Rapid evaluation system and method for irrigation performance of drip irrigation system

Abstract

The invention relates to a rapid evaluation system and method for the irrigation performance of a drip irrigation system, and belongs to the technical field of agricultural irrigation. A capillary pressure remote transmission subsystem in the system is used for monitoring capillary pressure changes in the drip irrigation system in real time; the unmanned aerial vehicle remote sensing monitoring subsystem is used for acquiring remote sensing data of a drip irrigation system area; and the central processing unit is in communication connection with the two subsystems and is used for receiving and processing the pressure data and the remote sensing data and evaluating the irrigation performance of the drip irrigation system. The method comprises the following steps: vectorizing a drip irrigation system; arranging capillary pressure monitoring points, and monitoring capillary pressure in real time; acquiring remote sensing data by using the unmanned aerial vehicle; performing multi-scale analysis on the remote sensing data; inverting crop growth indexes; predicting the scale irrigation water quantity of the drip irrigation points; and evaluating the irrigation performance of different scales. According to the method, multi-level irrigation performance evaluation is realized, the irrigation non-uniformity source can be accurately identified, the coupling relationship between the hydraulic parameters and the crop growth parameters is established, and the evaluation efficiency and precision are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of agricultural irrigation engineering technology, and in particular to a rapid evaluation system and method for the uniformity of irrigation in a drip irrigation system that combines real-time capillary pressure monitoring with UAV remote sensing technology. Background Technology

[0002] Drip irrigation technology, as a highly efficient and water-saving irrigation method, has been widely used in field crops, facility agriculture, and orchards. Irrigation performance is a core indicator for evaluating the design and operation quality of drip irrigation systems, directly affecting water resource utilization efficiency and crop yield. Currently, the evaluation of drip irrigation system performance mainly adopts manual field testing methods. This involves manually collecting water output from several representative emitters on the capillary tubes during system operation and calculating indicators such as irrigation uniformity. This method has significant limitations: First, the testing process is time-consuming and labor-intensive, typically requiring multiple workers to work continuously for several hours, and can only be conducted during irrigation; second, the number of test points is limited, making it difficult to comprehensively reflect the irrigation status of the entire system, especially for large-scale drip irrigation systems where the test representativeness is insufficient; third, existing evaluation methods cannot match the system's hydraulic performance with the spatial distribution of crop water requirements, leading to discrepancies between the evaluation results and actual irrigation effects.

[0003] In recent years, with the development of sensor and wireless communication technologies, some studies have attempted to apply pressure sensors to drip irrigation system monitoring. However, these technologies mainly focus on network pressure monitoring and early warning, failing to establish an effective correlation with irrigation uniformity evaluation and neglecting the impact of crop growth status on irrigation performance evaluation. On the other hand, UAV remote sensing technology has been widely used in agriculture, providing high-resolution spatial information on crop growth parameters. Nevertheless, existing research largely focuses on single-technology applications, failing to organically combine real-time capillary pressure monitoring with UAV remote sensing technology to achieve multi-level irrigation performance evaluation from system scale, unit scale to point scale.

[0004] Furthermore, existing evaluation methods for drip irrigation systems struggle to identify the sources of irrigation unevenness, failing to distinguish between system design issues, network hydraulic problems, and differences in field conditions. This scale effect is particularly pronounced in large-scale drip irrigation systems, where single-scale evaluation methods often lead to erroneous optimization decisions. Therefore, the industry urgently needs a comprehensive evaluation method and system capable of rapidly and accurately assessing the irrigation performance of drip irrigation systems and identifying the sources of unevenness, in order to guide the optimal design and operation management of drip irrigation systems.

[0005] Geographic Information System (GIS) technology has been applied in irrigation engineering planning, but it still suffers from low data acquisition and processing efficiency in real-time evaluation of irrigation performance. Existing technologies cannot acquire irrigation performance data for large-scale drip irrigation systems in a short time, especially when timely adjustments to irrigation strategies are needed during critical crop growth periods. The insufficient timeliness of traditional methods has become a key factor restricting the implementation of precision irrigation. Meanwhile, how to effectively integrate spatial information, hydraulic data, and crop growth parameters to construct a multi-scale irrigation performance evaluation model remains a technical challenge in the field of irrigation engineering. Summary of the Invention

[0006] This invention addresses the shortcomings of existing technologies by providing a rapid evaluation system and method for the irrigation performance of drip irrigation systems.

