricultural irrigation faces severe challenges. As one of the world's most important food crops, wheat production is not only directly related to food security but also closely linked to farmers' livelihoods.

[0003] In recent years, with the rapid development of smart agriculture technology, irrigation using advanced sensors, the Internet of Things, and other technologies has gradually become a research hotspot. For example, soil moisture sensors can monitor soil moisture in real time, allowing workers to adjust irrigation timing and volume based on practical experience. However, this method is susceptible to the influence of workers' subjective judgment, easily leading to water waste and low irrigation efficiency, negatively impacting wheat growth and yield. Furthermore, some systems trigger irrigation solely based on preset thresholds, neglecting crop growth stages, environmental changes (such as evaporation and rainfall probability), and resource optimization, lacking adaptation to the specific growth needs of wheat.

[0004] Chinese Patent Publication No. CN120069412A discloses a smart water-saving irrigation method for wheat, comprising: acquiring visible light images and hyperspectral images of wheat at various growth stages; selecting an image of a specific band from the hyperspectral image as an enhanced image; fusing the enhanced image and the visible light image to form a fused image; labeling the water requirement of wheat based on the fused image of wheat at various growth stages to form training samples; inputting the training samples into a neural network for training to obtain a wheat water requirement prediction model; using the wheat water requirement prediction model to calculate the water requirement of wheat in a target wheat field, and irrigating the target wheat field according to the water requirement.

[0005] The existing technology has the following problems: predicting the water requirement of wheat by only acquiring image data of wheat at various growth stages is difficult to guarantee that the water requirement will accurately meet the growth needs of wheat, and the accuracy is not high. Summary of the Invention

[0006] To address this issue, the present invention provides an IoT-based automatic irrigation control system and method for wheat, which overcomes the problem in the prior art that predicts the water requirement of wheat by only acquiring image data of wheat at various growth stages, making it difficult to ensure that the water requirement accurately meets the growth needs of wheat and resulting in low accuracy.

[0007] To achieve the above objectives, in one aspect, the present invention provides an automatic irrigation control method for wheat based on the Internet of Things, comprising: The parameters of wheat canopy, soil moisture distribution at different depths, wheat root growth, and environmental parameters within a future preset time period are obtained from several preset collection points within the target area. The preset collection points include a first preset collection point and a second preset collection point. The irrigation trend characterization value is determined based on the wheat canopy parameters of each of the first preset collection points and the environmental parameters within a future preset time period. The irrigation demand pattern of the target area is determined based on the irrigation trend characterization value, wherein the irrigation demand pattern includes waiting irrigation pattern, weak demand irrigation pattern and strong demand irrigation pattern. For the waiting irrigation method, the waiting irrigation time is determined based on environmental parameters within a preset future time period, and irrigation reminder information is issued accordingly; For low-demand irrigation methods, the second soil water demand characterization value is determined based on the soil water content distribution at different depths of each second preset collection point, so as to determine whether the irrigation method is intermittent irrigation or supplementary irrigation. For high-demand irrigation methods, wheat water demand characterization values ​​are determined based on wheat canopy parameters and wheat root growth at each of the second preset collection points, and a first soil water demand characterization value is determined based on soil moisture distribution at different depths at each of the preset collection points, in order to determine target irrigation parameters, wherein the irrigation parameters include irrigation rate and irrigation time.

[0008] Further, determine irrigation trend characterization values, including: The wheat canopy water shortage index is determined based on the wheat canopy parameters at each of the first preset collection points; The water replenishment index is determined based on environmental parameters within a preset future time period. The irrigation trend characterization value is determined based on the wheat canopy water shortage index and the water replenishment index.

[0009] Furthermore, the irrigation demand method for the target area is determined based on the comparison results between the irrigation trend characterization value and the first preset characterization value and the second preset characterization value.

[0010] Furthermore, the waiting time for irrigation is determined, including: The waiting adjustment coefficient is determined based on the comparison result between the moisture replenishment index and the preset replenishment index; The waiting irrigation time is determined based on the waiting adjustment coefficient and the preset irrigation time.

[0011] Further, the second soil water demand characterization value was determined, including: The second abnormal water shortage index corresponding to each second preset sampling point is determined based on the soil moisture content distribution at different depths of each second preset sampling point. The second soil water demand characterization value is determined based on the second abnormal water shortage index corresponding to each of the second preset collection points.

[0012] Furthermore, the irrigation method is determined based on the comparison between the second soil water demand characterization value and the preset water demand characterization value.

[0013] Furthermore, the water requirement characterization values ​​for wheat were determined, including: The wheat growth index is determined based on the wheat canopy parameters at each of the second preset collection points; The root growth index is determined based on the wheat root growth at each of the second preset collection points; The wheat water requirement characterization value is determined based on the wheat growth index and the root growth index.

[0014] Further, the first soil water requirement characterization value is determined, including: Based on the soil moisture content distribution at different depths of each of the first preset collection points, the first abnormal water shortage index corresponding to each of the first preset collection points is determined. The first soil water demand characterization value is determined based on each of the first abnormal water shortage index and each of the second abnormal water shortage index.

