Water and fertilizer intelligent analysis method and system based on farmland regionalization crop yield increase

Abstract

The invention relates to the technical field of intelligent water and fertilizer analysis, in particular to an intelligent water and fertilizer analysis method and system based on farmland regional crop yield increase. The method comprises the following steps: acquiring structure data of a farmland area and extracting the flow direction of irrigation water, deploying a sensor to monitor the farmland state, and generating farmland state data of an irrigation basin; crop form images are collected through electronic monitoring equipment and water flow direction data, the leaf yellowing and curling degree is evaluated, and the soil volume moisture saturation is extracted. According to the soil moisture data, nutrient element content change is extracted, the nutrient leaching loss gradient is quantified, and soil nitrogen circulation abnormity is further simulated; and finally, performing intelligent water and fertilizer dosage controlled release analysis on the leaf yellowing and curling degree based on the nitrogen circulation abnormal data, and sending a result to a terminal to improve the per unit area yield of crops. The water and fertilizer intelligent analysis technology is optimized, so that the water and fertilizer intelligent analysis technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent water and fertilizer analysis, and particularly to an intelligent water and fertilizer analysis method and system for improving crop yield per unit area based on farmland regionalization. Background Art

[0002] In recent years, with the rapid development of technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence, the intelligent management of agriculture has made great progress. Technologies such as farmland monitoring based on sensors, crop growth data collection, and precise water and fertilizer regulation have been gradually applied to agricultural production. By real-time monitoring data such as soil, climate, and crop growth status, and precisely adjusting the usage amount of water and fertilizer, it can not only improve crop yield per unit area, but also effectively reduce resource waste, reduce environmental pollution, and achieve sustainable agricultural production. Especially in the intelligent analysis of water and fertilizer, previous water and fertilizer management methods were mostly based on unified fertilization standards, ignoring the differences in different regions, different crops, and different soils. This way often leads to waste of water and fertilizer resources and even has a negative impact on the environment. The intelligent water and fertilizer analysis method for improving crop yield per unit area based on farmland regionalization can perform differential water and fertilizer management according to factors such as the characteristics of different regions in the farmland, crop requirements, and soil conditions. Through comprehensive analysis of data such as the flow direction of irrigation water, soil moisture, nutrient element content, and crop growth status, combined with intelligent control technology, precise regulation of water and fertilizer usage can be achieved. It can not only increase crop yield per unit area, but also reduce the input cost of water and fertilizer, reduce unnecessary resource consumption, and at the same time avoid pollution to the environment caused by excessive fertilization, promoting the green and sustainable development of agriculture. However, the traditional intelligent water and fertilizer analysis method for improving crop yield per unit area based on farmland regionalization cannot accurately analyze the nutrient loss in the soil, resulting in a large error in the use of water and fertilizer management. Summary of the Invention

[0003] Based on this, it is necessary to provide an intelligent water and fertilizer analysis method and system for improving crop yield per unit area based on farmland regionalization to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent water and fertilizer analysis method for improving crop yield per unit area based on farmland regionalization, the method includes the following steps: Step S1: Obtain farmland regional structure data; extract the irrigation water flow direction from the farmland regional structure data to obtain farmland irrigation water flow direction data; deploy sensors in multiple directions based on the farmland irrigation water flow direction data, and perform real-time monitoring of the farmland state in the irrigation basin, thereby generating farmland state monitoring data in the irrigation basin; Step S2: Through an electronic monitoring device, and based on the data of the flow direction of farmland irrigation water, collect the morphological images of crops to obtain the morphological images of crops in the water flow direction area; evaluate the degree of yellowing and curling of the leaves in the morphological images of crops in the water flow direction area to obtain the data on the degree of yellowing and curling of the leaves; according to the data on the degree of yellowing and curling of the leaves, extract the soil volume water saturation of the crops with yellowing and curling leaves from the farmland state monitoring data of the irrigation basin to obtain the soil volume water saturation of the crops with yellowing and curling leaves. Step S3: According to the soil volume water saturation, extract the change data of the nutrient element content from the farmland state monitoring data of the irrigation basin to obtain the change data of the soil nutrient element content; quantify the nutrient leaching loss gradient for the change data of the soil nutrient element content to obtain the nutrient leaching loss gradient data; based on the nutrient leaching loss gradient data, simulate and quantify the nitrogen cycle anomaly to obtain the soil nitrogen cycle anomaly data. Step S4: Based on the soil nitrogen cycle anomaly data, conduct an intelligent controlled release analysis of the soil water and fertilizer application amount for the data on the degree of yellowing and curling of the leaves to obtain the intelligent controlled release data of the soil water and fertilizer application amount, and send the intelligent controlled release data of the soil water and fertilizer application amount to the terminal to perform the intelligent analysis of water and fertilizer for improving the crop yield per unit area.

[0005] Preferably, step S2 includes the following steps: Step S21: Through an electronic monitoring device, and based on the data of the flow direction of farmland irrigation water, collect the morphological images of crops to obtain the morphological images of crops in the water flow direction area. Step S22: Identify the growth inhibition distribution in the morphological images of crops in the water flow direction area to obtain the crop growth inhibition distribution data. Step S23: Based on the crop growth inhibition distribution data, evaluate the degree of yellowing and curling of the leaves in the morphological images of crops in the water flow direction area to obtain the data on the degree of yellowing and curling of the leaves. Step S24: According to the data on the degree of yellowing and curling of the leaves, extract the soil volume water saturation of the crops with yellowing and curling leaves from the farmland state monitoring data of the irrigation basin to obtain the soil volume water saturation of the crops with yellowing and curling leaves.

[0006] Preferably, step S3 includes the following steps: Step S31: Based on the soil volume water saturation, calculate the soil particle dispersion density to obtain the soil particle dispersion density data. Step S32: According to the soil volume water saturation, extract the change data of the nutrient element content from the farmland state monitoring data of the irrigation basin to obtain the change data of the soil nutrient element content. Step S33: According to the soil particle dispersion density data and the data of the flow direction of farmland irrigation water, quantify the nutrient leaching loss gradient for the change data of the soil nutrient element content to obtain the nutrient leaching loss gradient data. Step S34: Based on the nutrient leaching loss gradient data and the soil volume water saturation, simulate and quantify the nitrogen cycle anomaly to obtain the soil nitrogen cycle anomaly data.

[0007] Preferably, step S33 includes the following steps: Step S331: Evaluate the soil particle size range of the soil particle dispersion density data to obtain the soil particle size range; Step S332: Perform hydrodynamic soil porosity fluctuation calculation based on the soil particle size range and the farmland irrigation water flow direction data to obtain the hydrodynamic soil porosity fluctuation data; Step S333: Based on the hydrodynamic soil porosity fluctuation data, perform numerical iteration of soil profile nutrient loss on the soil nutrient element content change data to obtain the soil profile nutrient loss iteration data; Step S334: Evaluate the enlarged amount of nutrient sinking range for the soil profile nutrient loss iteration data to obtain the enlarged amount of nutrient sinking range; Step S335: Based on the soil profile nutrient loss iteration data and the enlarged amount of nutrient sinking range, quantify the nutrient leaching loss gradient to obtain the nutrient leaching loss gradient data.

[0008] Preferably, step S333 includes the following steps: Analyze the hydrodynamic non-linear pore expansion relationship of the hydrodynamic soil porosity fluctuation data to obtain the hydrodynamic non-linear pore expansion relationship; Perform soil profile water flow shear stress analysis on the hydrodynamic non-linear pore expansion relationship to obtain the soil profile pore water flow stress data; Deduce the velocity differences with different orientations of the pore water flow for the soil profile pore water flow stress data to obtain the velocity differences with different orientations of the pore water infiltration in the soil profile; Evaluate the osmotic convective pressure based on the hydrodynamic non-linear pore expansion relationship and the velocity differences with different orientations of the pore water infiltration in the soil profile to obtain the soil profile pore water osmotic convective pressure data; Perform numerical iteration of soil profile nutrient loss on the soil nutrient element content change data according to the Richards equation, the velocity differences with different orientations of the pore water infiltration in the soil profile, and the soil profile pore water osmotic convective pressure data to obtain the soil profile nutrient loss iteration data.