[0007] To achieve the above-mentioned objectives, the technical solution adopted by the present invention is as follows:

[0008] A rapid evaluation system for irrigation performance of a drip irrigation system, the system comprising:

[0009] The capillary pressure remote transmission subsystem is used to monitor capillary pressure changes in the drip irrigation system in real time.

[0010] The UAV remote sensing monitoring subsystem is used to acquire remote sensing data of the drip irrigation system area;

[0011] The central processing unit communicates with the capillary pressure transmission subsystem and the UAV remote sensing monitoring subsystem to receive and process pressure data and remote sensing data, and to evaluate the irrigation performance of the drip irrigation system.

[0012] The central processing unit is configured via software to include a pressure data receiving module, a UAV remote sensing monitoring data processing module, and a system performance calculation module. The pressure data receiving module is used to receive capillary pressure data, the UAV remote sensing monitoring data processing module is used to process remote sensing data, and the system performance calculation module is used to calculate irrigation performance parameters.

[0013] Furthermore, the capillary pressure remote transmission subsystem includes a pressure sensor, a data acquisition unit, and a wireless transmission device. The pressure sensor is used to collect capillary pressure data in the drip irrigation system, and the wireless transmission device transmits the collected pressure data to the central processing unit.

[0014] Furthermore, the UAV remote sensing monitoring subsystem includes a UAV platform, an airborne dynamic carrier phase differential module (RTK), an airborne visible light camera, and a multispectral camera. The airborne dynamic carrier phase differential module (RTK) is used to provide high-precision positioning, and the airborne visible light camera and multispectral camera are used to acquire digital ground elevation (DEM), digital surface model (DSM), and multispectral image data of the drip irrigation area.

[0015] Furthermore, the central processing unit is equipped with a geographic information processing software module, which is used to perform spatial data processing, remote sensing image analysis and irrigation performance calculation of the drip irrigation system, and generate an irrigation performance evaluation report.

[0016] This invention also discloses a method for rapid evaluation of the irrigation performance of a drip irrigation system, the method comprising the following steps:

[0017] 1) Construct a drip irrigation performance evaluation system, including a capillary pressure remote transmission subsystem, an unmanned aerial vehicle (UAV) remote sensing monitoring subsystem, and a central processing unit;

[0018] 2) Vectorize the layout of the drip irrigation system network and the boundaries of irrigation units to generate a digital map;

[0019] 3) Select a typical irrigation unit, set up capillary pressure monitoring points in the typical irrigation unit, monitor the capillary pressure in real time, calculate the real-time flow of the emitter according to the flow-pressure relationship of the emitter, and obtain the irrigation volume through time integration.

[0020] 4) Measure crop plant height and leaf area index at the typical irrigation unit monitoring points selected in step 3);

[0021] 5) Use the UAV remote sensing monitoring subsystem to acquire digital ground elevation (DEM), digital surface model (DSM), and multispectral image data of the drip irrigation system area;

[0022] 6) Based on the remote sensing data obtained in step 5), calculate crop growth parameters at the system scale, unit scale, and point scale;

[0023] 7) Based on the crop growth parameters calculated in step 6), invert the crop growth indices at the drip irrigation point scale;

[0024] 8) Using crop height and leaf area index as independent variables, construct an irrigation volume prediction model to predict irrigation volume at the drip irrigation point scale;

[0025] 9) Based on the predicted and measured irrigation volumes, evaluate the irrigation performance of the drip irrigation system at different scales, including calculating the irrigation uniformity coefficient at the system scale and analyzing the sources of irrigation non-uniformity.

[0026] Furthermore, in step 2), when there is no plan of the drip irrigation system, use cross-platform mapping software to draw the various elements of the drip irrigation system, export them as KML or KMZ format, and then import them into the geographic information system software for symbolization settings; when there is a plan of the drip irrigation system, use computer-aided design software to calibrate the information of each element, and import them into the geographic information system software for coordinate transformation and symbolization settings.

