Method for planting large white kidney beans and angelica in intercropping based on niche complementation

Abstract

The application discloses a method for planting large white kidney beans and angelica based on niche complementation intercropping, and relates to the field of agricultural technology, comprising the following steps: first, according to the layout structure of crop planting, the intercropping area of large white kidney beans and angelica is divided into multiple independent management sub-areas according to the planting row area; before the start of the drip irrigation operation, for each sub-area divided, through the soil moisture sensor array arranged at different depths, the soil water content data information of the sub-area is collected in real time. Through sub-area division, multi-level soil moisture monitoring and intelligent evaluation, the application realizes fine perception and dynamic differentiated regulation of soil moisture in the planting area, breaks through the existing one-size-fits-all problem of drip irrigation, improves the water balance of the edge row and the central row, improves the consistency of the growth of the large white kidney bean and angelica groups, reduces the risk of drought and diseases, and promotes the stable improvement of yield and quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural technology, in particular to a method for interplanting large white kidney beans and angelica based on niche complementarity. BACKGROUND

[0002] The method for interplanting large white kidney beans and angelica based on niche complementarity refers to analyzing the niche differences between large white kidney beans (also known as multi-flower beans) and angelica in terms of resource demand, root distribution, light utilization, water and fertilizer demand, and growth cycle, scientifically configuring the planting layout and management measures of the two crops, and realizing their coordinated growth and complementary use of environmental resources in the same farmland. This method optimizes the spatial structure and time allocation between crops, reduces interspecific competition, enhances resource utilization, improves overall soil fertility recovery, pest control, and yield and quality levels, and promotes the nitrogen fixation effect of large white kidney beans as legume crops to improve the root growth environment of angelica, thereby achieving the comprehensive goals of grain and medicine collection, efficient land use, and stable and sustainable farmland ecosystem.

[0003] In the process of interplanting large white kidney beans (multi-flower beans) and angelica based on niche complementarity, drip irrigation is usually preferred. Drip irrigation can accurately deliver water to the soil near the crop roots in a low-flow and slow manner, avoiding large-scale evaporation or loss of water on the ground surface, and is particularly suitable for meeting the dual needs of water supply uniformity and stability for both the shallow root system of large white kidney beans and the deep root system of angelica. Through drip irrigation, the imbalance of soil moisture distribution caused by different light and ventilation conditions in the edge rows and central rows can be effectively reduced, and the growth disorders, root diseases, and premature decline caused by uneven water supply can be reduced

[0004] The prior art has the following disadvantages: in the prior art, in the drip irrigation management process of field crops or intercropping mode, a unified water quantity and frequency are usually used for overall water supply, and there is a lack of subdivision control strategy for the spatial differences in light, ventilation and water evaporation rate in the internal planting area. Especially in the intercropping system of big white kidney beans (Phaseolus lunatus) and angelica based on niche complementarity, due to the significant differences in light intensity, air flow and water evaporation rate between the crop rows near the edge of the planting area (edge rows) and the central crop rows (central rows), the soil water evaporation of the edge rows is intensified and the water loss speed is fast, while the soil water evaporation of the central rows is slow, and water retention is prone to occur. The drip irrigation method in the prior art does not compensate for the control of the above-mentioned internal micro-environment differences, which easily leads to the big white kidney beans (Phaseolus lunatus) and angelica plants in the edge area being in a water deficit stress state for a long time, showing dwarf growth, premature aging, yield and quality reduction; while the big white kidney beans (Phaseolus lunatus) and angelica in the central area are prone to overgrowth, root rot and disease outbreak due to excessive water, which seriously affects the planting uniformity, growth stability and final economic benefit of the intercropping system as a whole, and limits the popularization and application of the intercropping mode of big white kidney beans (Phaseolus lunatus) and angelica based on niche complementarity.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a method for intercropping big white kidney beans and angelica based on niche complementarity, which realizes fine perception and dynamic differentiated regulation of soil water in the planting area through sub-area division, multi-level soil water monitoring and intelligent evaluation, breaks through the one-size-fits-all problem of existing drip irrigation, improves the water balance of edge rows and central rows, improves the growth consistency of big white kidney bean and angelica groups, reduces the risk of drought and disease, and promotes stable improvement of yield and quality, to solve the problems in the background technology.

[0007] In order to achieve the above-mentioned purpose, the present application provides the following technical scheme: a method for intercropping big white kidney beans and angelica based on niche complementarity, comprising the following steps:

[0008] First, according to the layout structure of crop planting, the intercropping area of big white kidney beans and angelica is divided into multiple independent management sub-areas according to the planting row area;

[0009] Before the drip irrigation operation starts, for each sub-area divided, the soil moisture sensor array arranged at different depths is used to collect real-time soil water content data information of the sub-area;

[0010] The collected sub-region soil water content data information is pre-processed, and a data set is established to form a sub-region water state analysis standardized data input source;

[0011] Through feature engineering technology processing, the key indicator features that intuitively reflect the sub-region soil water deficit stress state are extracted from the data set, and the extracted key indicator features are comprehensively analyzed to quantify the current water loss degree of the sub-region;

[0012] The key feature indicators after comprehensive analysis are input into the machine learning model trained based on historical soil moisture data in advance, and the soil moisture content state of the sub-region is intelligently evaluated in real time through the model to determine whether the soil is in a water deficit stress state;

[0013] When it is identified that the current region soil is in a water deficit stress state, according to the water potential difference between the current region and other sub-regions, the flow regulating valve of each branch of the drip irrigation pipeline is dynamically adjusted, the drip irrigation flow of the water deficit region is automatically increased, and the water supply intensity of the water suitable region is reduced, thereby realizing asynchronous and different amount irrigation compensation between regions, and effectively completing the dynamic regulation and control of local water replenishment and overall water distribution balance.