[0009] Preferably, step S34 includes the following steps: Step S341: Analyze the soil oxygen content decline gradient based on the soil volume water saturation to obtain the soil oxygen content decline gradient data; Step S342: Analyze the enhanced function relationship of anaerobic microbial activity based on the nutrient leaching loss gradient data and the soil oxygen content decline gradient data to obtain the enhanced function relationship of anaerobic microbial activity; Step S343: Perform denitrification rate enhanced coupling according to the anaerobic microorganism activity enhancement relationship function to obtain denitrification rate enhanced coupling data; Step S344: Conduct progressive fitting estimation of nitrogen release on the denitrification rate enhanced coupling data to obtain nitrogen release fitting estimation data; Step S345: Perform abnormal simulation quantification of the nitrogen cycle based on the nitrogen release fitting estimation data to obtain soil nitrogen cycle abnormal data.

[0010] Preferably, step S344 includes the following steps: Perform equal ratio mapping of nitrogen release based on the denitrification rate enhanced coupling data to obtain rate-matched nitrogen release mapping data; Conduct multiple extreme value analysis of ammonia release on the rate-matched nitrogen release mapping data according to the denitrification rate enhanced coupling data to obtain rate-matched ammonia release multiple extreme values; Perform time series delay calculation on the rate-matched ammonia release multiple extreme values to obtain multiple extreme value time series delay data; Conduct cyclic repeat release mean difference calculation based on the multiple extreme value time series delay data and the rate-matched ammonia release multiple extreme values to obtain the extreme value mean difference of the ammonia release cycle period; Perform progressive fitting estimation of nitrogen release on the extreme value mean difference of the ammonia release cycle period according to the maximum likelihood estimation method to obtain nitrogen release fitting estimation data.

[0011] Preferably, step S4 includes the following steps: Step S41: Perform convolution calculation on the soil nitrogen cycle abnormal data to obtain soil nitrogen cycle abnormal convolution data; Step S42: Regulate the soil water saturation according to the soil nitrogen cycle abnormal convolution data and the nutrient leaching loss gradient data to obtain soil water saturation regulation data; Step S43: Perform intelligent controlled release analysis of soil water and fertilizer dosage on the leaf yellowing and curling degree data based on the soil water saturation regulation data and the soil nitrogen cycle abnormal convolution data to obtain soil water and fertilizer dosage intelligent controlled release data, and send the soil water and fertilizer dosage intelligent controlled release data to the terminal to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0012] Preferably, step S43 includes the following steps: Step S431: Conduct long-term cumulative effect analysis of nutrient deficiency on the soil nitrogen cycle abnormal convolution data to obtain long-term cumulative effect data of nutrient deficiency; Step S432: Evaluate the degradation of nutrient absorption ability on the leaf yellowing and curling degree data to obtain crop nutrient absorption ability degradation data; Step S433: Analyze the soil air permeability enhancement ratio based on the soil moisture saturation regulation data to obtain the soil air permeability enhancement ratio; Step S434: Perform multi-objective optimization of the phased water and fertilizer ratio for the degraded data of the crop nutrient absorption ability according to the long-term cumulative effect data of nutrient deficiency and the soil air permeability enhancement ratio to obtain the multi-objective optimization data of the water and fertilizer ratio; Step S435: Perform intelligent controlled release analysis of the soil water and fertilizer dosage based on the multi-objective optimization data of the water and fertilizer ratio to obtain the intelligent controlled release data of the soil water and fertilizer dosage, and send the intelligent controlled release data of the soil water and fertilizer dosage to the terminal to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0013] Preferably, the present invention also provides a water and fertilizer intelligent analysis system for improving crop yield per unit area in a farmland area, which is used to execute the water and fertilizer intelligent analysis method for improving crop yield per unit area in a farmland area as described above. The water and fertilizer intelligent analysis system for improving crop yield per unit area in a farmland area includes: An irrigation basin farmland state monitoring module, which is used to obtain the farmland area structure data; extract the irrigation water flow direction from the farmland area structure data to obtain the farmland irrigation water flow direction data; deploy sensors in multiple directions based on the farmland irrigation water flow direction data and perform real-time monitoring of the irrigation basin farmland state, so as to generate the irrigation basin farmland state monitoring data; A soil volume moisture saturation extraction module, which is used to collect the crop morphological images in the water flow direction area through an electronic monitoring device and based on the farmland irrigation water flow direction data to obtain the crop morphological images in the water flow direction area; evaluate the degree of yellowing and curling of the leaves of the crop morphological images in the water flow direction area to obtain the data of the degree of yellowing and curling of the leaves; extract the soil volume moisture saturation of the crops with yellowing and curling leaves from the irrigation basin farmland state monitoring data according to the data of the degree of yellowing and curling of the leaves to obtain the soil volume moisture saturation of the crops with yellowing and curling leaves; A soil nitrogen cycle anomaly analysis module, which is used to extract the change in the content of nutrient elements from the irrigation basin farmland state monitoring data according to the soil volume moisture saturation to obtain the soil nutrient element content change data; quantify the nutrient leaching loss gradient of the soil nutrient element content change data to obtain the nutrient leaching loss gradient data; perform abnormal simulation quantification of the nitrogen cycle based on the nutrient leaching loss gradient data to obtain the soil nitrogen cycle anomaly data; A water and fertilizer dosage intelligent analysis and regulation module, which is used to perform intelligent controlled release analysis of the soil water and fertilizer dosage on the data of the degree of yellowing and curling of the leaves based on the soil nitrogen cycle anomaly data to obtain the intelligent controlled release data of the soil water and fertilizer dosage, and send the intelligent controlled release data of the soil water and fertilizer dosage to the terminal to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0014] The beneficial effects of the present invention are as follows. By obtaining the farmland area structure data and extracting the irrigation water flow direction, the operation status of the irrigation system and the distribution of water flow in the farmland can be accurately understood. This step helps to accurately deploy multi-directional sensors to ensure coverage of different areas of the farmland for comprehensive monitoring. The acquisition of real-time monitoring data provides a basis for subsequent precise irrigation and farmland management, ensuring the efficient collection of irrigation basin status data and providing a reliable basis for further analysis. By collecting the morphological images of crops through electronic monitoring devices and evaluating the degree of yellowing and curling of the leaves, the health status of the crops can be detected in a timely manner, especially the initial symptoms of uneven water and fertilizer or pests and diseases. This step provides an intuitive assessment of the crop growth status through the analysis of the morphological images of crops in the water flow direction area. The data on the degree of yellowing and curling of the leaves can help identify potential problems of water or nutrient deficiency, ensuring that farmland managers can take intervention measures in a timely manner to avoid affecting crop growth, thereby optimizing agricultural production. The extraction of soil volumetric water saturation, combined with the analysis of the change in nutrient element content, can accurately evaluate the soil water and nutrient status. This process helps to reveal the nutrient supply capacity and water status of the soil by quantifying the changes in nutrients in the soil. In particular, the quantification of the nutrient leaching loss gradient can understand the severity of nutrient loss. Combining with the simulation analysis of abnormal nitrogen cycling, the abnormality of soil nitrogen supply can be accurately identified. This analysis provides a scientific basis for formulating reasonable fertilization and irrigation plans, avoiding resource waste and environmental pollution. Through the intelligent controlled release analysis of water and fertilizer application amount based on the abnormal data of soil nitrogen cycling, precise water and fertilizer management can be achieved, avoiding over-fertilization and over-irrigation. This process enables the scientific regulation of soil water and fertilizer application amount, intelligently releasing water and fertilizer according to the actual demand of crops, significantly improving the use efficiency of water and fertilizer, reducing resource waste, and increasing crop yield per unit area. By sending the intelligent analysis data to the terminal, agricultural managers can obtain decision-making support in a timely manner, further optimizing the management and production of farmland and promoting the sustainable development of agricultural production. Therefore, a water and fertilizer intelligent analysis method based on improving crop yield per unit area in farmland regions provided by the present invention is an optimized treatment of a traditional water and fertilizer intelligent analysis method based on improving crop yield per unit area in farmland regions, solving the problem that the traditional water and fertilizer intelligent analysis method based on improving crop yield per unit area in farmland regions cannot accurately analyze the nutrient loss in the soil, resulting in a large error in water and fertilizer management use, improving the accuracy of analyzing the nutrient loss in the soil, and reducing the error in water and fertilizer management use. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of the steps of a water and fertilizer intelligent analysis method based on improving crop yield per unit area in farmland regions; Figure 2 is Figure 1 a schematic detailed implementation step flow chart of step S2 in Figure 3 For Figure 1 a detailed implementation step flowchart of step S3 in Specific implementation manner