[0027] Further, in step 3), multiple irrigation units at different distances from the water source are selected as typical units. Multiple capillary pipes are selected on the branch pipes of each typical unit, and multiple pressure measuring points are evenly arranged on each capillary pipe. The data from the pressure measuring points are used to calculate the uniformity of irrigation.

[0028] Further, in step 7), crop height is inverted by the difference between the digital surface model (DSM) and the baseline digital ground elevation (DEM), and corrected by a linear regression model; vegetation index is calculated based on multispectral data, the spectral variable with the highest correlation to leaf area index is selected, and a leaf area index prediction model is constructed using machine learning algorithms.

[0029] Furthermore, in step 8), the constructed irrigation volume prediction model is a multiple regression model, which uses the predicted values ​​of crop plant height and leaf area index as independent variables to spatially estimate the grid irrigation volume in all irrigation units of the system.

[0030] Further, in step 9), the system-scale irrigation uniformity coefficient is calculated using the Christensen uniformity coefficient; the intra-unit variance importance index and inter-unit variance importance index are calculated using the variance decomposition principle; the sources of irrigation non-uniformity are analyzed based on the ratio of the intra-unit variance importance index and the inter-unit variance importance index, including: when the intra-unit variance importance index is greater than 70%, intra-unit non-uniformity is the main cause of system non-uniformity; when the inter-unit variance importance index is greater than 70%, inter-unit non-uniformity is the main cause of system non-uniformity; when the ratio is close to 50 / 50, optimization needs to be carried out across all scales of the system; the system uniformity level is determined based on the irrigation uniformity coefficient and variance importance index, and optimization suggestions are proposed.

[0031] Compared with the prior art, the advantages of the present invention are as follows:

[0032] 1. Significantly improve evaluation efficiency: By integrating capillary pressure remote monitoring and UAV remote sensing technology, the evaluation time is greatly shortened, reducing the traditional manual testing process that takes several days to be completed in a few hours. The evaluation efficiency is significantly improved, and it is especially suitable for the rapid diagnosis of large drip irrigation systems.

[0033] 2. Achieve multi-scale irrigation performance evaluation: Break through the limitations of traditional single-scale evaluation, and simultaneously achieve irrigation performance evaluation at the system scale, unit scale and point scale, comprehensively reflecting the working status of the drip irrigation system under different spatial resolutions, and providing a scientific basis for precision irrigation management.

[0034] 3. Accurately identify the sources of uneven irrigation: By using the principle of variance decomposition to calculate the variance importance index within a unit and the variance importance index between units, it can accurately distinguish whether uneven irrigation is caused by system design defects, pipeline hydraulic problems, or differences in field conditions, providing a clear direction for targeted optimization.

[0035] 4. Establish a water-crop coupling evaluation system: Innovatively establish a spatial correspondence between the water output status of the irrigation device and the crop growth status (plant height, leaf area index). The evaluation results not only reflect the hydraulic performance of the system, but also reflect the degree of matching between the irrigation effect and the crop water requirement, making the evaluation results more agronomically significant.

[0036] 5. Provide continuous spatial distribution information: Obtain continuous spatial data of drip irrigation areas through UAV remote sensing technology, overcome the problems of discreteness and insufficient representativeness of traditional point sampling, generate a spatial distribution map of irrigation performance, and intuitively display the weak links of the system.

[0037] 6. Improve evaluation accuracy and reliability: cross-validate pressure monitoring data and remote sensing inversion data to reduce the uncertainty of a single data source; construct leaf area index and irrigation volume prediction models through machine learning algorithms to improve spatial interpolation accuracy and make the evaluation results more reliable.

[0038] 7. Support digital irrigation management: Build a digital twin of the drip irrigation system based on geographic information system to realize the visualization and spatial query of evaluation results, and provide a data foundation for the management of historical data of irrigation system, analysis of performance change trends and long-term optimization decision-making.

[0039] 8. Lowering the technical threshold for evaluation: The systematic and standardized evaluation process and software support reduce the reliance on professional and technical personnel for irrigation performance evaluation, enabling grassroots irrigation managers to conduct scientific evaluations and promoting the widespread application of precision irrigation technology.

[0040] 9. Wide applicability: It is suitable for drip irrigation systems of different scales and crop types (field crops, fruit trees, and facility agriculture), and can adapt to complex terrain conditions, with good promotion value and application prospects.