[0014] Preferably, according to the layout structure of crop planting, the intercropping region of large white kidney beans and angelica is divided into multiple independent management sub-regions according to the planting row area, and the specific steps are as follows:

[0015] Firstly, the field geometric information and planting planning map of the intercropping region are obtained, including crop type distribution, row spacing, plant spacing and field boundary coordinates;

[0016] Subsequently, according to the actual planting row arrangement mode of large white kidney beans and angelica, combined with the row spacing and the shape of the field, the whole region is divided into multiple regular sub-regions according to the width of the row direction, so as to ensure that each sub-region covers one or a plurality of complete intercropping rows;

[0017] Then, the divided sub-regions are numbered and coded for management, and corresponding geographic information tags are established for subsequent data collection and spatial positioning of control instructions;

[0018] Finally, according to the consistency of crop combination, spatial position and environmental conditions in each sub-region, the adjustment is checked to ensure that the internal management target of each sub-region is consistent, the boundary is clear, and it is suitable for differentiated drip irrigation regulation and control.

[0019] Preferably, the key feature indicators reflecting the stress state of the sub-regional soil water deficit are extracted from the data set by feature engineering techniques, including the water conduction resistance degree in the soil profile and the loss of synchronism between the surface layer water content and the root layer water content. The water conduction resistance degree in the soil profile and the loss of synchronism between the surface layer water content and the root layer water content are analyzed comprehensively under the detection window to generate the evaporation conduction limited reference value and the root layer decoupling reference value, respectively, to quantify the current water deficiency degree of the sub-region.

[0020] Preferably, the specific steps of generating the evaporation conduction limited reference value by comprehensively analyzing the water conduction resistance degree in the soil profile under the detection window are as follows:

[0021] Based on the soil water content measurement data of each detection depth point in the soil profile, the water gradient resistance factors between each adjacent layer are calculated in sequence, and the calculation expression is as follows:

[0022] , wherein, is the soil volume water content of the first layer in the soil profile, is the soil volume water content of the first layer in the soil profile, is the soil volume water content of the next layer, is a very small positive number set to avoid division by zero error, is a water conduction directionality discrimination coefficient, is a water gradient resistance factor;

[0023] Based on the cumulative amplitude of all water gradient resistance factors , the overall water conduction limited degree of the profile is comprehensively calculated to generate the evaporation conduction limited reference value, and the generation formula is as follows:

[0024] , wherein, is the evaporation conduction limited reference value, is the total amount of soil profile detection depth, is a resistance intensity amplification coefficient, is a hyperbolic tangent function.

[0025] Preferably, the specific steps of generating the root layer decoupling reference value by comprehensively analyzing the loss of synchronism between the surface layer water content and the root layer water content under the detection window are as follows:

[0026] First, the real-time water content data of the surface layer soil and the root layer soil in the target sub-region are obtained, and based on the change rate of the water content between adjacent sampling time points, the surface layer water content change rate and the root layer water content change rate are calculated, and the surface layer-root layer synchronization difference factor is defined, and the calculation formula is as follows:​

[0027] In the formula, It is a synchronous difference factor. It is the rate of change of surface soil moisture. It is the rate of change of soil moisture content in the root zone. It is a stabilizing factor;

[0028] Synchronous difference factor obtained from continuous sampling Nonlinear accumulation processing is performed to generate root layer decoupling reference values, as shown in the following formula:

[0029] In the formula, It is the root layer decoupling reference value. It is the first The synchronization difference factor is calculated from the second sampling. It is the total number of samples. These are non-linear weighting coefficients. It is the sensitivity adjustment coefficient. It is the natural base.

[0030] Preferably, the reference values ​​for evaporation conduction limitation and root decoupling after comprehensive analysis are input into a machine learning model that has been pre-trained based on historical soil moisture data. The model generates a soil moisture deficit stress coefficient, and the soil moisture content status of the sub-region is intelligently assessed in real time based on the soil moisture deficit stress coefficient to determine whether the soil is under water deficit stress.

[0031] Preferably, the soil moisture deficit stress coefficient generated by the machine learning model, which is pre-trained based on historical soil moisture data, to perform real-time intelligent assessment of the soil moisture content status of a sub-region is compared and analyzed with a pre-set reference threshold for the soil moisture deficit stress coefficient to determine whether the soil is under water deficit stress. The judgment logic is as follows:

[0032] If the soil moisture deficit stress coefficient is greater than the preset reference threshold for soil moisture deficit stress coefficient, the soil is determined to be under water deficit stress; if the soil moisture deficit stress coefficient is less than or equal to the preset reference threshold for soil moisture deficit stress coefficient, the soil is determined not to be under water deficit stress.

[0033] Preferably, when the soil in the current area is identified as being under water deficit stress, the flow regulating valves of each branch of the drip irrigation pipeline are dynamically adjusted according to the difference in water potential between the current area and other sub-areas. This automatically increases the drip irrigation flow in the water deficit area while reducing the water supply intensity in the water-suitable area, thereby achieving asynchronous and heterogeneous irrigation compensation between areas. The specific steps are as follows:

[0034] Once a sub-region's soil is identified as being under water deficit stress, the soil water deficit stress coefficient is used as the basis for this process. Based on the difference from the reference threshold of the soil moisture deficit stress coefficient, a flow rate adjustment factor is constructed to dynamically adjust the drip irrigation flow rate. The calculation formula for the flow rate adjustment factor is as follows:

[0035] In the formula, It is a flow adjustment factor. It is the water potential response sensitivity coefficient. It is a sub-region Soil moisture deficit stress coefficient It is the reference threshold for the soil moisture deficit stress coefficient. This is the basic drip irrigation flow rate;

[0036] Obtain the flow adjustment factor corresponding to each sub-region Then, the initial drip irrigation flow rate of the sub-region is dynamically corrected based on the flow rate adjustment factor to obtain the updated target drip irrigation flow rate. The update formula is as follows:

[0037] In the formula, It is a sub-region Adjusted drip irrigation flow rate It is a sub-region The initial drip irrigation flow rate;

[0038] After dynamically adjusting the drip irrigation flow rate in each sub-region, the overall water distribution balance index within the current planting area is calculated to assess the water replenishment effect. Based on the assessment results, a decision is made on whether to trigger further fine-tuning. The index calculation formula is as follows:

[0039] In the formula, It is an indicator of the evenness of water distribution. It is the set target ideal water deficit stress coefficient. and Representing all current sub-regions The maximum and minimum values, It is a weighted index. This represents the total number of sub-regions;

[0040] If the calculated result If the water level is above the set balance threshold, it indicates that the regional water distribution is approaching balance, confirming that the water replenishment regulation is complete; if it is below the threshold, the next round of local fine-tuning will be initiated to further improve the overall water balance level.