[0016] Please refer to Figures 1 to 3 , a water and fertilizer intelligent analysis method based on improving the single crop yield in farmland regionalization, the method includes the following steps: Step S1: Obtain farmland regional structure data; extract the irrigation water flow direction from the farmland regional structure data to obtain farmland irrigation water flow direction data; deploy sensors in multiple directions based on the farmland irrigation water flow direction data, and conduct real-time monitoring of the farmland state in the irrigation basin, so as to generate farmland state monitoring data in the irrigation basin; Step S2: Through an electronic monitoring device, and collect crop morphological images based on the farmland irrigation water flow direction data to obtain crop morphological images in the water flow direction area; evaluate the degree of yellowing and curling of the leaves of the crop morphological images in the water flow direction area to obtain data on the degree of yellowing and curling of the leaves; extract the soil volume water saturation of the yellowing and curling crops from the farmland state monitoring data in the irrigation basin according to the data on the degree of yellowing and curling of the leaves, to obtain the soil volume water saturation of the yellowing and curling crops; Step S3: Extract the change in nutrient element content from the farmland state monitoring data in the irrigation basin according to the soil volume water saturation to obtain soil nutrient element content change data; quantify the nutrient leaching loss gradient of the soil nutrient element content change data to obtain nutrient leaching loss gradient data; simulate and quantify the nitrogen cycle anomaly based on the nutrient leaching loss gradient data to obtain soil nitrogen cycle anomaly data; Step S4: Conduct intelligent controlled release analysis of the soil water and fertilizer dosage on the data of the degree of yellowing and curling of the leaves based on the soil nitrogen cycle anomaly data to obtain intelligent controlled release data of the soil water and fertilizer dosage, and send the intelligent controlled release data of the soil water and fertilizer dosage to the terminal to perform intelligent analysis of water and fertilizer for improving the single crop yield.

[0017] In an embodiment of the present invention, referring to Figure 1 as described above, it is a step flowchart of a water and fertilizer intelligent analysis method based on improving the single crop yield in farmland regionalization of the present invention. In this example, the water and fertilizer intelligent analysis method based on improving the single crop yield in farmland regionalization includes the following steps: Step S1: Obtain farmland regional structure data; extract the irrigation water flow direction from the farmland regional structure data to obtain farmland irrigation water flow direction data; deploy sensors in multiple directions based on the farmland irrigation water flow direction data, and conduct real-time monitoring of the farmland state in the irrigation basin, so as to generate farmland state monitoring data in the irrigation basin; In the embodiments of the present invention, the acquisition of farmland area structure data is based on high-precision remote sensing mapping technology, and multi-spectral remote sensing images, lidar point cloud data, and geographic information system (GIS) technology are used for data collection and processing. First, a remote sensing image of the target farmland is obtained by using a high-resolution multi-spectral imaging satellite, and indices such as the normalized difference vegetation index (NDVI) and the ratio vegetation index (RVI) are used to enhance the distribution characteristics of farmland vegetation. Secondly, a lidar scanning system is carried by a drone, and the elevation model of the farmland surface is calculated through laser ranging and reflection intensity to obtain the internal terrain information of the farmland, including ridge, drainage ditch, and slope distribution. The multi-spectral remote sensing image and the lidar point cloud data are georegistered, and combined with the GIS spatial analysis method to generate the farmland area structure data. When extracting the irrigation water flow direction from the farmland area structure data, a digital elevation model (DEM) is used to calculate the water flow direction matrix, and combined with a watershed segmentation algorithm (such as the D8 algorithm) to determine the irrigation path, and the farmland irrigation water flow direction data is obtained. Based on the farmland irrigation water flow direction data, multi-directional sensors are deployed, and soil moisture sensors, conductivity sensors, temperature and humidity sensors are arranged by using a wireless sensor network (WSN), and a remote data acquisition system is established by using LoRa communication technology to realize real-time monitoring of the farmland state in the irrigation basin, and finally the farmland state monitoring data in the irrigation basin is generated.

[0018] Step S2: Through an electronic monitoring device, and based on the farmland irrigation water flow direction data, collect the crop morphological images in the water flow direction area to obtain the crop morphological images in the water flow direction area; evaluate the degree of yellowing and curling of the leaves of the crop morphological images in the water flow direction area to obtain the data on the degree of yellowing and curling of the leaves; according to the data on the degree of yellowing and curling of the leaves, extract the soil volume water saturation of the yellowing and curling crops from the farmland state monitoring data in the irrigation basin to obtain the soil volume water saturation of the yellowing and curling crops; In the embodiments of the present invention, the acquisition of crop morphological images is based on the data of the flow direction of farmland irrigation water. The crop morphological images are acquired by a hyperspectral imager and an RGB camera. It should be noted that the crops are planted at the same time and are of the same type, and the same type of crops will be planted in the same area. First, a hyperspectral imager is installed in the key irrigation water flow direction area of the farmland, and a fixed-angle automatic shooting system is used to collect images at different times. Secondly, a multi-scale segmentation algorithm is used to preprocess the acquired crop morphological images in the water flow direction area, removing shadows and soil background interference and retaining the crop canopy area. When evaluating the degree of yellowing and curling of the leaves in the extracted crop canopy area, color histogram statistical analysis and edge detection methods are used to calculate the leaf yellowing rate and curling degree. The leaf texture information is extracted by the local binary pattern (LBP) feature description method, and a support vector machine (SVM) classifier is used to determine the health status of the leaves, obtaining the data on the degree of yellowing and curling of the leaves. Based on the data on the degree of yellowing and curling of the leaves, the soil volume water saturation of the yellowing and curling crops is extracted from the farmland status monitoring data in the irrigation basin. The geostatistical interpolation method is used to calculate the soil water content in different depth soil layers, and the time series analysis method is combined to estimate the soil volume water saturation in the root zone of the yellowing and curling crops, and finally the soil volume water saturation data of the yellowing and curling crops is generated.

[0019] Step S3: Extract the change in nutrient element content from the farmland status monitoring data in the irrigation basin according to the soil volume water saturation to obtain the data on the change in soil nutrient element content; quantify the nutrient leaching loss gradient for the data on the change in soil nutrient element content to obtain the nutrient leaching loss gradient data; simulate and quantify the nitrogen cycle anomaly based on the nutrient leaching loss gradient data to obtain the soil nitrogen cycle anomaly data; In the embodiments of the present invention, according to the soil volume water saturation of the crops with yellow and curled leaves, the change in the content of nutrient elements is extracted from the monitoring data of the farmland state in the irrigation basin. The near-infrared spectroscopy (NIR) analysis method and the ion chromatography (IC) method are used to detect the change in the content of main nutrient elements such as nitrogen (N), phosphorus (P), and potassium (K) in the soil solution. The partial least squares regression (PLSR) method is used to reduce the dimension of the near-infrared spectral data, and the concentration of each nutrient element in the soil is calculated in combination with the standard curve. The Kriging interpolation method is used to construct the spatial distribution map of the change in the content of soil nutrient elements in different regions. When quantifying the nutrient leaching loss gradient of the soil nutrient element content change data, a one-dimensional vertical water flow-solute transport model (such as the HYDRUS-1D model) is used to simulate the dynamic process of soil nutrient migration with water under rainfall and irrigation conditions, and the leaching loss gradients of nitrogen, phosphorus, and potassium in different depth soil layers are calculated to obtain the nutrient leaching loss gradient data. Based on the nutrient leaching loss gradient data, the abnormal simulation quantification of the nitrogen cycle is carried out. The stable isotope analysis method (15N tracer technology) is used to measure the migration dynamics of nitrogen in the soil-plant system, and the abnormal parameters of the nitrogen cycle are calculated in combination with the improved nitrogen mass balance equation to obtain the abnormal data of the soil nitrogen cycle.