[0041] 10. Water and management cost savings: By accurately identifying areas and causes of uneven irrigation, targeted modifications and operational optimizations can be guided, effectively improving the irrigation uniformity coefficient, reducing ineffective irrigation water use, extending the system's service life, and generating significant economic and ecological benefits. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of the rapid evaluation method for irrigation performance of a drip irrigation system in an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram illustrating the construction of a rapid evaluation system for drip irrigation systems in an embodiment of the present invention;

[0045] Figure 3 These are the vectorized drip irrigation system plan layout diagram and typical unit measuring point layout diagram in the embodiments of the present invention;

[0046] Figure 4 This is a diagram showing the measured irrigation volume at a typical unit measuring point of the drip irrigation system in this embodiment of the invention.

[0047] Figure 5 This is a remote sensing data distribution map (DEM / DSM / vegetation index data) of the drip irrigation system in this embodiment of the invention.

[0048] Figure 6 This is a schematic diagram of irrigation unit grid subdivision and remote sensing data extraction in an embodiment of the present invention;

[0049] Figure 7 This is a diagram illustrating the process of constructing a crop plant height prediction model based on measured plant height data from monitoring points in an embodiment of the present invention.

[0050] Figure 8 This is a diagram illustrating the process of constructing a crop leaf area index prediction model based on multispectral data and measured leaf area index data in an embodiment of the present invention.

[0051] Figure 9 This is a graph showing the predicted irrigation volume at the grid scale of the drip irrigation unit, based on predicted plant height and leaf area index, in an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] like Figure 1As shown, this invention provides a rapid evaluation method for the irrigation performance of a drip irrigation system, comprising nine steps: 1) Construction of a drip irrigation performance evaluation system; 2) Planar layout of the drip irrigation system network and vectorization of irrigation unit boundaries; 3) Monitoring of capillary pressure and calculation of irrigation volume in typical irrigation units; 4) Measurement of crop height and leaf area index at monitoring points in typical irrigation units; 5) Acquisition of remote sensing data at the drip irrigation system scale; 6) Analysis of remote sensing data at the drip irrigation system scale, unit scale, and point scale; 7) Remote sensing inversion of crop growth indicators at the drip irrigation point scale; 8) Prediction of irrigation volume at the drip irrigation point scale; 9) Evaluation of irrigation performance at different scales of drip irrigation.

[0054] This embodiment uses a drip irrigation system located in Xinjiang as an example. The crop variety considered is cotton, and drip irrigation is used for cotton irrigation and fertilization. The drip irrigation system includes one water source, one main pipe, two branch pipes, and 12 irrigation units. Each irrigation unit is 90 m long and 60 m wide, with an irrigation area of ​​0.54 hm². 2 The system covers a total area of ​​6.48 hm². 2 The drip irrigation tape selected is an inlaid patch type drip irrigation tape, with a water emitter spacing of 20 cm and a capillary tube spacing of 100 cm.

[0055] The first step in this embodiment is to construct a rapid evaluation system for this drip irrigation system.

[0056] like Figure 2 As shown, the system comprises three parts: a capillary pressure remote transmission subsystem 201, a UAV remote sensing monitoring subsystem 202, and a central processing unit 203. The capillary pressure remote transmission subsystem 201 consists of a pressure acquisition module 201-1 and a data transmission module 202-2. The UAV remote sensing monitoring subsystem 202 includes a UAV system 202-1, an airborne dynamic carrier phase differential module (RTK) 202-2, and an airborne visible light and multispectral camera 202-3. The central processing unit 203 includes a pressure data receiving module 203-1 and a UAV remote sensing monitoring data processing and system performance calculation module 203-2. The central processing unit 203 is equipped with cross-platform mapping software (such as Aowei Maps), geographic information system software (such as ArcGIS), and data calculation software (such as Excel) for data collection, processing, and calculation.

[0057] Step 2: Vectorization of the drip irrigation system network layout and irrigation unit boundaries.