[0015] Further, the target irrigation parameters are determined, including: Irrigation adjustment coefficients are determined based on the wheat water requirement characterization values ​​and the second soil water requirement characterization values. The target irrigation parameters are determined based on the irrigation adjustment coefficient and the preset irrigation parameters.

[0016] On the other hand, the present invention also provides an automatic irrigation control system for wheat, comprising: The data acquisition module is used to acquire wheat canopy parameters, soil moisture distribution at different depths, wheat root growth, and environmental parameters within a future preset time period from several preset collection points within the target area. The preset collection points include a first preset collection point and a second preset collection point. The data analysis module, which is connected to the data acquisition module, is used to determine the irrigation trend characterization value based on the wheat canopy parameters of each of the first preset collection points and the environmental parameters within a future preset time period. An irrigation control module, which is connected to the data acquisition module and the data analysis module respectively, is used to determine the irrigation demand mode of the target area based on the irrigation trend characterization value, wherein the irrigation demand mode includes waiting irrigation mode, weak demand irrigation mode and strong demand irrigation mode. For the waiting irrigation method, the waiting irrigation time is determined based on environmental parameters within a preset future time period, and irrigation reminder information is issued accordingly; For low-demand irrigation methods, the second soil water demand characterization value is determined based on the soil water content distribution at different depths of each second preset collection point, so as to determine whether the irrigation method is intermittent irrigation or supplementary irrigation. For high-demand irrigation methods, wheat water demand characterization values ​​are determined based on wheat canopy parameters and wheat root growth at each of the second preset collection points, and a first soil water demand characterization value is determined based on soil moisture distribution at different depths at each of the preset collection points, in order to determine target irrigation parameters, wherein the irrigation parameters include irrigation rate and irrigation time.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: By acquiring wheat canopy parameters, soil moisture distribution at different depths, wheat root growth, and environmental parameters within a predetermined time period from several preset sampling points within a target area, this invention can comprehensively assess the water requirements and growth environment of wheat, providing comprehensive data support for precision irrigation and avoiding the limitations of single-parameter decision-making. By determining irrigation trend characterization values ​​based on the wheat canopy parameters at each preset sampling point and the environmental parameters within a predetermined time period, the water requirement trend of wheat can be predicted in advance, avoiding blindly entering the refined calculation stage and saving computational resources. By determining the irrigation demand mode of the target area based on the irrigation trend characterization values, irrigation demand can be divided into different levels, allowing for hierarchical management according to the actual growth needs of wheat, improving the accuracy and efficiency of the irrigation process.

[0018] Furthermore, this invention determines the wheat canopy water shortage index based on wheat canopy parameters and, relying on the regional deployment of a first preset collection point, achieves a comprehensive characterization of the canopy water shortage state. This allows for a preliminary assessment of the degree of water shortage based on wheat growth patterns, improving irrigation analysis efficiency. By determining the water replenishment index based on future environmental parameters, the potential for natural water replenishment and loss is quantified, avoiding ineffective irrigation due to the failure to consider natural rainfall. By comprehensively considering both the wheat canopy water shortage index and the water replenishment index to determine the irrigation trend characterization value, the accuracy and efficiency of wheat irrigation processes are improved.

[0019] Furthermore, this invention determines the waiting adjustment coefficient based on the comparison between the water replenishment index and the preset replenishment index, which can improve analysis efficiency and determine the waiting irrigation time. This enables precise control of irrigation time, avoids the irrationality of fixed irrigation time, and improves irrigation efficiency.

[0020] Furthermore, this invention determines the second abnormal water shortage index corresponding to each second preset collection point by analyzing and determining the second soil water demand characterization value, clarifying the actual water shortage location of the wheat root water absorption layer corresponding to the second preset collection point, achieving comprehensiveness in judging wheat soil demand, and achieving precision in the irrigation process.

[0021] Furthermore, this invention determines the wheat growth index based on the wheat canopy parameters at each second preset sampling point, which can comprehensively assess the growth status of wheat. It also determines the root growth index based on the wheat root growth at each second preset sampling point, which can comprehensively assess the health status and growth vitality of wheat roots. By comprehensively considering the wheat growth index and the root growth index, the water requirement characterization value of wheat is determined, ensuring the flexibility and adaptability of irrigation decisions and achieving precision irrigation.

[0022] Furthermore, by combining the first abnormal water shortage index corresponding to the first preset sampling point and the second abnormal water shortage index corresponding to the second preset sampling point, the present invention comprehensively determines the first soil water demand characterization value, which can accurately analyze the distribution of soil moisture content in the target area. Thus, irrigation strategies can be adjusted in a targeted manner to improve the accuracy of wheat irrigation.