[0020] Step S4: Based on the abnormal data of the soil nitrogen cycle, perform intelligent controlled release analysis of the soil water and fertilizer dosage for the data of the degree of yellowing and curling of the leaves, obtain the intelligent controlled release data of the soil water and fertilizer dosage, and send the intelligent controlled release data of the soil water and fertilizer dosage to the terminal to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0021] In the embodiments of the present invention, based on the abnormal data of the soil nitrogen cycle, perform intelligent controlled release analysis of the soil water and fertilizer dosage for the data of the degree of yellowing and curling of the leaves. The spatio-temporal variability analysis method is used to construct a dynamic model of soil water and fertilizer supply and demand, and the areas where the soil water and fertilizer supply and demand do not match are analyzed. During the intelligent controlled release analysis process, the fuzzy control algorithm is used to set the critical threshold of soil water and fertilizer, and in combination with the abnormal data of the soil nitrogen cycle and the data of the degree of yellowing and curling of the leaves, the optimal application amounts of nitrogen fertilizer, phosphorus fertilizer, potassium fertilizer, and water in different regions are calculated. The drip irrigation system and the intelligent fertilization system are combined to achieve precise water and fertilizer regulation. The variable rate drip irrigation technology is used to adjust the irrigation flow according to the real-time soil humidity, and the high-throughput liquid fertilization system is combined for precise fertilizer application. The intelligent controlled release data of the soil water and fertilizer dosage are sent to the remote terminal control system, and the 5G Internet of Things technology is used to achieve data transmission, and the field water and fertilizer integration equipment is automatically controlled to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0022] Step S2 includes the following steps: Step S21: Through the electronic monitoring device, and based on the data of the flow direction of the farmland irrigation water, collect the morphological images of the crops to obtain the morphological images of the crops in the area where the water flows; Step S22: Identify the growth inhibition distribution of the crop morphological images in the water flow direction area to obtain the crop growth inhibition distribution data; Step S23: Evaluate the degree of yellowing and curling of the leaves of the crop morphological images in the water flow direction area based on the crop growth inhibition distribution data to obtain the data on the degree of yellowing and curling of the leaves; Step S24: Extract the soil volume water saturation of the yellowing and curling crops from the farmland status monitoring data in the irrigation basin according to the data on the degree of yellowing and curling of the leaves to obtain the soil volume water saturation of the yellowing and curling crops.

[0023] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: Collect crop morphological images through an electronic monitoring device and based on the farmland irrigation water flow direction data to obtain the crop morphological images in the water flow direction area; In the embodiment of the present invention, the collection of crop morphological images is based on the farmland irrigation water flow direction data, and a high-resolution optical imaging device, a multispectral imager, and a drone remote sensing system are used to cooperate in data collection. First, fixed electronic monitoring devices are arranged in the key farmland irrigation water flow direction areas, including visible light cameras and near-infrared imagers, and a multi-axis gimbal system is used to automatically adjust the camera angle to ensure that the shooting angle is consistent with the crop growth direction. Secondly, a drone is used to carry a hyperspectral imaging system to fly low at a specific trajectory, and an orthophoto mosaic technique is used to generate a complete crop morphological image in the water flow direction area. During the collection process, an adaptive exposure control technique is used to adjust the imaging parameters to eliminate the influence of the change in the sunlight irradiation angle on the image quality. Radiometric correction is performed on the collected multispectral and RGB images, and a linear normalization method is used to unify the pixel gray level range. A background segmentation algorithm (such as the GrabCut algorithm) is used to remove non-crop areas, and a morphological filtering method is used to remove small-area noise points to ensure the accuracy of the crop morphological images in the water flow direction area.

[0024] Step S22: Identify the growth inhibition distribution of the crop morphological images in the water flow direction area to obtain the crop growth inhibition distribution data; In the embodiment of the present invention, the identification of the growth inhibition distribution is based on the morphological images of crops in the water flow direction area, and a variety of vegetation indices such as the Normalized Difference Vegetation Index (NDVI), Greenness Index (GI), and Leaf Area Index (LAI) are used to jointly calculate the growth characteristics of crops. First, band calculations are performed on the multispectral image, and the NDVI formula is used to calculate the green vegetation coverage degree of the crop canopy, and the GI index is combined to enhance the contrast of the green leaf area. Secondly, based on the LAI index, the leaf density information of the crop is extracted, and the image contrast is adjusted by the adaptive histogram equalization method to enhance the distinguishability of the crop growth area. The K-means clustering algorithm is used to classify the crop growth area, and the vigorously growing area and the growth inhibition area are partitioned. Spatial autocorrelation analysis (Moran's I) is used to calculate the aggregation degree of the spatial distribution of crop growth, and a spatial variation model of growth change is established by combining the semi-variance analysis method, and finally the crop growth inhibition distribution data is generated. The Laplace operator is used to sharpen the boundary of the growth inhibition area to ensure data accuracy, and discrete noise points are eliminated based on morphological closing operation to make the crop growth inhibition distribution data more coherent.

[0025] Step S23: Based on the crop growth inhibition distribution data, evaluate the degree of yellowing and curling of the leaves in the morphological image of the crops in the water flow direction area to obtain the degree data of yellowing and curling of the leaves; In the embodiment of the present invention, the evaluation of the degree of yellowing and curling of the leaves is based on the crop growth inhibition distribution data, and the yellowing degree and curling morphology of the leaves are quantified through color feature analysis, edge detection, and texture feature extraction methods. First, the RGB image is converted to the Lab color space using color space conversion technology, and the channel value is extracted, and the Yellowing Index (YI) is calculated to characterize the degree of leaf yellowing. Secondly, the Canny edge detection algorithm is used to obtain the leaf contour, and the curvature change of the leaf edge is calculated based on the morphological gradient analysis method to quantify the degree of leaf curling. The Local Binary Pattern (LBP) method is used to extract the surface texture features of the leaves, and principal component analysis (PCA) is combined for feature dimensionality reduction to reduce redundant information. The extracted leaf yellowing index, curling curvature, and texture feature data are normalized, and a Support Vector Machine (SVM) classifier is used to classify the leaf health status. Based on the region growing algorithm, the area ratio of the yellowing area of the leaves is calculated, and a spatial correlation model is established by combining the growth inhibition distribution data to evaluate the severity of leaf yellowing and curling in different areas, and finally the degree data of yellowing and curling of the leaves is generated.

[0026] Step S24: According to the degree data of yellowing and curling of the leaves, extract the soil volume water saturation of the yellowing and curling crops from the farmland status monitoring data of the irrigation basin to obtain the soil volume water saturation of the yellowing and curling crops.

[0027] In the embodiments of the present invention, the extraction of soil volume water saturation is based on the data of the degree of yellowing and curling of leaves, and is calculated by the methods of multi-source data fusion and time series analysis. First, soil moisture sensors are arranged in the farmland monitoring area, and the TDR (time domain reflectometry) method is used to measure the soil moisture content, and the frequency domain reflectometry (FDR) method is combined to supplement the measurement data to obtain the soil moisture change at different depths. Secondly, based on the data of the degree of yellowing and curling of leaves, a random forest regression algorithm is used to construct a relationship model between leaf morphology and soil moisture, and the least squares support vector regression (LSSVR) method is used to optimize the prediction accuracy. The time series decomposition method is combined to analyze the soil moisture change trend, and the Kriging interpolation method is used to generate the soil volume water saturation distribution map of different regions. According to the water transfer characteristics of different soil layers, the Richards equation is used to calculate the soil water potential in the root zone, and the crop transpiration is estimated by combining the leaf stomatal conductance data, so as to invert the soil moisture deficit state. Finally, a mathematical relationship model of soil moisture-leaf state is constructed by the spatial regression analysis method to ensure the scientificity and accuracy of the soil volume water saturation data.