[0058] Since this system lacks a floor plan of the drip irrigation system, the point and line tools in the cross-platform mapping software (Aowei Map) on the central processing unit are used to draw the floor plan of the drip irrigation system. Figure 3The process involves several steps: 1) Using the "Draw Points" tool to draw elements such as water source 301, outlet pile 302, and measuring point 303; using the "Draw Lines" tool to draw elements such as main pipe 304, branch pipe 305, and branch pipe 306 along the pipeline path; and using the "Draw Polygons" tool to draw irrigation unit element 307. After each element is drawn, its corresponding attribute values ​​are set. 2) Drip Irrigation System Data Export: Check the integrity of the drawn drip irrigation system element data and export the data in KML or KMZ format. 3) Drip Irrigation System Data Conversion: Import the exported drip irrigation system data into the ArcGIS platform, symbolize different elements, and create a drip irrigation system layout map containing different elements and irrigation unit boundaries, as shown in the example below. Figure 3 As shown.

[0059] Step 3: Monitoring capillary pressure and calculating irrigation volume in typical irrigation units.

[0060] Based on the distance from the water source, three irrigation units were selected: near, middle, and far, numbered 1, 5, and 9 respectively. Three capillary tubes were evenly selected on the branch pipes of each unit, and four capillary pressure measuring points were evenly arranged on each capillary tube. A capillary pressure remote monitoring device 201-1 was installed here, with the sensor having data remote transmission capability, and data was collected at 5-minute intervals. During irrigation, the capillary pressure changes were measured in real time, and the real-time flow rate of the emitters was calculated using the flow-pressure relationship within the system. In this embodiment, this relationship was provided by the drip irrigation tape manufacturer as follows:

[0061]

[0062] In the formula: q is the actual flow rate of the irrigator, L / h; K is the flow coefficient, which is 0.52 in this embodiment; P is the pressure head, m; and x is the flow index of the irrigator, which is x=0.50 in this embodiment.

[0063] Because capillary pressure may change over time during actual irrigation, the irrigation depth D (mm) at a specific monitoring point is obtained by integrating the values ​​over the irrigation period, as shown in the following formula:

[0064]

[0065] In the formula: t0 is the irrigation start time, h; t1 is the irrigation end time, h; S e The spacing between the water emitters is in centimeters; in this study, it is 20 cm. l The distance between capillaries is in cm, which is 100 cm in this study.

[0066] In a specific irrigation process, the irrigation duration was 3 hours. The irrigation water depth at all capillary pressure measuring points was calculated at 5-minute intervals, revealing an irrigation water volume range of 20.5–35.5 mm at different emitter locations. (Details are as follows...) Figure 4 As shown.

[0067] Step 4: Measurement of crop height and leaf area index at monitoring points in typical irrigation units.

[0068] Around the monitoring points established in step three, a certain number of crops were selected three times during the early, middle, and late stages of the crop irrigation season to measure crop height (H, cm) and leaf area (LAI). Crop height was measured using measuring tools such as a ruler; the leaf area index was obtained by directly measuring the length and width of all leaves of the plant under test using a ruler. During the middle of the crop growth period, 15 representative leaves of different sizes were selected, and the length and width of each leaf were measured. Then, a multi-functional leaf area meter was used to scan the actual area of ​​each leaf, establishing a linear empirical relationship between the actual leaf area and the product of leaf length and width: y = ax + b (where y represents the actual leaf area, x represents the measured product of leaf length and width, and a and b are regression coefficients). The actual leaf area was then calculated using this empirical formula, and finally, the leaf area index (LAI) was obtained by dividing the obtained crop leaf area by the crop's land area.

[0069] Step 5: Remote Sensing Data Acquisition at the Drip Irrigation System Scale. Based on the configured UAV remote sensing monitoring subsystem including an RTK module, visible light, and multispectral cameras, remote sensing data will be collected during a clear, windless, and cloudless daytime at the following times: before crop sowing, early irrigation season, mid-irrigation season, and late irrigation season. The data collection time will be from 11:00 AM to 1:00 PM on the selected day. Before crop sowing, the data will primarily be used to acquire the bare land baseline digital elevation (DEM). During the early, mid, and late irrigation seasons, the data will be acquired for crop canopy digital surface elevation (DSM) and spectral data in the green (560 nm), red (650 nm), infrared (730 nm), and near-infrared (860 nm) bands. Specific details are as follows... Figure 5 As shown.

[0070] Step 6: Remote sensing data analysis at the drip irrigation system scale, unit scale, and point scale. The remote sensing image processing platform installed in the central processing unit is used to perform radiometric correction and image stitching on the UAV aerial images.