[0023] Furthermore, this invention determines the irrigation adjustment coefficient based on wheat water requirement characterization value and second soil water requirement characterization value, thereby more accurately determining irrigation demand and avoiding over-irrigation or under-irrigation. By combining the irrigation adjustment coefficient with preset irrigation parameters, the specific parameters of irrigation can be determined more accurately, ensuring the timeliness and effectiveness of irrigation. Attached Figure Description

[0024] Figure 1 This is a schematic flowchart of an embodiment of the Internet of Things-based automatic irrigation control method for wheat according to the present invention. Figure 2 This is a schematic diagram of the process for determining irrigation trend characterization values ​​in an embodiment of the present invention; Figure 3 This is a logic diagram illustrating how the irrigation demand of a target area is determined in an embodiment of the present invention. Figure 4 This is a structural block diagram of the automatic irrigation control system for wheat according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0026] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0027] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0028] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0029] Please see Figures 1-4 As shown, Figure 1 This is a schematic flowchart of an embodiment of the Internet of Things-based automatic irrigation control method for wheat according to the present invention. Figure 2 This is a schematic diagram of the process for determining irrigation trend characterization values ​​in an embodiment of the present invention; Figure 3 This invention provides a logical decision diagram for determining the irrigation demand of a target area according to an embodiment of the invention; the invention also provides an IoT-based automatic irrigation control method for wheat, comprising: Step S1: Obtain wheat canopy parameters, soil moisture distribution at different depths, wheat root growth, and environmental parameters within a future preset time period from several preset collection points within the target area. The preset collection points include a first preset collection point and a second preset collection point. In implementation, wheat canopy parameters include, but are not limited to, canopy height, canopy temperature, leaf area index (LAI), chlorophyll content, and normalized vegetation index (NVI). Practitioners can set up wheat canopy parameter acquisition devices at various pre-defined collection points. The specific structure of these devices is not limited; for example, image acquisition devices (hyperspectral cameras, multispectral cameras, depth cameras, thermal infrared imaging cameras, etc.) and various detection sensors (infrared temperature sensors, lidar, etc.) can be used. LiDAR or multi-view RGB image technology can be used to generate a three-dimensional canopy model to determine canopy height and retrieve the LAI. A thermal infrared imaging camera can be used to acquire canopy temperature. A leaf area meter or canopy analyzer can be used to retrieve the LAI. Different bands of wheat canopy spectral response information can be acquired, and the chlorophyll content and NVI of the wheat canopy can be obtained through inversion. Alternatively, based on pixel-based fluorescence emission maps, the fluorescence spectrum information reflected by the wheat canopy can be obtained, thereby obtaining the chlorophyll content of the wheat canopy. This is existing technology and will not be elaborated further.

[0030] It is understandable that implementers can set up soil moisture sensors or TDR detectors at each preset sampling point to measure soil moisture content at different depths. There are no restrictions on the specific sampling methods or the specific structure of the equipment; this is existing technology and will not be elaborated further. The detection depth can be set to several groups, for example: surface layer: 0–200 mm, middle layer: 200 mm–400 mm, deep layer: 400 mm–600 mm, and deepest layer: 600 mm–1000 mm.

[0031] It is understandable that implementers can set up root collection devices at each of the second preset collection points to collect data such as wheat root length, root spread, number of branches, and depth of the main water absorption layer in order to construct a wheat root distribution model. The specific structure of the root collection devices is not limited. For example, underground root image acquisition sensors, root radar sensors, root growth monitors, etc. are existing technologies and will not be elaborated further.

[0032] It is understandable that environmental parameters include ambient temperature, humidity, wind speed, and rainfall. Implementers can use IoT terminals to connect to third-party meteorological platforms or set up meteorological sensors to predict environmental parameters within a preset time period. Preferably, the preset time period is set to a range of 8 hours to 12 hours.

[0033] It is understandable that the number of the first and second preset collection points is positively correlated with the area of ​​the target region. The first and second preset collection points are set at intervals. In actual implementation, the target region can be evenly divided into several grid sub-regions, and preset collection points can be set at the center of the grid sub-regions.

[0034] Step S2: Determine the irrigation trend characterization value based on the wheat canopy parameters of each of the first preset collection points and the environmental parameters within the future preset time period; Specifically, in step S2, determining the irrigation trend characterization value includes: Step S21: Determine the wheat canopy water shortage index based on the wheat canopy parameters at each of the first preset collection points; Step S22: Determine the water replenishment index based on environmental parameters within a future preset time period; Step S23: Determine the irrigation trend characterization value based on the wheat canopy water shortage index and the water replenishment index.

[0035] In implementation, the wheat canopy water deficiency index is used to reflect the degree of water deficiency at the physiological level of wheat, with a value ranging from 0 to 1. The higher the value, the more severe the water deficiency and the greater the need for irrigation. The collected wheat canopy parameters are standardized to convert the values ​​of different parameters to the same dimension. For example, the Z-score standardization method can be used: standardized value = the ratio of the difference between the parameter value and the mean to the standard deviation. The wheat canopy water deficiency degree value corresponding to any first preset sampling point can be determined by weighted summation based on the standardized wheat canopy parameters corresponding to the first preset sampling point. Therefore, the wheat canopy water deficiency index QZ for the target area is calculated as follows: QZ = (∑... m j=1 (∑ n i=1 (w i ×MA i,j ))) / m, where j=1,2,…,m; i=1,2,…,n; m is the number of the first preset sampling points, n is the number of wheat canopy parameters, MA i,j w represents the water deficiency value of the wheat canopy corresponding to the j-th first preset sampling point. i The weighting coefficient corresponding to the i-th wheat canopy parameter can be determined based on a finite number of experiments or set based on an expert system according to the wheat's sensitivity to water during its growth period.