[0028] Step S3 includes the following steps: Step S31: Perform soil particle dispersion density calculation based on the soil volume water saturation to obtain soil particle dispersion density data; Step S32: Extract the change in nutrient element content from the farmland state monitoring data in the irrigation basin according to the soil volume water saturation to obtain soil nutrient element content change data; Step S33: Quantify the nutrient leaching loss gradient of the soil nutrient element content change data according to the soil particle dispersion density data and the farmland irrigation water flow direction data to obtain nutrient leaching loss gradient data; Step S34: Perform abnormal simulation quantification of the nitrogen cycle based on the nutrient leaching loss gradient data and the soil volume water saturation to obtain soil nitrogen cycle abnormal data.

[0029] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: Perform soil particle dispersion density calculation based on the soil volume water saturation to obtain soil particle dispersion density data; In the embodiments of the present invention, the calculation of the soil particle dispersion density is based on the soil volume water saturation, and is calculated through the soil particle classification analysis and the sedimentation rate modeling method. First, a laser particle size analyzer is used to measure the particle sizes of the soil at different sampling depths, and the dispersion coefficients of soil particles with different particle sizes are calculated based on Stokes' sedimentation law. Secondly, combined with the soil volume water saturation data, the fractal theory is used to calculate the degree of soil particle aggregation, and the particle dispersion index (PDI) is used to characterize the discrete state of soil particles. By constructing a soil particle dispersion potential energy model, the discrete element method (DEM) is used to simulate the dynamic process of particle dispersion under different soil moisture conditions, calculate the adsorption force, repulsive force and gravitational force between particles, and combine the soil moisture-porosity ratio analysis to calculate the particle dispersion density. The Gaussian mixture model (GMM) is used to fit the particle dispersion density data, and the spatial distribution map is generated by the Kriging interpolation method to finally obtain the soil particle dispersion density data.

[0030] Step S32: Extract the changes in the nutrient element content from the farmland state monitoring data of the irrigation basin according to the soil volume water saturation to obtain the soil nutrient element content change data; In the embodiments of the present invention, the extraction of the changes in the soil nutrient element content is based on the soil volume water saturation, combined with the farmland state monitoring data of the irrigation basin, and the data is extracted through multi-element spectral analysis and dynamic balance calculation. First, an atomic absorption spectrometer (AAS) and an inductively coupled plasma optical emission spectrometer (ICP-OES) are used to measure the initial concentrations of nutrient elements such as nitrogen, phosphorus, and potassium in soil samples, and the content data of trace elements (iron, zinc, copper, etc.) are obtained by combining high-throughput ion chromatography analysis methods. Secondly, based on the soil volume water saturation, a one-dimensional solute transport model is used to calculate the migration rates of nutrient elements under different moisture conditions, and the release, absorption and loss of soil nutrients are deduced by combining the nutrient cycling equation of the soil-plant system. The spatial variation intensity of nutrients in different regions is calculated by coefficient of variation analysis, and the wavelet analysis method is used to denoise the time series nutrient data to obtain the true nutrient change trend. The principal component analysis (PCA) is used to screen the factors that have the greatest impact on the soil nutrient dynamics, and the random forest regression algorithm is used to predict the future nutrient change trend to finally obtain the soil nutrient element content change data.

[0031] Step S33: Quantify the nutrient leaching loss gradient of the soil nutrient element content change data according to the soil particle dispersion density data and the farmland irrigation water flow direction data to obtain the nutrient leaching loss gradient data; In the embodiment of the present invention, the nutrient leaching loss gradient is quantified based on the soil particle dispersion density data and the farmland irrigation water flow direction data, and is quantitatively analyzed by establishing a soil solute migration model and a percolation coefficient calculation method. First, the solute penetration curve under different soil particle dispersion density conditions is determined by a soil column experiment, the water infiltration rate is calculated in combination with the Brutsaert nonlinear seepage equation, and the hydraulic gradient of different soil layers is calculated using the two-dimensional Darcy law. Secondly, based on the farmland irrigation water flow direction data, the finite difference method (FDM) is used to simulate the water flow path, and the nutrient migration amount of each watershed section is calculated in combination with the solute balance equation. The influence of soil particle dispersion density on the water flow rate is analyzed by Fourier transform, and the nutrient leaching loss gradient of different soil layers is calculated by geostatistical methods. The nutrient leaching gradient distribution map is drawn using the contour line method, and the spatial uniformity of nutrient leaching is calculated by fractal dimension, and finally the nutrient leaching loss gradient data is obtained.

[0032] Step S34: Perform nitrogen cycle anomaly simulation and quantification based on nutrient leaching loss gradient data and soil volume water saturation to obtain soil nitrogen cycle anomaly data.

[0033] In the embodiment of the present invention, the simulation and quantification of nitrogen cycle anomaly is based on nutrient leaching loss gradient data and soil volume water saturation, and is quantitatively simulated through a biogeochemical cycle model and a nitrogen flux calculation method. First, the soil ammonia volatilization is determined by a static chamber method and gas chromatography analysis technology, and the N in the soil nitrification-denitrification process is determined by solid phase microextraction-mass spectrometry technology. 2 O, NO and N 2 The release amount. Secondly, based on the nutrient leaching loss gradient data, the step-by-step inversion method was used to estimate the nitrate nitrogen leaching loss, and the soil nitrogen conversion rate was calculated in combination with the first-order kinetic equation. The mathematical model of nitrogen input, consumption and loss was established using the mass balance principle, and the risk of nitrogen cycle anomaly under different water and fertilizer management modes was evaluated using the Monte Carlo random simulation method. The spatial regression analysis method was used to calculate the nitrogen accumulation in different regions, and the Kriging interpolation method was used to generate the nitrogen anomaly distribution map, and finally the soil nitrogen cycle anomaly data was obtained.

[0034] Step S33 includes the following steps: Step S331: evaluating the soil particle size interval of the soil particle dispersion density data to obtain the soil particle size interval; Step S332: performing hydrodynamic soil porosity fluctuation calculation according to the soil particle size range and farmland irrigation water flow direction data to obtain hydrodynamic soil porosity fluctuation data; Step S333: performing soil profile nutrient loss numerical iteration on soil nutrient element content change data based on hydrodynamic soil porosity fluctuation data to obtain soil profile nutrient loss iteration data; Step S334: Evaluate the enlarged amount of nutrient sinking range for the iterative data of soil profile nutrient loss to obtain the enlarged amount of nutrient sinking range; Step S335: Quantify the nutrient leaching loss gradient based on the iterative data of soil profile nutrient loss and the enlarged amount of nutrient sinking range to obtain the nutrient leaching loss gradient data.