[0071] ①System-scale data analysis: The corrected and stitched images are imported into the ArcGIS platform. A mask area is drawn according to the boundary of the drip irrigation system. The original multispectral images are masked to preserve the images within the experimental study area and obtain basic remote sensing data at the system scale.

[0072] ② Unit-scale data analysis. Each drip irrigation unit within the system is uniquely numbered. Using the ArcGIS platform, vector segmentation is performed based on the unit number attribute. Batch processing tools are then used to create a grid for each irrigation unit, with a recommended grid size of 5 m × 5 m. The grid is then labeled with G. i-j (Indicates the j-th grid of the i-th unit), specifically as follows Figure 6 As shown.

[0073] ③ Point-scale data analysis. Centered on the coordinates of each monitoring point in a typical irrigation unit, the baseline digital ground elevation (DEM), digital surface model (DSM), and mean spectral reflectance of the pixels surrounding the observation point are extracted using programming software (such as Python) in a sliding window manner. The window is traversed according to its start and end positions, and the mean value of the window data is calculated. This mean value is used as the DEM, DSM, and spectral reflectance values ​​at the sampling point.

[0074] Step 7: Remote sensing inversion of crop growth indicators at the drip irrigation point scale. The crop height at the monitoring point is inverted by the difference between the crop digital surface model (DSM) at a typical unit monitoring point and the baseline digital ground elevation (DEM), as shown in the following formula.

[0075]

[0076] In the formula: This represents the crop plant height inversion value at the i-th monitoring point; The digital surface height of the crop obtained by remote sensing at the i-th monitoring point; Let be the elevation of the bare ground obtained by remote sensing at the i-th monitoring point.

[0077] Based on measured data, a linear regression model was used to correct the remotely sensed plant height, resulting in the predicted plant height at point i. As shown in the following formula.

[0078]

[0079] In the formula: a and b are regression coefficients; H i实测 The crop height was measured at the i-th monitoring point. In this embodiment, the crop height was retrieved as follows: Figure 7 As shown.

[0080] Several typical spectral vegetation indices (VIs) were calculated for monitoring points in typical irrigation units. These included Normalized Difference Vegetation Index (NDVI), Normalized Green Light Vegetation Index (GNDVI), Normalized Red Edge Vegetation Index (NDRE), Optimized Soil-Regulated Vegetation Index (OSAVI), and Ratio Vegetation Index (RVI). Pearson correlation analysis was performed between the calculated spectral variables and the crop leaf area index (LAI). The five spectral variables with the highest correlation to the LAI were selected. Based on these variables, methods such as random forest regression, support vector machine, and neural networks were used to construct a LAI prediction model based on spectral indices. In this embodiment, the correlation between the crop leaf area index and the spectral indices is as follows: Figure 8 As shown, a random forest regression algorithm is used to construct an LAI prediction model.

[0081] When building the model, the first step is to combine the spectral index and LAI measured value dataset D. total Divided into training set D train and verification set D test The specific formula is as follows:

[0082]

[0083]

[0084]

[0085] In the formula: N is the number of datasets; It is the first The vegetation index vector of each sample; is the corresponding true LAI value; J is the number of training sets.

[0086] Based on the training set data, establish a parameter set ( The mapping function f of the vegetation index vector is given by the vegetation index vector. Predict crop LAI and define the loss function during training. ,by Seeking the optimal parameter set based on the principle of minimization. .

[0087]

[0088]

[0089] In the formula: This is a predicted value for the LAI index; This is the set of parameters for the prediction model, which varies depending on the model used.

[0090] Using test dataset D testThe generalization ability of the LAI prediction model is evaluated using metrics including root mean square error (RMSE) and coefficient of determination R. 2 .

[0091]

[0092]

[0093] In the formula: This is the average of the measured LAI values.

[0094] The crop leaf area index prediction effect in this embodiment is as follows: Figure 8 As shown.

[0095] Step 8: Irrigation Water Quantity Prediction at Drip Irrigation Point Scale. Based on the constructed crop plant height and leaf area index (LAI) inversion model, crop plant height and LAI are inverted at all monitoring points and unit grids within the drip irrigation system. Furthermore, using plant height and LAI prediction values ​​as independent variables, the predicted values ​​of irrigation water quantity and crop growth indicators at monitoring points are constructed using the method described in Step 7. and The estimation model is as follows. Similarly, the optimal parameter set is sought by defining a loss function. .