[0036] Understandably, the water replenishment index is used to quantitatively assess the water supply capacity of the natural environment within a predetermined future time period. Its value ranges from 0 to 1; a higher value indicates more abundant natural replenishment and less need for irrigation. Standardizing the collected environmental parameters to convert different parameter values ​​to the same dimension is an existing technique and will not be elaborated further. Water Replenishment Index SZ = (∑ h g=1 (u g ×SA g )) / (∑ y x=1 (u x ×SB x Where g = 1, 2, ..., h; x = 1, 2, ..., y; h is the total number of environmental parameters that have a positive impact on water replenishment, such as rainfall and ambient humidity; y is the total number of environmental parameters that have a negative impact on water replenishment, such as ambient temperature and wind speed. g Let u be the weighting coefficient of the g-th environmental parameter that has a positive impact on water replenishment. x The weighting coefficient for the xth environmental parameter that has a negative impact on water replenishment can be determined by the implementers based on a limited number of experiments or set by an expert system based on the sensitivity of wheat to water during its growth period.

[0037] Understandably, the higher the irrigation trend index, the greater the need for irrigation. In practical applications, the ratio of wheat canopy water shortage index to water replenishment index can be used as the irrigation trend index.

[0038] Specifically, this invention determines the wheat canopy water shortage index based on wheat canopy parameters. By leveraging the regional deployment of a first preset sampling point, it achieves a comprehensive characterization of canopy water shortage status, allowing for a preliminary assessment of the degree of water shortage from wheat growth patterns, thus improving irrigation analysis efficiency. Furthermore, by determining the water replenishment index based on future environmental parameters, it quantifies the potential for natural water replenishment and loss, avoiding ineffective irrigation due to neglecting natural rainfall. Finally, by comprehensively considering both the wheat canopy water shortage index and the water replenishment index to determine irrigation trend characterization values, it improves the accuracy and efficiency of wheat irrigation processes.

[0039] Step S3: Determine the irrigation demand mode of the target area based on the irrigation trend characterization value, wherein the irrigation demand mode includes waiting irrigation mode, weak demand irrigation mode and strong demand irrigation mode; Specifically, in step S3, the irrigation demand method for the target area is determined based on the comparison results between the irrigation trend characterization value and the first preset characterization value and the second preset characterization value.

[0040] In implementation, if the irrigation trend indicator value is greater than the first preset indicator value, the irrigation demand mode is determined as a strong demand irrigation mode; if the irrigation trend indicator value is greater than the second preset indicator value and less than or equal to the first preset indicator value, the irrigation demand mode is determined as a weak demand irrigation mode; if the irrigation trend indicator value is less than or equal to the second preset indicator value, the irrigation demand mode is determined as a waiting irrigation mode. The first preset indicator value is greater than the second preset indicator value. The actual implementers can set the first preset indicator value and the second preset indicator value based on the actual situation.

[0041] For the waiting irrigation method, the waiting irrigation time is determined based on environmental parameters within a preset future time period, and irrigation reminder information is issued accordingly; Specifically, in step S3, determining the waiting time for irrigation includes: Step S311: Determine the waiting adjustment coefficient based on the comparison result between the moisture replenishment index and the preset replenishment index; Step S312: Determine the waiting irrigation time based on the waiting adjustment coefficient and the preset irrigation time.

[0042] In implementation, the ratio of the water replenishment index to the preset replenishment index is determined as the waiting adjustment coefficient, and the product of the waiting adjustment coefficient and the preset irrigation time is determined as the waiting irrigation time.

[0043] It is understandable that implementers can set a preset replenishment index based on the actual situation or the average value of the water replenishment index that has passed the qualification test in historical data. Preferably, the preset replenishment index is set to a value range of 0.8 to 0.9. Implementers can set a preset irrigation time based on the actual situation or according to the wheat growth stage based on the expert system. In actual application, if no adjustment is made, the preset irrigation amount of water will be replenished once every preset irrigation time. The preset irrigation amount is to meet the basic needs of wheat growth and can be set based on the actual situation. The supplementary irrigation is carried out by sprinkler irrigation.

[0044] Specifically, this invention determines the waiting adjustment coefficient based on the comparison between the water replenishment index and the preset replenishment index, which can improve analysis efficiency and determine the waiting irrigation time. This enables precise control of irrigation time, avoids the irrationality of fixed irrigation time, and improves irrigation efficiency.