[0041] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0042] The application can realize fine perception and dynamic differentiated compensation of the soil moisture state in the planting area, and breaks through the one-size-fits-all problem of drip irrigation management in the prior art, and cannot accurately control spatial heterogeneity. Through sub-area division and multi-level soil moisture monitoring, combined with feature engineering key index extraction and intelligent machine learning evaluation, early identification and partition dynamic regulation of local water deficit stress state are realized, the balance of soil moisture distribution between edge rows and central rows is effectively improved, the consistency of large white kidney bean and angelica population growth is significantly improved, the occurrence probability of drought stress and waterlogging disease is reduced, and then the yield stability, quality consistency and economic benefit of the intercropping system as a whole are improved, and the sustainable popularization and application of the intercropping mode based on the principle of niche complementation are promoted. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only represent some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0044] Figure 1 A method flowchart for intercropping large white kidney beans and angelica based on niche complementation. DETAILED DESCRIPTION

[0045] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art.

[0046] The present application provides a method for intercropping large white kidney beans and angelica based on niche complementation, as shown in Figure 1 The method comprises the following steps:

[0047] First, according to the layout structure of crop planting, the intercropping area of large white kidney beans and angelica is divided into a plurality of independent management sub-areas according to the planting row area, and the number of large white kidney bean / angelica rows in each sub-area is 1:12, which is a vertical frame, the ridge distance of large white kidney bean is 3.0 meters, the pond distance is 0.8 meters, the density is 270 ponds per mu, the row distance of angelica is 0.25 meters, the plant distance is 0.25 meters, and the density specification is 10672 plants per mu;

[0048] Specifically, according to the planting row distribution rule, the crop type, planting density and spatial layout in each sub-area are ensured to be relatively uniform, so as to facilitate the accurate monitoring of the water state of each sub-area. The main role of this division step is to form an irrigation management unit with a moderate spatial scale, so that the subsequent data collection, analysis and drip irrigation regulation can have clear and detailed targeting, avoiding the situation that the internal water is difficult to regulate due to the too large management scale.

[0049] According to the layout structure of crop planting, the intercropping area of large white kidney beans and angelica is divided into multiple independent management sub-areas according to the planting row area, and the specific steps are as follows: first, obtain the field geometric information and planting planning map of the intercropping area, including crop type distribution, row spacing, plant spacing and field boundary coordinates; then, according to the actual planting row arrangement mode of large white kidney beans and angelica, combining row spacing and field shape, the whole area is divided into multiple regular sub-areas according to the width of the row direction, ensuring that each sub-area covers one or a group of complete intercropping rows; then, the sub-areas divided are numbered and coded for management, and corresponding geographic information tags are established for subsequent data collection and spatial positioning of control instructions; finally, according to the consistency of crop combination, spatial position and environmental conditions in each sub-area, the adjustment is checked to ensure that the internal management target of each sub-area is consistent, the boundary is clear, and it is suitable for differentiated drip irrigation regulation. Through the above steps, the fine partitioning of the planting area is realized, and the spatial basic unit for intelligent irrigation management is provided.

[0050] Before the drip irrigation operation starts, for each sub-area divided, through the soil moisture sensor array arranged at different depths, the soil water content data information of the sub-area is collected in real time;

[0051] These sensors are preferably high-precision capacitive or time domain reflection (TDR) type soil moisture sensors, and the buried depths correspond to the root zone of large white kidney beans with shallow root system (such as 10-20 cm) and the root zone of angelica with deep root system (such as 30-50 cm), respectively, to realize multi-level and multi-scale accurate acquisition of soil water content data. The role of this step is to comprehensively and accurately master the actual water state of each sub-area before drip irrigation, and to provide a reliable data basis for subsequent intelligent analysis and decision-making.

[0052] After the collected soil water content data information of the sub-area is preprocessed, a data set is established to form a standardized data input source for sub-area water state analysis;

[0053] The data preprocessing includes outlier rejection, data missing filling, data smoothing processing and standardization transformation, so that the data of the sub-regions have comparability and uniformity. Among them, the outlier rejection adopts a robust statistical method (such as the interquartile range method) for identification, the data smoothing uses a moving average or a Savitzky-Golay filter, and the standardization transformation adopts a Min-Max or Z-score normalization method. The role of this step is to improve the data quality and the accuracy of data analysis, to ensure the stability and accuracy of subsequent feature extraction, and to avoid misjudgment and misadjustment caused by abnormal data interference.

[0054] The processed data is established as a structured data set in a unified format, forming a standardized data input source for sub-regional water state analysis. The purpose of this step is to improve data quality, eliminate error and noise effects, and provide a stable and reliable data foundation for the next accurate analysis, to ensure the accuracy of subsequent feature extraction and intelligent evaluation.

[0055] Through feature engineering technology processing, key indicator features that directly reflect the soil water deficit stress state of the sub-region are extracted from the data set, and the extracted key indicator features are comprehensively analyzed to quantify the current water deficiency degree of the sub-region.

[0056] Through feature engineering technology processing, key indicator features that directly reflect the soil water deficit stress state of the sub-region are extracted from the data set. The extracted key indicator features include the degree of water conduction resistance in the soil profile and the degree of loss of synchronization between surface water and root water. The degree of water conduction resistance in the soil profile and the degree of loss of synchronization between surface water and root water are comprehensively analyzed under the detection window to generate evaporation conduction limited reference value and root layer decoupling reference value, respectively. The current water deficiency degree of the sub-region is quantified by the evaporation conduction limited reference value and the root layer decoupling reference value.

[0057] The current water deficiency degree of the sub-region is quantified by the evaporation conduction limited reference value and the root layer decoupling reference value, which can accurately depict the formation mechanism and influence depth of water deficit stress state from two key dimensions of soil structural water migration obstruction and vertical water supply system imbalance. The evaporation conduction limited reference value reflects whether the water conduction channel in the soil profile from the wet area to the dry area is limited, revealing problems such as pore structure degradation, capillary water rupture or vertical permeability reduction in local soil. The root layer decoupling reference value focuses on whether the actual water absorption root zone of crops can get effective water supply, which is a key indicator for measuring "apparently wet surface but serious root water loss". Joint analysis of these two reference values not only avoids the judgment deviation caused by relying only on the average water content, but also substantially improves the early identification and grading response ability of water deficit risk, providing reliable quantitative basis for subsequent drip irrigation control, ensuring that water precise supply is more targeted, timely and efficient.