[0096]

[0097] In the formula: This is the parameter set for the prediction model.

[0098] The irrigation volume prediction model based on crop growth indicators was used to predict the irrigation volume D in all grids within all irrigation units of the system. ij The irrigation amount of the j-th grid in the i-th unit is estimated.

[0099] The irrigation depth prediction effect and typical unit distribution in this embodiment are as follows: Figure 9 As shown.

[0100] Step 9: Performance evaluation of drip irrigation at different scales. The system-scale irrigation uniformity coefficient (CU) is calculated using the Christensen uniformity coefficient. system As shown in the following style:

[0101]

[0102] Where: N unit N represents the number of irrigation units in the system. i-grid Let i be the number of grids to be divided in the i-th irrigation unit; Estimate the irrigation amount for the j-th grid in the i-th irrigation unit; The average irrigation amount is estimated for all grids in the system.

[0103] The variance decomposition principle is further used to evaluate the irrigation uniformity of the drip irrigation system at both the unit and system scales to identify the sources of irrigation non-uniformity. The specific calculation process is as follows:

[0104]

[0105]

[0106]

[0107]

[0108] In the formula: The total variance of irrigation volume at the system scale; The variance of irrigation volume within the unit; PI represents the variance of irrigation volume between units. in-unit PI is the importance index for intra-cell variance. be-unit This is the variance importance index between units.

[0109] The system performance evaluation indicators are determined as follows:

[0110] CU system ≥90%, the system uniformity is registered as "excellent";

[0111] 80≤CU system <90%, system uniformity is registered as "good";

[0112] 70≤CU system <80%, system uniformity is registered as "moderate";

[0113] 70≤CU system If the uniformity is less than 80%, the system uniformity is recorded as "poor".

[0114] The sources of uneven irrigation in the system are analyzed as follows:

[0115] PI in-unit >70% unevenness within irrigation units is the main cause of unevenness in the system. Key factors to be checked include capillary pipe layout, sprinkler blockage, and terrain influence.

[0116] PI be-unit >70% uneven irrigation between irrigation units is the main cause of uneven system performance, which needs to be addressed by factors such as system design, operating conditions, and tank group division.

[0117] PI in-unit / PI be-unit With a ratio of approximately 50 / 50, the uneven impact of irrigation unit scale and the units on the system is basically balanced, requiring comprehensive optimization across all scales of the system.

[0118] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0120] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0121] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A rapid evaluation system for the irrigation performance of a drip irrigation system, characterized in that, The system includes: The capillary pressure remote transmission subsystem is used to monitor capillary pressure changes in the drip irrigation system in real time. The UAV remote sensing monitoring subsystem is used to acquire remote sensing data of the drip irrigation system area; The central processing unit communicates with the capillary pressure transmission subsystem and the UAV remote sensing monitoring subsystem to receive and process pressure data and remote sensing data, and to evaluate the irrigation performance of the drip irrigation system. The central processing unit is configured via software to include a pressure data receiving module, a UAV remote sensing monitoring data processing module, and a system performance calculation module. The pressure data receiving module is used to receive capillary pressure data, the UAV remote sensing monitoring data processing module is used to process remote sensing data, and the system performance calculation module is used to calculate irrigation performance parameters.

2. The rapid evaluation system for irrigation performance of a drip irrigation system according to claim 1, characterized in that, The capillary pressure remote transmission subsystem includes a pressure sensor, a data acquisition unit, and a wireless transmission device. The pressure sensor is used to collect capillary pressure data in the drip irrigation system, and the wireless transmission device transmits the collected pressure data to the central processing unit.

3. The rapid evaluation system for irrigation performance of a drip irrigation system according to claim 1, characterized in that, The UAV remote sensing monitoring subsystem includes a UAV platform, an airborne dynamic carrier phase difference module (RTK), an airborne visible light camera, and a multispectral camera. The airborne dynamic carrier phase difference module (RTK) is used to provide high-precision positioning, and the airborne visible light camera and multispectral camera are used to acquire digital ground elevation (DEM), digital surface model (DSM), and multispectral image data of the drip irrigation area.