[0045] For low-demand irrigation methods, the second soil water demand characterization value is determined based on the soil water content distribution at different depths of each second preset collection point, so as to determine whether the irrigation method is intermittent irrigation or supplementary irrigation. Specifically, in step S3, determining the second soil water demand characterization value includes: Step S321: Determine the second abnormal water shortage index corresponding to each second preset collection point based on the soil moisture distribution at different depths of each second preset collection point. Step S322: Determine the second soil water demand characterization value based on the second abnormal water shortage index corresponding to each of the second preset collection points.

[0046] In implementation, the second soil water demand characterization value is used to quantitatively assess the degree of soil water shortage conducive to wheat growth at each second preset sampling point. The value ranges from 0 to 1; the smaller the value, the greater the soil water shortage conducive to wheat growth, and the greater the need for irrigation. Using soil moisture content at the same depth as data of the same dimension, the collected soil moisture content is normalized to convert it to the range of 0 to 1. This is existing technology and will not be elaborated further. Therefore, the second abnormal water shortage index EZ corresponding to any second preset sampling point is calculated as follows: EZ = ∑ q p=1 (v p ×ET p ), where p = 1, 2, ..., q; q is the soil depth layer number, v p ET represents the weighting coefficient corresponding to the depth of the p-th soil layer. pFor the normalized soil moisture content corresponding to the p-th soil depth, implementers can set corresponding weight coefficients for each depth based on the proportion of water absorption by wheat roots. Generally, the weight coefficient of the middle layer is greater than that of the deep layer, and the weight coefficients of the surface layer and the deepest layer are the smallest. For example, the weight coefficient of the surface layer is 0.15, the weight coefficient of the middle layer is 0.4, the weight coefficient of the deep layer is 0.3, and the weight coefficient of the deepest layer is 0.15. Alternatively, the weight coefficients corresponding to different soil depths can be set based on the sensitivity of wheat to soil moisture during its growth period using an expert system.

[0047] It is understandable that the average value of the second abnormal water shortage index corresponding to each second preset collection point is used to determine the second soil water demand characterization value.

[0048] Specifically, this invention determines the second abnormal water shortage index corresponding to each second preset collection point by analyzing and determining the second soil water demand characterization value, clarifying the actual water shortage location of the wheat root water absorption layer corresponding to the second preset collection point, achieving comprehensiveness in judging wheat soil demand, and achieving precision in the irrigation process.

[0049] Specifically, in step S3, the irrigation method is determined based on the comparison between the second soil water demand characterization value and the preset water demand characterization value.

[0050] In implementation, if the second soil water demand characteristic value is less than the preset water demand characteristic value, the irrigation method for the weak demand irrigation mode is determined as supplementary irrigation; if the second soil water demand characteristic value is greater than or equal to the preset water demand characteristic value, the irrigation method for the weak demand irrigation mode is determined as intermittent irrigation. Practitioners can set the preset water demand characteristic value based on actual conditions. Preferably, the preset water demand characteristic value is set to a range of 0.6 to 0.7.

[0051] It is understandable that supplemental irrigation is to replenish the preset irrigation amount of water in one go, and the irrigation method is sprinkler irrigation. Intermittent irrigation is to divide the preset irrigation amount YG of water into r intervals for irrigation, with each irrigation amount being YG / r, and the irrigation method is drip irrigation. Preferably, the interval time is 15min to 30min.

[0052] For high-demand irrigation methods, wheat water demand characterization values ​​are determined based on wheat canopy parameters and wheat root growth at each of the second preset collection points, and a first soil water demand characterization value is determined based on soil moisture distribution at different depths at each of the preset collection points, in order to determine target irrigation parameters, wherein the irrigation parameters include irrigation rate and irrigation time.

[0053] Specifically, in step S3, determining the water requirement characterization value for wheat includes: Step S331: Determine the wheat growth index based on the wheat canopy parameters of each of the second preset collection points; Step S332: Determine the root growth index based on the wheat root growth at each of the second preset collection points; Step S333: Determine the wheat water requirement characterization value based on the wheat growth index and the root growth index.

[0054] In implementation, wheat canopy parameters collected during the wheat growth process in historical data of the target area are preprocessed, including data cleaning and standardization. Parameter values ​​exceeding reasonable ranges can be removed based on the 3σ principle. Missing data are filled with the mean of samples from the same growth stage and environmental conditions. Z-score standardization is used to eliminate dimensional differences in wheat canopy parameters. The preprocessed historical data is divided into four datasets according to wheat growth stages (greening stage, jointing stage, heading stage, and grain-filling stage). For each growth stage dataset, a training set (for model training) and a test set (for model evaluation) are divided in a 7:3 ratio. The wheat growth water requirement status (the water requirement at each stage within each growth stage) is quantified. For example, the wheat growth water requirement status rating (levels 1-5) is mapped to a quantitative label Y (wheat growth index) in the range of 0-1, with the formula: Y=(L-1) / 4 (e.g., level 5 corresponds to 1.0, level 3 corresponds to 0.5, and level 1 corresponds to 0), where L is the wheat growth water requirement status rating. A multiple linear regression model or a lightweight random forest model can be chosen as the base model. The core input is the standardized wheat canopy parameters, and the output is the quantified wheat growth index (0-1). The training sets for each growth stage are input into the model, and the parameters are iteratively optimized using the least squares method (linear regression) or the gradient descent method (random forest) until the model converges (the number of iterations ≤ 1000, and the error is less than a preset threshold). The coefficient of determination R² (goodness of fit) and the mean absolute error MAE (prediction accuracy) are used as core indicators, requiring R² ≥ 0.85 and MAE ≤ 0.05. If the evaluation indicators meet the standards, the model parameters for each growth stage (a, b, c, d or random forest decision tree rules) are saved; if they do not meet the standards, the model is retrained after supplementing the historical samples for the corresponding growth stages, and finally the wheat growth model is obtained.