[0058] The significant water conduction blockage in soil profile usually indicates that the current sub-region is in a potential or actual soil water deficit stress state, which is fundamentally caused by the failure of water to effectively migrate from the relatively humid layer to the dry layer, resulting in the interruption or significant reduction of available water resources in the crop root zone. Especially in the niche complementary intercropping system, such as the planting mode of large white kidney beans and angelica, there are vertical differences in root distribution. If the water conduction performance of the soil profile is limited (such as due to soil compaction, pore structure degradation, or soil particle differentiation), a water barrier is easily formed at a certain depth, making it difficult for surface water to infiltrate or deep water to move upwards, thereby causing a certain root layer of the crop to be in a drought state. This structural water migration failure not only reduces the utilization efficiency of irrigation water, but also directly interferes with the normal absorption of water by the crop, causing typical water stress symptoms such as leaf water loss, transpiration inhibition, and growth stagnation. Therefore, water conduction blockage is not only a physical process, but also an important external manifestation of functional water shortage in the sub-region, and needs to be monitored and responded as a key indicator for water stress determination.

[0059] The specific steps of generating the evaporation conduction limited reference value by comprehensively analyzing the water conduction blockage degree in the soil profile within the detection window are as follows:

[0060] Based on the soil water content measurement data of each detection depth point in the soil profile, the water gradient blockage factor between each adjacent layer is calculated in turn, and the calculation expression is as follows:

[0061] In the formula, is the soil volume water content of the layer in the soil profile, which is used to represent the volume proportion of water contained in the unit volume of the soil in the layer, and is a direct quantitative indicator of the soil water state, is the soil volume water content of the layer in the soil profile, i.e. the soil volume water content of the next layer, is a very small positive number set to avoid division by zero error (preferably ), is a water conduction directionality discrimination coefficient, which is used to amplify the potential blockage effect caused by the reverse water gradient, making the blockage index more sensitive to abnormal conduction phenomena, is the water gradient blockage factor, which is a quantitative factor of the water conduction blockage degree between the layer and the layer detection point in the soil profile;

[0062] By calculating the water gradient mutation and directionality anomaly between each adjacent layer of the soil profile, the local characteristics of the limited water conduction in the soil are accurately captured, and the potential water migration barrier area is identified. By establishing the water gradient resistance factor, the problem of ignoring profile heterogeneity in simple water measurement can be avoided, laying a fine-grained data foundation for subsequent comprehensive evaluation of the overall water supply connectivity of the profile.

[0063] Based on the cumulative amplitude of all water gradient resistance factors , the overall water conduction limitation of the profile is comprehensively calculated, and the evaporation conduction limitation reference value is generated, and the formula is as follows:

[0064] , in the formula, is the evaporation conduction limitation reference value, is the total number of layers of the soil profile detection depth, is the resistance intensity amplification coefficient, which moderately amplifies the overall resistance intensity according to the soil type, water characteristics or crop water sensitivity, so that the sensitivity of the evaporation conduction limitation index is more in line with the actual water deficit response demand, and the preferred value range is: between 1 and 3, is the hyperbolic tangent function.

[0065] The above step selects the hyperbolic tangent function as the normalization processing means of the evaporation conduction limitation reference value, the main purpose is to realize the boundary convergence and stable suppression of the numerical output on the basis of retaining the trend of the cumulative effect of water conduction resistance. Since the cumulative water gradient resistance may vary greatly in different sub-regions and different detection windows, if directly linearly processed, it is easy to cause the result to present abnormal amplification or severe fluctuation, affecting the consistency and reliability of subsequent judgment. The hyperbolic tangent function has good nonlinear compression characteristics, which can smoothly map the input value to a limited interval (-1, 1), and in this application, the resistance amount is positive, so the output range is naturally limited to (0, 1), and as the resistance accumulation degree increases, the exponential growth rate gradually slows down, avoiding extreme resistance values dominating the overall evaluation results. Through the introduction of the function, slight resistance changes can still maintain a sensitive response, while in the case of severe resistance, the index oversaturation can be effectively suppressed, improving the numerical stability, comparability and robustness of the evaporation conduction limitation index in practical applications.

[0066] Through the above processing, the local water migration limitation characteristics can be normalized and integrated, and finally a unified evaporation conduction limitation reference value is output. The larger the reference value, the higher the degree of soil water migration limitation in the sub-region, and the more obvious the water deficit stress state, which provides an accurate basis for subsequent water supply regulation.

[0067] The greater the evaporation transmission restriction reference value generated by the comprehensive analysis of the degree of water transmission resistance in the soil profile in the detection window, the more significant the water transmission resistance phenomenon in the current sub-region soil, reflecting a more serious water deficit stress state. The reference value is the degree of restriction in the vertical direction of water transmission, which is evaluated by analyzing the water gradient continuity, transmission rate, and capillary water rising efficiency between different depths in the soil profile within the monitoring window. When the reference value increases, it usually indicates that there is a fault between the wet layer and the dry layer, making it difficult for water to effectively migrate from the wet area to the crop root zone, resulting in a significant lack of available water for the roots, and further inducing physiological water stress response. When the reference value is low, it indicates that the water transmission in the soil profile is smooth, the water supply chain is complete, and the root zone water status is relatively stable.

[0068] When the synchronization between the surface layer water content and the root layer water content is significantly decoupled, it usually indicates that the current sub-region soil has entered a water deficit stress state. From the perspective of soil-plant water dynamics, the surface layer and root layer soil water should normally present a high consistency, i.e., they should be wet simultaneously after water replenishment and maintain a certain degree of synchronous decline during evaporation or absorption. When the synchronization is decoupled, i.e., the surface layer water content remains at a high level while the root layer soil water content continues to decline, it means that the vertical transmission of water in the profile is blocked or the surface layer water cannot effectively replenish the crop root zone, resulting in a sharp decrease in available water resources for crops, and further triggering a decrease in root water potential and an increase in physiological water stress. This phenomenon is often accompanied by a decrease in transpiration rate, an increase in canopy temperature, and other physiological responses, which are typical early signs of soil water deficit stress. Therefore, the surface-root decoupling phenomenon not only sensitively reflects the destruction of soil hydraulic continuity, but also directly reveals the risk of imbalance in water supply to the crop root zone, and is an important criterion for identifying the entry of a sub-region into a water deficit stress state.