[0035] In the embodiments of the present invention, the evaluation of the soil particle size range is based on the soil particle dispersion density data, and is calculated by combining the laser particle size analysis method with the probability statistics method. First, a laser particle size analyzer is used to measure soil samples at different depths to obtain the particle size distribution curve, and the relative content of each particle size segment is calculated based on the Mie scattering theory. Secondly, the fractal dimension analysis method is used to calculate the aggregation degree of soil particles, and the Gaussian mixture model (GMM) is used to fit the particle size distribution data to separate different particle size components. The probability density function of particles with different particle sizes is calculated by combining the Poisson distribution model, and the Kolmogorov-Smirnov test method is used to evaluate the normality of the particle size distribution. Subsequently, the K-means clustering algorithm is used to classify the particle size data, the boundaries of each particle size component are calculated, and the volume fraction of each particle size range is calculated according to the soil particle density and porosity. Finally, the obtained soil particle size range data is cross-compared with the soil texture classification data of different regions of the farmland, and the outliers are corrected to obtain the soil particle size range. The hydrodynamic soil porosity fluctuation calculation is based on the soil particle size range and the farmland irrigation water flow direction data, and is calculated by combining the hydrodynamics method with the soil permeability analysis. First, the permeability coefficient of soil in different particle size ranges is calculated based on Darcy's law, and the Kozeny-Carman equation is used to estimate the effective porosity of each layer of soil. Secondly, combined with the farmland irrigation water flow direction data, the finite element method (FEM) is used to construct a water movement model to simulate the hydrodynamic changes in different soil regions. The water flow pattern of each watershed section is calculated by the Reynolds number, and the Navier-Stokes equation is used to simulate the velocity change of the pore water in the soil. Subsequently, combined with the porosity-flow relationship curve, the nonlinear regression method is used to calculate the hydrodynamic changes under different porosity conditions, and the time series analysis method is used to extract the porosity fluctuation characteristics. Finally, the spatial interpolation method is used to generate the hydrodynamic soil porosity fluctuation distribution map and error correction is performed to obtain the hydrodynamic soil porosity fluctuation data. The numerical iteration of soil profile nutrient loss is based on the hydrodynamic soil porosity fluctuation data and the soil nutrient element content change data, and is calculated by the numerical simulation method. First, based on the hydrodynamic porosity data, the Richards equation is used to calculate the water infiltration rate of soil at different depths, and the solute transport equation (ADE) is combined to calculate the migration rate of different nutrients in the soil profile. Secondly, using the soil profile layered model, the farmland soil is divided into multiple calculation units, and the finite difference method (FDM) is used for numerical solution. The mineralization rate of soil organic matter is calculated by the first-order reaction kinetics equation, and the release and absorption amounts of nutrients such as nitrogen, phosphorus, and potassium are calculated by combining the solute balance model. Subsequently, the time step iteration method is used to perform multiple calculations on each unit, and the results are corrected in combination with the error convergence criterion.Finally, based on the numerical iteration results, a spatial distribution map of nutrient loss in the soil profile is generated, and the multivariate regression analysis method is used to calculate the nutrient loss trend of different soil types, obtaining the iterative data of nutrient loss in the soil profile. The evaluation of the enlarged amount of nutrient sinking range is based on the iterative data of nutrient loss in the soil profile and is determined by combining statistical analysis methods with hydrodynamic calculations. First, the Kriging interpolation method is used to perform spatial interpolation on the nutrient loss data in the soil profile to calculate the change gradient of nutrient concentration in different soil layers at different depths. Secondly, based on Stokes' sedimentation law, the sedimentation rate of nutrient particles of different particle sizes is calculated, and combined with Fick's diffusion law, the lateral diffusion amount of nutrients is calculated. Subsequently, the solute transport model (CDE) is used to simulate the sinking rate of nutrients under different water states, and combined with the one-dimensional vertical seepage model, the nutrient accumulation amount in different soil layers is calculated. Geostatistical methods are used to calculate the nutrient sinking range of different soil types, and the partial least squares regression (PLSR) analysis method is used to screen the key factors affecting the enlarged amount of nutrient sinking. Finally, based on the spatial regression analysis method, the nutrient diffusion coefficient of different soil layers is calculated, and combined with the tomography method, the distribution data of the enlarged amount of nutrient sinking range is generated, obtaining the enlarged amount of nutrient sinking range. The quantification of the nutrient leaching loss gradient is based on the iterative data of nutrient loss in the soil profile and the enlarged amount of nutrient sinking range, and is calculated using the multi-dimensional coupling modeling method. First, based on the hydrodynamic porosity data, the two-dimensional Darcy seepage model is used to calculate the water migration rate of different soil layers, and combined with the solute transport model, the loss rate of different nutrients is calculated. Secondly, the Lagrange interpolation method is used to discretize the calculation of the nutrient loss gradient, and combined with geostatistical methods, the nutrient leaching loss gradient distribution in different regions is calculated. The principal component analysis (PCA) is used to screen the key variables affecting the nutrient leaching gradient, and the K-means clustering method is used to divide the soil area into different leaching loss levels. Subsequently, the numerical integration method is used to calculate the cumulative amount of nutrient loss at different time scales, and combined with the Fourier transform, the periodic change of nutrient loss is analyzed. Finally, the geographic information system (GIS) technology is used to draw the nutrient leaching loss gradient distribution map, and the multivariate regression model is used to predict the nutrient leaching change trend under different future irrigation conditions, obtaining the nutrient leaching loss gradient data.

[0036] Step S333 includes the following steps: Analyze the hydrodynamic nonlinear pore expansion relationship of the hydrodynamic soil porosity fluctuation data to obtain the hydrodynamic nonlinear pore expansion relationship; Conduct soil profile water flow shear stress analysis on the hydrodynamic nonlinear pore expansion relationship to obtain the pore water flow stress data of the soil profile; Deduce the velocity differences in different directions of the pore flow of the soil profile from the pore water flow stress data of the soil profile to obtain the velocity differences in different directions of pore penetration of the soil profile; Based on the hydrodynamic nonlinear pore expansion relationship and the velocity difference of different flow directions in the cross-sectional pore permeability, the osmotic convection pressure is evaluated to obtain the cross-sectional pore osmotic convection pressure data; According to the Richards equation, the velocity difference of different flow directions in the cross-sectional pore permeability, and the cross-sectional pore osmotic convection pressure data, numerical iteration of soil nutrient loss is carried out on the soil nutrient element content change data to obtain the soil profile nutrient loss iteration data.

[0037] In the embodiments of the present invention, the analysis of the hydrodynamic non-linear pore expansion relationship is based on the hydrodynamic soil porosity fluctuation data, and the non-linear expansion law under different pore states is determined through soil mechanics and seepage mechanics calculations. First, based on the soil particle size distribution and porosity data, the particle stress states under different pore structures are calculated using the particle contact mechanics method, and the pore boundary stress characteristics are analyzed in combination with the Hertz contact theory. Secondly, the Biot solid-liquid coupling equation is used to solve the pore deformation of the soil under the action of water flow, and the elastic deformation of the soil skeleton is calculated in combination with the generalized Hooke's law. Subsequently, based on the change of pore water pressure, the Navier-Stokes equation is used to simulate the dynamic distribution of pore water, and the Reynolds-averaged equation is used to calculate the pore expansion effect at different water flow velocities. Through the multiple regression analysis method, a non-linear relationship between the pore expansion coefficient and hydrodynamic variables (pore water pressure, shear stress, seepage rate, etc.) is constructed, and the Boussinesq equation is used to correct the hydrodynamic non-linear effect to obtain the hydrodynamic non-linear pore expansion relationship data. The analysis of the water flow shear stress in the soil profile is based on the hydrodynamic non-linear pore expansion relationship, and the water flow force of different soil layers is calculated using shear mechanics. First, based on the Darcy-Weisbach equation, the water flow resistance under different pore states is calculated, and the effective shear stress between soil particles is calculated in combination with the Mohr-Coulomb criterion. Secondly, using the Reynolds stress model in fluid dynamics, the water flow disturbances at different pore scales are analyzed layer by layer, and the two-dimensional turbulent transport equation is used to solve the evolution characteristics of the hydrodynamic shear force over time. Subsequently, in combination with the soil particle arrangement structure, the Bagnold effect is used to calculate the shear slip rate between particles, and the influence of different shear frequencies on pore stability is analyzed based on the Fourier transform. The boundary layer theory is used to calculate the shear stress gradient inside the soil profile, and the pore water flow shear stress distribution of different depth soil layers is obtained through numerical integration to obtain the pore water flow stress data of the soil profile. The deduction of the flow velocity difference in different directions is based on the pore water flow stress data of the soil profile, and the flow velocity differences of different soil layers are calculated using seepage mechanics and non-uniform fluid mechanics. First, based on the non-uniform seepage theory, the Laplace equation is used to calculate the water flow pressure field of different soil layers, and in combination with the anisotropic permeability coefficient of the soil, the spatial variation trend of the water flow rate is deduced using Darcy's law. Secondly, in combination with the soil pore structure, the Kozeny-Carman equation is used to calculate the seepage resistance in different directions, and the second-order differential equation in fluid dynamics is used to analyze the gradient change of the flow velocity along the profile. Subsequently, based on the variational method, the optimal flow velocity distribution of different seepage paths is solved, and in combination with the soil particle size and pore morphology, the Navier-Stokes equation is used to calculate the flow velocity differences in different directions of the soil profile.Finally, using the finite element analysis (FEM) method, the velocity difference of the soil profile is numerically simulated, and the velocity deviation is corrected based on the law of soil pore deformation to obtain the velocity difference data with different orientations of pore penetration in the profile. The evaluation of the osmotic convection pressure is based on the hydrodynamic nonlinear pore swelling relationship and the velocity difference with different orientations of pore penetration in the profile. The pressure distribution under different water flow states is calculated using hydrostatics and osmotic mechanics. First, the osmotic pressure of different pore structures is calculated based on Poiseuille's law, and the hydrodynamic potential energy distribution of different soil layers is solved by combining with the soil water potential formula. Secondly, the fluid energy distribution under different hydrodynamic conditions is calculated using the Bernoulli equation, and the spatio-temporal evolution characteristics of the osmotic convection pressure are solved by combining with the water flow shear force and the pore penetration resistance using the Navier-Stokes equation. Subsequently, the pressure change of different penetration paths is calculated based on the mass conservation equation, and the influence of pore deformation under water flow on the pressure is analyzed using the generalized Stokes law. The numerical simulation method is used to calculate the osmotic convection pressure of different soil types, and the pressure fluctuation under the pore flow state is analyzed by combining with the boundary layer theory to obtain the osmotic convection pressure data of the pore in the profile. The numerical iteration of nutrient loss in the soil profile is based on the Richards equation, the velocity difference with different orientations of pore penetration in the profile, and the osmotic convection pressure data of the pore in the profile, and is solved using the water-soil-solute coupling calculation method. First, the soil water potential under different water contents is calculated based on the Richards equation, and the dynamic equation of nutrient dissolution and migration is deduced by combining with the water infiltration rate. Secondly, the one-dimensional solute transport model (CDE) is used to calculate the distribution of nutrients such as nitrogen, phosphorus, and potassium in the profile, and the nutrient diffusion rate is solved by combining with Fick's law. Subsequently, the nutrient migration amount under different velocity difference conditions is calculated based on the convection-diffusion coupling equation, and the retention ability of soil particles to nutrients is solved by combining with the adsorption-desorption equilibrium model. The finite volume method (FVM) is used to discretize the calculation of the nutrient loss process, and multiple rounds of numerical iteration are carried out by combining with the error convergence criterion. Finally, the influencing factors of the nutrient loss rate are analyzed using the multivariate regression analysis method, and the spatial distribution map of nutrient loss in the soil profile is generated by combining with the Kriging interpolation method to obtain the iterative data of nutrient loss in the soil profile.