[0055] Understandably, the standardized wheat canopy parameters from each of the second preset sampling points are input into the wheat growth model to obtain the predicted wheat growth index value corresponding to each second preset sampling point. The average of the predicted wheat growth index values ​​for each second preset sampling point is then determined as the wheat growth index. The wheat growth index can assess the water requirement of wheat at its current growth stage; a higher wheat growth index indicates a greater water requirement.

[0056] Understandably, the wheat root growth index can assess the water absorption capacity of wheat roots; a larger root growth index indicates a greater water absorption capacity. Based on wheat root growth, a wheat root distribution model can be constructed, for example, Z(k) = A × e (-B×k)+C, where k is the soil depth, Z(k) is the root mass percentage at depth k, A is the surface root mass coefficient (reflecting the enrichment of surface roots), B is the root mass decay coefficient (reflecting the root system's ability to extend downwards), and C is the deep root mass baseline value (reflecting the deep root system distribution). A, B, and C vary with the growth period and can be determined by fitting historical data. Historical root distribution data (root mass percentage at each depth) for each growth period are used as input samples. The least squares method is used to iteratively optimize parameters A, B, and C. The goal is to ensure that the average absolute error between the root mass percentage predicted by the model and the actual collected values ​​is less than or equal to 5%. Each growth period is trained independently to obtain specific model parameters. The goodness of fit R² (≥0.85) and mean absolute error (MAE) (≤5%) are used as core indicators to ensure that the model can accurately represent the vertical distribution pattern of roots. By inputting the wheat root growth data from each of the second preset sampling points into the wheat root distribution model, key parameter features can be obtained: the effective root mass ratio YG (obtained by integrating the model distribution curve to get the proportion of roots in the main water absorption layer), the root concentration depth fit GS (the degree of matching between the root concentration depth output by the model and the optimal water absorption layer depth for this growth stage), and the distribution uniformity JF (the coefficient of variation calculated from the model distribution curve converted to a standardized value in the 0-1 range). These key parameter features are then normalized and weighted (the weights can be dynamically determined based on the wheat growth stage; for example, during the greening stage, the weight of YG is 0.4). The weights for each second preset sampling point are as follows: GS = 0.35, JF = 0.25; jointing stage: YG = 0.45, GS = 0.3, JF = 0.25; heading stage: YG = 0.5, GS = 0.25, JF = 0.25; grain filling stage: YG = 0.48, GS = 0.27, JF = 0.25. This is used to obtain the predicted root growth index value for each second preset sampling point, and the average of the predicted root growth index values ​​for each second preset sampling point is determined as the root growth index.

[0057] It is understandable that the product of the wheat growth index and the root growth index is used as the characterization value of wheat water requirement.

[0058] Specifically, this invention determines the wheat growth index based on wheat canopy parameters at each second preset sampling point, which can comprehensively assess the growth status of wheat. It also determines the root growth index based on wheat root growth at each second preset sampling point, which can comprehensively assess the health status and growth vitality of wheat roots. By comprehensively considering the wheat growth index and root growth index, the water requirement characterization value of wheat is determined, ensuring the flexibility and adaptability of irrigation decisions and achieving precision irrigation.

[0059] Specifically, in step S3, determining the first soil water demand characterization value includes: Step S341: Determine the first abnormal water shortage index corresponding to each first preset collection point based on the soil moisture distribution at different depths of each first preset collection point. Step S342: Determine the first soil water demand characterization value based on each of the first abnormal water shortage index and each of the second abnormal water shortage index.

[0060] In implementation, the first soil water demand characterization value is used to quantitatively assess the degree of soil water shortage conducive to wheat growth at each first preset sampling point. The value ranges from 0 to 1; the smaller the value, the greater the soil water shortage conducive to wheat growth, and the greater the need for irrigation. Using soil moisture content at the same depth as data of the same dimension, the collected soil moisture content is normalized to convert it to the range of 0 to 1. This is existing technology and will not be elaborated further. Therefore, the first abnormal water shortage index YZ corresponding to any first preset sampling point is calculated as follows: YZ = ∑ q p=1 (v p ×YT p ), where p = 1, 2, ..., q; q is the soil depth layer number, v p YT represents the weighting coefficient corresponding to the p-th soil layer depth. p Let be the normalized soil moisture content corresponding to the depth of the p-th soil layer.