[0069] The specific steps for generating the root layer decoupling reference value by comprehensively analyzing the loss of synchronization between the surface layer water content and the root layer water content in the detection window are as follows:

[0070] First, obtain the real-time water content data of the surface layer soil (depth of 10-20 cm) and the root layer soil (depth of 30-50 cm) in the target sub-region, and based on the change rate of water content between adjacent sampling times, calculate the surface layer water content change rate and the root layer water content change rate, and define the surface-root synchronization difference factor, the calculation formula is as follows:

[0071] , wherein, is the synchronization difference factor, which quantifies the relative synchronization difference between the surface layer soil water content change rate and the root layer soil water content change rate, is the surface soil water content change rate, which represents the change rate of the surface soil (usually refers to the 10-20 cm depth range) in the detection time interval, is the root layer soil water content change rate, which represents the change rate of the root layer soil (usually refers to the 30-50 cm depth range) in the detection time interval, is a stability factor, to avoid the denominator tends to zero at a very small change rate, causing numerical anomaly amplification or unstable operation, usually a small positive number between 0.01 and 0.1 is selected;

[0072] The above formula is to accurately depict the relative difference between the instantaneous change trend of the surface and root layer water content. If the surface soil water content change rate is significantly lower than the root layer, it means that the soil water cannot be effectively conducted from the surface to the root layer, and the synchronization between the surface and the root layer is obviously lost, significantly deviates from the 0 value.

[0073] The synchronization difference factor obtained by continuous sampling is subjected to nonlinear accumulation processing to generate a root layer decoupling reference value, and the generation formula is as follows:

[0074] , wherein is the root layer decoupling reference value, is the synchronization difference factor obtained by the sampling calculation, which measures the degree of asynchronization of the surface soil and the root layer soil at a single sampling time, is the total number of samplings, is a nonlinear weight coefficient, which is an exponential weight for nonlinear reinforcement processing of each synchronization difference factor , and the value is , is a sensitivity adjustment coefficient, is a coefficient in the function for controlling the slope of the curve, and the value range is: , which is used to adjust the response rate between the total amount of decoupling degree and output value, is a natural base.

[0075] Through the above formula, the degree of synchronization loss in the detection window can be quantified to the [0, 1] interval, wherein the greater the value, the more serious the decoupling degree of the surface and root layer soil water content dynamics, and the higher the risk of the current sub-area entering the water deficit stress state; on the contrary, the smaller the value, the better the continuity of soil water conduction, and the normal water state of the sub-area.

[0076] Through the above steps, the soil in the sub-region can be dynamically monitored and identified whether it is in a water deficit stress state, and the real-time perception and fine regulation ability of the irrigation management system to local water shortage risk can be improved.

[0077] The greater the root layer decoupling reference value generated after comprehensive analysis of the degree of loss of synchronism between surface layer water content and root layer water content in the detection window, the more significant the difference in water dynamic changes between the surface layer and the root layer, i.e., the surface layer may maintain a certain degree of moisture while the root layer is significantly drought, indicating that the actual available water source for the root system is severely insufficient, and the soil in the sub-region is in a state of obvious water deficit stress. Conversely, when the root layer decoupling reference value is smaller, it indicates that the water changes between the surface layer and the root layer maintain good synchronism, and the water transmission continuity is good, and the crop root zone can continuously obtain stable water source, indicating that the soil water content in the sub-region is in a normal and suitable state.

[0078] The key feature indicators after comprehensive analysis are input into the machine learning model trained in advance based on historical soil moisture data, and the soil moisture content state of the sub-region is intelligently evaluated in real time through the model to determine whether the soil is in a water deficit stress state;

[0079] The evaporation transmission limited reference value and the root layer decoupling reference value after comprehensive analysis are input into the machine learning model trained in advance based on historical soil moisture data, and a soil water deficit stress coefficient is generated through the model, and the soil moisture content state of the sub-region is intelligently evaluated in real time through the soil water deficit stress coefficient to determine whether the soil is in a water deficit stress state.

[0080] The machine learning model trained in advance based on historical soil moisture data refers to an intelligent decision-making model that can automatically identify and predict the soil water deficit stress state of the sub-region by using a large amount of previously collected soil moisture dynamic change data, combining soil physical properties, meteorological conditions, crop growth stages, and other multi-dimensional features, and through supervised learning or semi-supervised learning methods. This training process usually includes data preprocessing, feature extraction, model selection, parameter optimization and validation evaluation, etc. The model can be a support vector machine (SVM), a random forest (Random Forest), an extreme gradient boosting tree (XGBoost), or a long short-term memory network (LSTM), etc. During the training process, the historical samples are labeled according to whether there is water deficit stress, and the input samples include the evaporation transmission limited reference value, the root layer decoupling reference value and other auxiliary features, and the output label is the corresponding water stress grade or stress coefficient value. Through the learning of a large number of samples, the model gradually masters the complex mapping relationship between key features and the actual soil moisture state, and has the ability to quickly and accurately distinguish new input samples, forming an intelligent evaluation module that can be deployed in a real-time system.

[0081] In a specific application, before the drip irrigation operation, the evaporation conduction limited reference value and the root layer decoupling reference value obtained through the real-time detection on site are standardized and then input into the trained machine learning model as input features, and the model automatically generates a soil moisture deficit stress coefficient according to the built-in learning rule. The coefficient serves as a comprehensive index for quantitatively representing the stress degree of the current sub-region water deficit, and the numerical value directly reflects whether the soil is currently in a mild, moderate or severe water shortage state, and can be classified according to the preset threshold. Through this process, the system can real-time, intelligently and accurately evaluate the soil moisture condition of the sub-region without human intervention, greatly improving the timeliness and accuracy of drip irrigation regulation, avoiding the problem of misjudgment or lag response caused by the traditional single water content index, and laying a foundation for high-precision dynamic water management.