[0038] Step S34 includes the following steps: Step S341: Analyze the decreasing gradient of soil oxygen content according to the soil volume water saturation to obtain the decreasing gradient data of soil oxygen content; Step S342: Analyze the enhanced function relationship of anaerobic microbial activity based on the nutrient leaching loss gradient data and the decreasing gradient data of soil oxygen content to obtain the enhanced relationship function of anaerobic microbial activity; Step S343: Perform the enhanced coupling of denitrification rate according to the enhanced relationship function of anaerobic microbial activity to obtain the enhanced coupling data of denitrification rate; Step S344: Carry out a progressive fitting estimation of nitrogen release on the denitrification rate enhanced coupling data to obtain the nitrogen release fitting estimation data; Step S345: Carry out a simulation quantification of the nitrogen cycle anomaly based on the nitrogen release fitting estimation data to obtain the soil nitrogen cycle anomaly data.

[0039] In the embodiments of the present invention, the analysis of the soil oxygen content decline gradient is based on the soil volumetric water saturation data. By analyzing the influence of water on the oxygen distribution in the soil, the gradient of soil oxygen decline is determined. First, combining the aeration performance and water content of the soil, the Darcy's law is used to calculate the water permeability and water flow velocity, and the water saturation at different depths in the soil is calculated. Then, based on the water saturation in the soil, the Fick's diffusion law is used to describe the oxygen diffusion process in the soil, and further the change of oxygen concentration gradient under different water conditions is calculated. By experimentally measuring the oxygen concentration in different soil layers and combining the relationship between water flow permeability and pore structure, a mathematical model of the change of oxygen concentration with water saturation is established. In the model, when the water saturation increases, the gas exchange in the soil pores is restricted, and the oxygen diffusion ability decreases, resulting in an increase in the oxygen content gradient. The numerical integration method is used to simulate the change of oxygen concentration in different soil types, and according to the soil type (such as clay, sand, etc.) and its gas diffusion characteristics, the specific change of oxygen content gradient is determined. Finally, through multiple regression analysis, the soil oxygen content decline gradient data is obtained. Analysis of the enhanced functional relationship of anaerobic microbial activity Combining the nutrient leaching loss gradient data and the soil oxygen content decline gradient data, the enhanced relationship between the activities of anaerobic microorganisms in the soil and the water and oxygen conditions is deduced. First, according to the nutrient leaching loss gradient of nitrogen, phosphorus and other nutrients in the soil, the Fick's law and the Advection-Dispersion model are used to simulate the flow and migration process of nutrients, and the longitudinal distribution of nutrients in the soil is obtained. Then, combining the soil oxygen content decline gradient, the Monod equation is used to describe the growth and reproduction rate of anaerobic microorganisms in a low-oxygen environment. The growth rate in the Monod equation has a non-linear relationship with the oxygen concentration and the nutrient concentration. On this basis, combining the water, oxygen concentration and nutrient loss data, an enhanced function of anaerobic microbial activity is established. By comparing the activities of anaerobic microorganisms under different water and oxygen conditions, the quantitative relationship between nutrient loss and microbial activity is determined. The parameters of the function are obtained by data fitting, and a non-linear function describing the interaction of water, oxygen and nutrients is constructed. Finally, the polynomial regression method or the Lagrange interpolation method is used to optimize the function, and the enhanced relationship function of anaerobic microbial activity is obtained. Enhancement coupling of denitrification rate Based on the enhanced relationship function of anaerobic microbial activity, the rate change in the denitrification process is deduced. First, according to the relationship between the activity of anaerobic microorganisms and the water, oxygen and nutrient concentrations, the Michaelis-Menten equation is used to describe the dependence of the denitrification rate on the substrate concentration, and the initial rate of the denitrification reaction is obtained. Subsequently, combining the metabolic characteristics of microorganisms in an anaerobic environment, the relationship between the denitrification reaction rate and the microbial activity is quantified based on the Hill equation. By introducing variables such as the nitrogen source concentration, oxygen concentration and temperature in the soil, a multi-factor coupled denitrification rate model is established.The denitrification rate in this model is not only limited by oxygen, but also affected by the water saturation and nutrient availability in the soil. To further enhance the simulation effect of the denitrification rate, combined with experimental data, the Newton method is used to optimize and solve the parameters in the denitrification rate model, and the enhanced coupling relationship between the denitrification rate and the anaerobic microbial activity is obtained. Finally, the obtained enhanced coupling data is used to numerically simulate the denitrification rate, and the specific enhanced coupling data of the denitrification rate is obtained. The progressive fitting estimation of nitrogen release is based on the enhanced coupling data of the denitrification rate to calculate the nitrogen release amount in the soil. First, based on the denitrification rate data, the cumulative nitrogen release model is used to simulate the nitrogen release process. By dynamically tracking the soil nitrogen source (such as nitrate), combined with the experimental data of nitrogen release, the least squares method is used to fit the relationship between nitrogen release and denitrification rate. During the fitting process, factors such as soil temperature, moisture, and oxygen concentration that affect nitrogen release are considered to obtain the progressive process of nitrogen release. Then, the exponential decay model is used to describe the relationship between the nitrogen release rate and time, and the change trend of nitrogen release in different time periods is analyzed. Through data analysis, the cumulative amount of nitrogen release is obtained, and the relationship model between the nitrogen release rate and the denitrification process is established. Finally, through multiple fittings, the progressive fitting estimation data of nitrogen release is obtained, which can accurately reflect the nitrogen release amount under different soil conditions. The quantification of abnormal nitrogen cycling simulation is based on the fitting estimation data of nitrogen release and combined with the nitrogen cycling process in the soil for quantification. First, the Richards equation is used to simulate the dynamic changes of soil moisture and gas, combined with the distribution of soil nitrogen sources, to calculate the conversion rate and loss rate of nitrogen in the soil. Subsequently, the nitrogen cycling model is used to dynamically simulate the release, absorption, and conversion processes of nitrogen, and the abnormal conditions of nitrogen cycling in different soil environments are simulated. By analyzing the change trend of the nitrogen release rate in the soil, combined with factors such as soil nitrogen content, temperature, and humidity, it is detected whether the nitrogen cycling is abnormal. For example, excessive nitrogen release indicates that the soil is in an anaerobic state and the denitrification process is abnormally intensified. The differential equation is used to discretize the dynamic process of nitrogen cycling to obtain the quantification data of abnormal nitrogen cycling. Finally, by comparing the nitrogen cycling data under different soil types and different management measures, the abnormal conditions of soil nitrogen cycling are quantitatively evaluated to obtain the abnormal data of soil nitrogen cycling.