[0061] It is understandable that the average of each first abnormal water shortage index and each second abnormal water shortage index is determined as the first soil water demand characterization value.

[0062] Specifically, the present invention comprehensively determines the first soil water demand characterization value by combining the first abnormal water shortage index corresponding to the first preset collection point and the second abnormal water shortage index corresponding to the second preset collection point. This allows for precise analysis of the soil moisture content distribution within the target area, thereby enabling targeted adjustment of irrigation strategies and improving the accuracy of wheat irrigation.

[0063] Specifically, in step S3, determining the target irrigation parameters includes: Step S351: Determine the irrigation adjustment coefficient based on the wheat water requirement characterization value and the second soil water requirement characterization value; Step S352: Determine the target irrigation parameters based on the irrigation adjustment coefficient and the preset irrigation parameters, which include the preset irrigation time and the preset irrigation rate.

[0064] In practice, the product of the wheat water requirement characterization value and the second soil water requirement characterization value is determined as the irrigation adjustment coefficient.

[0065] It is understandable that the product of the irrigation adjustment coefficient and the preset irrigation rate is determined as the target irrigation rate, and the product of the irrigation adjustment coefficient and the preset irrigation time is determined as the target irrigation time. The implementers can set the preset irrigation rate based on the actual situation or the average irrigation rate that has passed the qualification test in historical data, and the implementers can set the preset irrigation time based on the actual situation or the average irrigation time that has passed the qualification test in historical data. Preferably, the preset irrigation rate ranges from 50 L / min·mu to 80 L / min·mu, and the preset irrigation time ranges from 30 min / mu to 50 L / min / mu, and irrigation is carried out by sprinkler irrigation based on the target irrigation parameters.

[0066] Specifically, this invention determines irrigation adjustment coefficients based on wheat water requirement characterization values ​​and second soil water requirement characterization values, thereby more accurately determining irrigation needs and avoiding over-irrigation or under-irrigation. By combining the irrigation adjustment coefficients with preset irrigation parameters, the specific parameters for irrigation can be determined more accurately to meet the growth needs of wheat and ensure the timeliness and effectiveness of irrigation.

[0067] This invention comprehensively assesses wheat's water requirements and growth environment by acquiring wheat canopy parameters, soil moisture distribution at different depths, wheat root growth, and environmental parameters for a predetermined time period from several pre-set sampling points within a target area. This provides comprehensive data support for precision irrigation and avoids the limitations of single-parameter decision-making. By determining irrigation trend characteristics based on wheat canopy parameters at each pre-set sampling point and environmental parameters for a predetermined time period, the water requirement trend of wheat can be predicted in advance, avoiding blindly entering the detailed calculation stage and saving computational resources. Based on the irrigation trend characteristics, the irrigation demand pattern of the target area can be determined, and irrigation demand can be divided into different levels. This allows for tiered management based on the actual growth needs of wheat, improving the accuracy and efficiency of the irrigation process.

[0068] Please see Figure 4 The diagram shown is a structural block diagram of an automatic wheat irrigation control system according to an embodiment of the present invention; the present invention also provides an automatic wheat irrigation control system, comprising: The data acquisition module is used to acquire wheat canopy parameters, soil moisture distribution at different depths, wheat root growth, and environmental parameters within a future preset time period from several preset collection points within the target area. The preset collection points include a first preset collection point and a second preset collection point. The data analysis module, which is connected to the data acquisition module, is used to determine the irrigation trend characterization value based on the wheat canopy parameters of each of the first preset collection points and the environmental parameters within a future preset time period. An irrigation control module, which is connected to the data acquisition module and the data analysis module respectively, is used to determine the irrigation demand mode of the target area based on the irrigation trend characterization value, wherein the irrigation demand mode includes waiting irrigation mode, weak demand irrigation mode and strong demand irrigation mode. For the waiting irrigation method, the waiting irrigation time is determined based on environmental parameters within a preset future time period, and irrigation reminder information is issued accordingly; For low-demand irrigation methods, the second soil water demand characterization value is determined based on the soil water content distribution at different depths of each second preset collection point, so as to determine whether the irrigation method is intermittent irrigation or supplementary irrigation. For high-demand irrigation methods, wheat water demand characterization values ​​are determined based on wheat canopy parameters and wheat root growth at each of the second preset collection points, and a first soil water demand characterization value is determined based on soil moisture distribution at different depths at each of the preset collection points, in order to determine target irrigation parameters, wherein the irrigation parameters include irrigation rate and irrigation time.

[0069] Specifically, the automatic wheat irrigation control system provided in this embodiment of the invention can achieve the same technical effect by adopting the above-mentioned IoT-based automatic wheat irrigation control method, which will not be repeated here.