[0082] The machine learning model is not limited here, and any machine learning model that can realize comprehensive analysis of the evaporation conduction limited reference value and the root layer decoupling reference value to generate a soil moisture deficit stress coefficient can be used. To realize the technical solution of the present application, the present application provides a specific implementation method:

[0083] The soil moisture deficit stress coefficient is calculated according to the following formula: , wherein and are preset proportion coefficients of the evaporation conduction limited reference value and the root layer decoupling reference value , and and are both greater than 0.

[0084] The preset proportion coefficient refers to a set of weight parameters artificially set in advance according to the different importance and sensitivity of the evaporation conduction limited reference value and the root layer decoupling reference value in describing the soil moisture deficit stress process. Specifically, is used to adjust the contribution degree of the evaporation conduction limited reference value to the final soil moisture deficit stress coefficient , is used to adjust the contribution degree of the root layer decoupling reference value to the soil moisture deficit stress coefficient The contribution degree of the result. The preset of these proportion coefficients can be determined according to historical experience data, actual observation analysis or model training process, and the purpose is to ensure that the two key indicators can reasonably reflect the actual influence degree of each other when generating the soil water deficit stress coefficient in the comprehensive analysis, and to avoid the evaluation result deviation caused by the difference of index scale or different response speed. By introducing the preset proportion coefficient, the adaptability optimization of different sub-regions, different soil types or different crop root zone characteristics can be realized, so as to improve the scientificity and accuracy of the overall water deficit stress discrimination.

[0085] According to the soil water deficit stress coefficient, the greater the evaporation transmission limited reference value generated by the comprehensive analysis of the water transmission resistance degree in the soil profile in the detection window, the greater the root layer decoupling reference value generated by the comprehensive analysis of the loss of synchronization between the surface layer water content and the root layer water content in the detection window, the greater the soil water deficit stress coefficient generated by the real-time intelligent evaluation of the soil water content state of the sub-region by the machine learning model trained in advance based on the historical soil water data, and the greater the probability that the current sub-region soil is in the water deficit stress state, and vice versa.

[0086] The soil water deficit stress coefficient generated by the real-time intelligent evaluation of the soil water content state of the sub-region by the machine learning model trained in advance based on the historical soil water data is compared and analyzed with the preset soil water deficit stress coefficient reference threshold value to determine whether the soil is in the water deficit stress state, and the judgment logic is as follows:

[0087] If the soil water deficit stress coefficient is greater than the preset soil water deficit stress coefficient reference threshold value, it is judged that the soil is in the water deficit stress state; if the soil water deficit stress coefficient is less than or equal to the preset soil water deficit stress coefficient reference threshold value, it is judged that the soil is not in the water deficit stress state.

[0088] When it is identified that the soil of the current region is in the water deficit stress state, according to the water potential difference between the current region and other sub-regions, the flow regulating valve of each branch of the drip irrigation pipeline is dynamically adjusted, the drip irrigation flow of the water deficit region is automatically increased, and the water supply intensity of the water suitable region is reduced, so as to realize the asynchronous and different amount irrigation compensation between regions, and effectively complete the dynamic regulation and control of local water supplement and overall water distribution balance.

[0089] To address the uneven spatial distribution of soil moisture within planting areas caused by differences in environmental conditions, crop transpiration rates, or soil structural heterogeneity, this approach dynamically adjusts drip irrigation flow rates in each sub-region based on real-time detected water potential differences. This enables precise irrigation management that is tailored to local conditions and supplied water on demand. By automatically increasing drip irrigation flow rates in water-deficient stress areas, the missing water can be quickly replenished, alleviating water stress on plant roots and preventing slow crop growth, premature aging, and yield reduction caused by localized water shortages. Conversely, by simultaneously reducing the water supply intensity in water-suitable areas, it effectively prevents problems such as decreased soil aeration, root rot, and energy waste caused by excessive water, thus avoiding the risk of imbalanced growth in the plant population due to a uniform water supply model. This asynchronous, heterogeneous drip irrigation strategy, based on dynamic adjustment according to water potential differences, establishes a dynamic water balance mechanism within different sub-regions, promoting the consistency and coordination of the overall growth status of the planting population and significantly improving the overall yield and quality of white kidney beans and angelica in the intercropping system. Meanwhile, this control method also has strong real-time and adaptive capabilities, and can dynamically adjust the water supply strategy according to environmental changes and crop growth stages, so that drip irrigation management can be transformed from traditional static control to intelligent dynamic optimization, improve water resource utilization efficiency, ensure optimal water supply for crops at different growth stages, and support the goal of efficient, stable and sustainable planting under the niche complementary intercropping model.

[0090] When the soil in the current area is identified as being under water deficit stress, the flow regulating valves of each branch of the drip irrigation pipeline are dynamically adjusted based on the difference in water potential between the current area and other sub-areas. This automatically increases the drip irrigation flow in the water deficit area while reducing the water supply intensity in the water-suitable area, thereby achieving asynchronous and heterogeneous irrigation compensation between areas. The specific steps are as follows:

[0091] Once a sub-region's soil is identified as being under water deficit stress, the soil water deficit stress coefficient is used as the basis for this process. Based on the difference from the reference threshold of the soil moisture deficit stress coefficient, a flow rate adjustment factor is constructed to dynamically adjust the drip irrigation flow rate. The calculation formula for the flow rate adjustment factor is as follows:

[0092] In the formula, It is a flow adjustment factor, indicating that the sub-region should be adjusted accordingly. The absolute adjustment amount for increasing or decreasing the current drip irrigation flow rate. A positive value indicates that the flow rate needs to be increased, and a negative value indicates that it needs to be decreased. The value range is: Limited by The output range is [-1, 1]. This is the water potential response sensitivity coefficient, which represents the sensitivity of soil water potential difference to the magnitude of flow rate adjustment. Its value range is: , It is a sub-region a soil water deficit stress coefficient, is a soil water deficit stress coefficient reference threshold, is a basic drip irrigation flow, which is a standard drip irrigation flow reference value uniformly set for all sub-regions, usually used to regulate the upper limit of the flow adjustment factor, has global applicability, and does not change with the specific sub-region number;

[0093] Through this step, the flow adjustment amount of each sub-region can be quantitatively obtained based on the difference in water deficit intensity.