4. The rapid evaluation system for irrigation performance of a drip irrigation system according to claim 1, characterized in that, The central processing unit is equipped with a geographic information processing software module, which is used to perform spatial data processing, remote sensing image analysis, and irrigation performance calculation of the drip irrigation system, and generate an irrigation performance evaluation report.

5. A method for rapid evaluation of irrigation performance of a drip irrigation system, characterized in that, The method includes the following steps: 1) Construct a drip irrigation performance evaluation system, including a capillary pressure remote transmission subsystem, an unmanned aerial vehicle (UAV) remote sensing monitoring subsystem, and a central processing unit; 2) Vectorize the layout of the drip irrigation system network and the boundaries of irrigation units to generate a digital map; 3) Select a typical irrigation unit, set up capillary pressure monitoring points in the typical irrigation unit, monitor the capillary pressure in real time, calculate the real-time flow of the emitter according to the flow-pressure relationship of the emitter, and obtain the irrigation volume through time integration. 4) Measure crop plant height and leaf area index at the typical irrigation unit monitoring points selected in step 3); 5) Use the UAV remote sensing monitoring subsystem to acquire digital ground elevation (DEM), digital surface model (DSM), and multispectral image data of the drip irrigation system area; 6) Based on the remote sensing data obtained in step 5), calculate crop growth parameters at the system scale, unit scale, and point scale; 7) Based on the crop growth parameters calculated in step 6), invert the crop growth indices at the drip irrigation point scale; 8) Using crop height and leaf area index as independent variables, construct an irrigation volume prediction model to predict irrigation volume at the drip irrigation point scale; 9) Based on the predicted and measured irrigation volumes, evaluate the irrigation performance of the drip irrigation system at different scales, including calculating the irrigation uniformity coefficient at the system scale and analyzing the sources of irrigation non-uniformity.

6. The method for rapid evaluation of irrigation performance of a drip irrigation system according to claim 5, characterized in that, In step 2), when there is no plan of the drip irrigation system, use cross-platform mapping software to draw the various elements of the drip irrigation system, export them as KML or KMZ format, and then import them into the geographic information system software for symbolization settings; when there is a plan of the drip irrigation system, use computer-aided design software to calibrate the information of each element, and import them into the geographic information system software for coordinate transformation and symbolization settings.

7. The method for rapid evaluation of irrigation performance of a drip irrigation system according to claim 5, characterized in that, In step 3), multiple irrigation units at different distances from the water source are selected as typical units. Multiple capillary pipes are selected on the branch pipes of each typical unit, and multiple pressure measuring points are evenly arranged on each capillary pipe. The data from the pressure measuring points are used to calculate the irrigation uniformity.

8. The method for rapid evaluation of irrigation performance of a drip irrigation system according to claim 5, characterized in that, In step 7), crop height is inverted by the difference between the digital surface model (DSM) and the baseline digital ground elevation (DEM), and corrected by a linear regression model. Based on multispectral data, vegetation index is calculated, and the spectral variable with the highest correlation to leaf area index is selected. A leaf area index prediction model is constructed using machine learning algorithms.

9. The method for rapid evaluation of irrigation performance of a drip irrigation system according to claim 5, characterized in that, In step 8), the constructed irrigation volume prediction model is a multiple regression model, which uses the predicted values ​​of crop height and leaf area index as independent variables to spatially estimate the grid irrigation volume in all irrigation units of the system.

10. The method for rapid evaluation of irrigation performance of a drip irrigation system according to claim 5, characterized in that, In step 9), the system-scale irrigation uniformity coefficient is calculated using the Christensen uniformity coefficient. The importance index of intra-unit variance and the importance index of inter-unit variance are calculated using the principle of variance decomposition. The sources of irrigation unevenness are analyzed based on the ratio of these two indices, including: when the intra-unit variance importance index is greater than 70%, unevenness within irrigation units is the main cause of system unevenness; when the inter-unit variance importance index is greater than 70%, unevenness between irrigation units is the main cause of system unevenness; when the ratio is close to 50 / 50, optimization across all scales of the system is necessary; and the system's uniformity level is determined based on the irrigation uniformity coefficient and variance importance index, with optimization suggestions proposed.

Images