[0070] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A wheat automatic irrigation control method based on Internet of Things, characterized in that, The method comprises the following steps: acquiring wheat canopy parameters at a plurality of preset collection points in a target area, soil water content distribution at different depths, wheat root growth conditions, and environmental parameters in a future preset time period, wherein the preset collection points include first preset collection points and second preset collection points; determining an irrigation trend representation value based on the wheat canopy parameters at each first preset collection point and the environmental parameters in the future preset time period; determining an irrigation demand mode of the target area based on the irrigation trend representation value, wherein the irrigation demand mode includes a waiting irrigation mode, a weak demand irrigation mode, and a strong demand irrigation mode; for the waiting irrigation mode, determining a waiting irrigation time based on the environmental parameters in the future preset time period to issue an irrigation prompt message; for the weak demand irrigation mode, determining a second soil water demand representation value based on the soil water content distribution at different depths at each second preset collection point to determine an irrigation mode as intermittent irrigation or supplemental irrigation; for the strong demand irrigation mode, determining a wheat water demand representation value based on the wheat canopy parameters and the wheat root growth conditions at each second preset collection point, and determining a first soil water demand representation value based on the soil water content distribution at different depths at each preset collection point to determine a target irrigation parameter, wherein the irrigation parameter includes an irrigation rate and an irrigation time. 2.The IoT-based automatic wheat irrigation control method of claim 1, wherein, The method for determining the irrigation trend representation value comprises the following steps: determining a wheat canopy water deficit index based on the wheat canopy parameters at each first preset collection point; determining a water replenishment index based on the environmental parameters in the future preset time period; determining the irrigation trend representation value based on the wheat canopy water deficit index and the water replenishment index. 3.The IoT-based automatic wheat irrigation control method of claim 2, wherein, The method for determining the irrigation demand mode of the target area based on the comparison result of the irrigation trend representation value, a first preset representation value, and a second preset representation value. 4.The IoT-based automatic wheat irrigation control method of claim 3, wherein, The method for determining the waiting irrigation time comprises the following steps: determining a waiting adjustment coefficient based on the comparison result of the water replenishment index and a preset replenishment index; determining the waiting irrigation time based on the waiting adjustment coefficient and a preset irrigation time. 5.The IoT-based automatic wheat irrigation control method of claim 4, wherein, The method for determining the second soil water demand representation value comprises the following steps: determining a second abnormal water deficit index corresponding to each second preset collection point based on the soil water content distribution at different depths at each second preset collection point; determining the second soil water demand representation value based on the second abnormal water deficit index corresponding to each second preset collection point. 6.The IoT-based automatic wheat irrigation control method of claim 5, wherein, The method for determining the irrigation mode based on the comparison result of the second soil water demand representation value and a preset water demand representation value. 7.The IoT-based automatic wheat irrigation control method of claim 6, wherein, The method for determining the wheat water demand representation value comprises the following steps: determining a wheat growth index based on the wheat canopy parameters at each second preset collection point; determining a root growth index based on the wheat root growth conditions at each second preset collection point; determining the wheat water demand representation value based on the wheat growth index and the root growth index. 8.The IoT-based automatic wheat irrigation control method of claim 7, wherein, The method for determining the first soil water demand representation value comprises the following steps: determining a first abnormal water deficit index corresponding to each first preset collection point based on the soil water content distribution at different depths at each first preset collection point; determining the first soil water demand representation value based on each first abnormal water deficit index and each second abnormal water deficit index. 9.The IoT-based automatic wheat irrigation control method of claim 8, wherein, The method for determining the target irrigation parameter comprises the following steps: determine an irrigation adjustment coefficient based on the wheat water requirement representation value and the second soil water requirement representation value; determine a target irrigation parameter based on the irrigation adjustment coefficient and a preset irrigation parameter.

10. A wheat automatic irrigation control system employing the wheat automatic irrigation control method based on the Internet of Things according to any one of claims 1-9, characterized in that, Comprise: a data acquisition module configured to acquire wheat canopy parameters at a plurality of preset collection points in a target area, soil water content distribution at different depths, wheat root growth conditions, and environmental parameters in a future preset time period, wherein the preset collection points include first preset collection points and second preset collection points; a data analysis module connected to the data acquisition module and configured to determine an irrigation trend representation value based on the wheat canopy parameters at each of the first preset collection points and the environmental parameters in the future preset time period; an irrigation control module connected to the data acquisition module and the data analysis module and configured to determine an irrigation demand mode for the target area based on the irrigation trend representation value, wherein the irrigation demand mode includes a waiting irrigation mode, a weak demand irrigation mode, and a strong demand irrigation mode; for the waiting irrigation mode, determine a waiting irrigation time based on the environmental parameters in the future preset time period to issue an irrigation prompt message; for the weak demand irrigation mode, determine a second soil water requirement representation value based on the soil water content distribution at different depths at each of the second preset collection points to determine an irrigation mode as intermittent irrigation or supplemental irrigation; for the strong demand irrigation mode, determine a wheat water requirement representation value based on the wheat canopy parameters and the wheat root growth conditions at each of the second preset collection points, and determine a first soil water requirement representation value based on the soil water content distribution at different depths at each of the preset collection points to determine a target irrigation parameter, wherein the irrigation parameter includes an irrigation rate and an irrigation time.

Images