[0094] After obtaining the flow adjustment factor corresponding to each sub-region , the initial drip irrigation flow of the sub-region is dynamically corrected according to the flow adjustment factor to obtain the updated target drip irrigation flow, and the update formula is as follows:

[0095] , wherein, is the adjusted drip irrigation flow of the sub-region , which is the new target drip irrigation flow finally set for the sub-region after dynamic regulation, is the initial drip irrigation flow of the sub-region , which is the basic drip irrigation flow preset or regularly set by the system for the sub-region before dynamic flow regulation;

[0096] Through the above formula, if there is a serious water deficit in the sub-region, the irrigation flow is increased; if the water state of the sub-region is suitable or wet, the flow is appropriately reduced, realizing the local differentiation regulation of water supply, thereby preferentially relieving the water stress of the deficit area and inhibiting the excessive water supply of the suitable area.

[0097] After completing the dynamic adjustment of the drip irrigation flow of each sub-region, the water distribution uniformity index of the whole planting area is calculated to evaluate the water supplement effect, and whether to trigger further fine tuning is decided according to the evaluation result, and the index calculation formula is as follows:

[0098] , wherein, is the water distribution uniformity index, which comprehensively reflects the spatial uniformity degree of the water deficit state of each sub-region in the current planting area, and the value range is 0-1, the closer to 1, the more balanced the overall water distribution, and the water state of each sub-region is close to ideal; the closer to 0, the more uneven the water distribution, and the local water supplement regulation needs to be continued, is a set target ideal water deficit stress coefficient, and respectively represent the maximum and minimum of in all current sub-regions, is a weighted index, an index factor for non-linearly weighting the deviation degree of water deficit of each sub-region, and the value range is 1.5-2, is the total number of sub-regions;

[0099] If the calculated value is higher than the set balance threshold value, it indicates that the water distribution of the region tends to be balanced, and it is confirmed that the water supplement control is completed;If it is lower than the threshold, the next round of local fine-tuning action is started, and the overall water balance level is further improved.

[0100] Through the above steps, a precise drip irrigation control mechanism with real-time feedback and dynamic closed loop can be formed.

[0101] The present application can realize fine perception and dynamic differentiated compensation of the soil moisture state in the planting area, and break through the problem of one-size-fits-all drip irrigation management in the prior art, which cannot accurately regulate according to spatial heterogeneity. Through sub-region division and multi-level soil moisture monitoring, combined with feature engineering key index extraction and intelligent machine learning evaluation, early identification and zoned dynamic regulation of local water deficit stress state are realized, the balance of soil moisture distribution between edge rows and central rows is effectively improved, the consistency of large white kidney bean and angelica population growth is significantly improved, the occurrence probability of drought stress and waterlogging disease is reduced, and then the yield stability, quality consistency and economic benefit of the intercropping system are improved, and the sustainable popularization and application of the intercropping mode based on the principle of ecological niche complementation are promoted.

[0102] The above formulas are all dimensionless numerical calculations, the formula is obtained by software simulation of a large amount of data to obtain the latest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0103] The above only describes some exemplary embodiments of the present application by way of illustration, and it is needless to say that the described embodiments can be modified in various ways without departing from the spirit and scope of the present application for those skilled in the art. Therefore, the above figures and descriptions are illustrative in nature and should not be understood as limiting the scope of protection of the claims of the present application.

[0104] ​It should be noted that, in the present document, relational terms are used to convey a relationship of one entity or action to another entity or action. For example, without necessarily implying any actual relationship or order between entities or actions, the terms "first," "second," "top" and "bottom" are used to name different entities and actions, and are used to distinguish one entity or action from another entity or action, without necessarily conveying any actual relationship or order between such entities or actions. Furthermore, the terms "comprise," "include," and "have," and variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, includes, or has a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises... a," "includes... a," or "has... a" does not, without more constraints, foreclose the existence of additional identical elements other than the one listed or other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0105] It should be understood that the sequence numbers of the processes described above do not mean the execution sequence of the processes, and the execution sequence of the processes should be determined according to the functions and inherent logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0106] Those skilled in the art can clearly understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present document can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software mode depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0108] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0109] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0110] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0111] The foregoing merely describes certain exemplary embodiments of this application by way of illustration. Obviously, modifications and alterations can be made by those skilled in the art without departing from the spirit and scope of the application. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of the claims of the present application.

Claims

1. A method for interplanting large white kidney beans and angelica based on niche complementarity, characterized in that, The method comprises the following steps: First, according to the layout structure of crop planting, the intercropping area of large white kidney beans and angelica is divided into multiple independent management sub-areas according to the planting row area; Before the drip irrigation operation starts, for each sub-area divided, real-time collection of sub-area soil moisture data information is carried out through the soil moisture sensor array arranged at different depths; After preprocessing the collected sub-area soil moisture data information, a data set is established to form a sub-area water state analysis standardized data input source; Through feature engineering technology processing, key indicator features directly reflecting the stress state of sub-area soil water deficit are extracted from the data set, and the extracted key indicator features are comprehensively analyzed to quantify the current water loss degree of the sub-area; The key feature indicators after comprehensive analysis are input into the machine learning model trained based on historical soil moisture data in advance, and the soil water content state of the sub-area is intelligently evaluated in real time through the model to determine whether the soil is in a water deficit stress state; When it is identified that the current area soil is in a water deficit stress state, according to the water potential difference between the current area and other sub-areas, the flow regulating valve of each branch of the drip irrigation pipeline is dynamically adjusted to automatically increase the drip irrigation flow of the water deficit area and reduce the water supply intensity of the water suitable area, thereby realizing asynchronous and different amount irrigation compensation between areas and effectively completing the dynamic regulation and control of local water replenishment and overall water distribution balance.

2. The method for growing large white kidney beans and angelica in interplanting based on niche complementation according to claim 1, characterized in that, According to the layout structure of crop planting, the intercropping area of large white kidney beans and angelica is divided into multiple independent management sub-areas according to the planting row area, and the specific steps are as follows: Firstly, the geometric information and planting plan of the intercropping area are obtained, including crop type distribution, row spacing, plant spacing and field boundary coordinates; Subsequently, according to the actual planting row arrangement mode of large white kidney beans and angelica, combined with row spacing and field shape, the whole area is divided into multiple regular sub-areas according to the width of the row direction to ensure that each sub-area covers one or a group of complete intercropping rows; Next, the sub-areas divided are numbered and coded for management, and corresponding geographic information tags are established for subsequent data collection and spatial positioning of control instructions; Finally, according to the consistency of crop combination, spatial position and environmental conditions in each sub-area, the adjustment is checked to ensure that the internal management objectives of each sub-area are consistent, the boundaries are clear, and it is suitable for differential drip irrigation regulation and control.

3. The method for growing Macuna bean and Angelica by niche complementary intercropping according to claim 1, characterized in that, Through feature engineering technology processing, key indicator features directly reflecting the stress state of sub-area soil water deficit are extracted from the data set, and the extracted key indicator features are comprehensively analyzed to quantify the current water loss degree of the sub-area.

4. The method for growing large white kidney beans and angelica in interplanting based on niche complementation according to claim 3, characterized in that, The specific steps of generating the evaporation conduction limited reference value by comprehensively analyzing the evaporation conduction limited reference value in the detection window are as follows: Based on the soil moisture content measurement data of each detection depth point of the soil profile, the water gradient resistance factor between each adjacent layer is calculated in turn, and the calculation expression is as follows: wherein is the volumetric soil water content of the layer of the soil profile, is the volumetric soil water content of the layer of the soil profile, is the volumetric soil water content of the layer of the soil profile, i.e. the volumetric soil water content of the next layer, is a very small positive number set to avoid division by zero errors, is a water conduction directionality discrimination coefficient, is a water gradient retardation factor;​ Based on the cumulative amplitude of all moisture gradient resistance factors The degree of limitation of the overall moisture conduction of the profile is comprehensively calculated, and the evaporation conduction limitation reference value is generated, and the formula is as follows: , wherein, is an evapotranspiration conductance limited reference value, is the total number of soil profile detection depth layers, is a retardation strength amplification coefficient, is a hyperbolic tangent function.

5. The method according to claim 3, wherein the method is characterized in that, The specific steps of generating the root layer decoupling reference value by comprehensively analyzing the loss of synchronization between the surface layer water content and the root layer water content in the detection window are as follows: First, the real-time water content data of the surface layer soil and the root layer soil in the target sub-region are obtained, and based on the change rate of water content between adjacent sampling time, the surface layer water content change rate and the root layer water content change rate are calculated respectively, and the surface layer-root layer synchronization difference factor is defined, and the calculation formula is as follows: wherein, is a synchronization difference factor, is a surface soil water content change rate, is a root layer soil water content change rate, is a stabilization factor; Synchronization difference factors obtained by continuous sampling The nonlinear accumulation processing is performed to generate the root layer decoupling reference value, and the generation formula is as follows: In the formula, It is the root layer decoupling reference value. It is the first The synchronization difference factor is calculated from the second sampling. It is the total number of samples. These are non-linear weighting coefficients. It is the sensitivity adjustment coefficient. It is the natural base.

6. The method for growing large white kidney beans and angelica in an ecological niche complementary interplanting mode according to claim 3, characterized in that, The evaporation transmission limited reference value and the root layer decoupling reference value after comprehensive analysis are input into the machine learning model trained based on historical soil moisture data in advance, and the soil moisture deficit stress coefficient is generated through the model, and the soil moisture content state of the sub-region is intelligently evaluated in real time through the soil moisture deficit stress coefficient, and it is judged whether the soil is in water deficit stress state.

7. The method according to claim 6, wherein the method is characterized in that, When the soil moisture deficit stress coefficient generated by the real-time intelligent evaluation of the soil moisture content state of the sub-region through the machine learning model trained based on historical soil moisture data in advance is compared and analyzed with the pre-set soil moisture deficit stress coefficient reference threshold, it is judged whether the soil is in water deficit stress state, and the judgment logic is as follows: If the soil moisture deficit stress coefficient is greater than the pre-set soil moisture deficit stress coefficient reference threshold, it is judged that the soil is in water deficit stress state; if the soil moisture deficit stress coefficient is less than or equal to the pre-set soil moisture deficit stress coefficient reference threshold, it is judged that the soil is not in water deficit stress state.

8. The method according to claim 7, wherein the method is characterized in that, When it is identified that the current regional soil is in water deficit stress state, according to the water potential difference between the current region and other sub-regions, the flow regulating valve of each branch of the drip irrigation pipeline is dynamically adjusted, the drip irrigation flow of the water deficit region is automatically increased, and the water supply intensity of the water suitable region is reduced, so as to realize the specific steps of asynchronous and different amount irrigation compensation between regions as follows: Once a sub-region's soil is identified as being under water deficit stress, the soil water deficit stress coefficient is used as the basis for this process. Based on the difference from the reference threshold of the soil moisture deficit stress coefficient, a flow rate adjustment factor is constructed to dynamically adjust the drip irrigation flow rate. The calculation formula for the flow rate adjustment factor is as follows: In the formula, It is a flow adjustment factor. It is the water potential response sensitivity coefficient. It is a sub-region Soil moisture deficit stress coefficient It is the reference threshold for the soil moisture deficit stress coefficient. This is the basic drip irrigation flow rate; obtaining the flow adjustment factor corresponding to each sub-region After that, the initial drip irrigation flow set for the sub-region is dynamically corrected according to the flow adjustment factor, and the updated target drip irrigation flow is obtained, and the updating formula is as follows: wherein is the adjusted drip irrigation flow for a sub-area of the crop field, is the initial drip irrigation flow for a sub-area of the crop field; After completing the dynamic adjustment of the drip irrigation flow of each sub-region, the water distribution uniformity index of the whole planting region is calculated to evaluate the water supplement effect, and whether to trigger further fine tuning is decided according to the evaluation result, and the index calculation formula is as follows: In the formula, It is an indicator of the evenness of water distribution. It is the set target ideal water deficit stress coefficient. and Representing all current sub-regions The maximum and minimum values, It is a weighted index. This represents the total number of sub-regions; If the calculated value is higher than the set threshold value, it indicates that the regional water distribution tends to be balanced, and it is confirmed that the water supplement control is completed. If the calculated value is higher than the set threshold value, it indicates that the regional water distribution tends to be balanced, and it is confirmed that the water supplement control is completed. If it is lower than the threshold, the next round of local fine tuning action is started to further improve the overall water uniformity level.

Images