[0040] Step S344 includes the following steps: Perform an isometric mapping of nitrogen release based on the enhanced coupling data of the denitrification rate to obtain rate-matched nitrogen release mapping data; Perform a multiple extreme value analysis of ammonia release on the rate-matched nitrogen release mapping data according to the enhanced coupling data of the denitrification rate to obtain rate-matched multiple extreme values of ammonia release; Perform a time-series delay calculation on the rate-matched multiple extreme values of ammonia release to obtain multiple extreme value time-series delay data; Based on the multiple extreme value time series delay data and the rate matching ammonia release multiple extreme values, the cyclic repeatability release mean difference calculation is carried out to obtain the extreme value mean difference of the ammonia release cycle period; According to the maximum likelihood estimation method, the extreme value mean difference of the ammonia release cycle period is asymptotically fitted and estimated for nitrogen release to obtain the nitrogen release fitting estimation data.

[0041] In the embodiment of the present invention, according to the denitrification rate enhanced coupling data, the denitrification rate data is converted into nitrogen release data by using the equal ratio mapping method. In this process, first, based on the relationship between the denitrification rate and nitrogen release, a proportional model of the denitrification rate and nitrogen release is established. The model obtains the basic relationship between the denitrification rate and nitrogen release rate through linear regression analysis of experimental data. Then, through equal ratio mapping, for different denitrification rates, they are converted into corresponding nitrogen release rates. The process of equal ratio mapping is carried out as follows: Assume the denitrification rate and the nitrogen release rate The relationship between them can be expressed by the proportionality coefficient k, that is =k× 。The proportionality coefficient k is determined through experiments or can be obtained from relevant technical literature and corrected in combination with environmental factors such as different soil moisture and temperature. The denitrification rate data at different time points are subjected to geometric mapping to obtain the nitrogen release rate data corresponding to each time point, and the data are smoothed through interpolation to obtain high-precision rate-matched nitrogen release mapping data. Based on the rate-matched nitrogen release mapping data, a multiple extreme value analysis of ammonia release is carried out. In this step, first, based on the rate-matched nitrogen release mapping data, the peaks and valleys of ammonia release are identified. By solving the derivative in the ammonia release process, the extreme value points of the ammonia release rate change with time can be identified. These extreme value points represent the maximum release rate (peak value) and the minimum release rate (valley value) in the ammonia release process. For the analysis of multiple extreme values, the second derivative method is used to determine multiple extreme value points, and the existence and position of these extreme values are further verified through an extreme value detection algorithm (such as solving the Lagrange multiplier method). During this process, special attention is paid to the periodic change of the ammonia release rate. Using a periodic analysis method, such as the fast Fourier transform (FFT), the frequency of ammonia release is analyzed to identify the periodic peaks and valleys, and by calculating the parameters of its periodic change, the multiple extreme value data of rate-matched ammonia release are finally obtained. Based on the multiple extreme value data of rate-matched ammonia release, a time series delay calculation is carried out to obtain the time series delay data in the ammonia release process. First, based on the multiple extreme value data, an autoregressive integrated moving average (ARIMA) model is used for time series analysis to analyze the time series change law of ammonia release. Through model fitting, the time delay between each extreme value point is calculated. During this process, the difference method is used to smooth the time series to eliminate the trend change and ensure that the data is suitable for ARIMA modeling. Then, using time delay analysis technology, the time series delay between each extreme value point is determined, that is, the time offset of each extreme value point. To more accurately capture the dynamic change of ammonia release, the cross-correlation function (CCF) is used to compare the ammonia release rates at different time points, and the delay between the ammonia release peak and valley is calculated. Through the time series delay calculation, the time series delay data of multiple extreme values are obtained, so as to further analyze the time correlation in the ammonia release process. Combining the multiple extreme value time series delay data and the multiple extreme value data of rate-matched ammonia release, an average difference calculation of the extreme values of the ammonia release cycle period is carried out. First, based on the multiple extreme value time series delay data, the cycle period in the ammonia release process is calculated, that is, the time interval between extreme value points. According to the known multiple extreme value points, the mean method is used to calculate the extreme value difference within each cycle, and the average difference of each cycle is calculated to reflect the cycle stability in the ammonia release process. In the specific operation process, the range method is used to calculate the range of each cycle, that is, the difference between the maximum and minimum extreme values within a complete cycle. Then, the ranges of all cycles are averaged to obtain the average difference of the extreme values of the ammonia release cycle.By statistically analyzing the mean difference of extreme values over multiple cycles, the cyclic pattern of ammonia release is judged, and the degree of fluctuation in each cycle is quantified. The calculation process of the mean difference of extreme values is based on the root mean square error (RMSE) method in statistics to ensure that the differences between cycles can accurately reflect the dynamic changes in ammonia release. According to the mean difference data of extreme values, the maximum likelihood estimation method is used for asymptotic fitting estimation of nitrogen release. First, based on the distribution of the mean difference of extreme values, it is assumed that the asymptotic process of nitrogen release conforms to a certain statistical distribution (such as normal distribution or lognormal distribution), and the maximum likelihood estimation method (MLE) is used to determine the parameters of the fitting function. The maximum likelihood estimation method estimates the parameters by maximizing the likelihood function. In this step, by deriving the maximum likelihood function for the time series data of ammonia release, the optimal parameters related to the nitrogen release process are calculated. The specific method is to construct a likelihood function representing the probability distribution of the parameters given the data. The optimal fitting parameters are obtained by solving this likelihood function through optimization methods (such as Newton's method or quasi-Newton method). Finally, through this estimation method, the asymptotic behavior of the nitrogen release process is matched with the actual data, thereby obtaining the fitting estimation data of nitrogen release. This fitting estimation can provide an accurate mathematical basis for the subsequent quantification of nitrogen release.

[0042] Step S4 includes the following steps: Step S41: Perform convolution calculation on the abnormal data of soil nitrogen cycling to obtain the abnormal convolution data of soil nitrogen cycling; Step S42: Regulate the soil water saturation according to the abnormal convolution data of soil nitrogen cycling and the nutrient leaching loss gradient data to obtain the soil water saturation regulation data; Step S43: Based on the soil water saturation regulation data and the abnormal convolution data of soil nitrogen cycling, perform intelligent controlled release analysis of soil water and fertilizer usage on the data of leaf yellowing and curling degree to obtain the intelligent controlled release data of soil water and fertilizer usage, and send the intelligent controlled release data of soil water and fertilizer usage to the terminal to perform intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0043] In the embodiments of the present invention, first, convolution calculation is performed on the abnormal data of soil nitrogen cycling, and the characteristic change trend of the data is analyzed through convolution operation. The convolution calculation is realized by convolving the abnormal data of soil nitrogen cycling with a convolution kernel (or filter). In the specific operation, first, according to the time series characteristics of the abnormal data of soil nitrogen cycling, a suitable data window size and convolution kernel are selected. The selection of the convolution kernel is based on experimental data and research on similar data in relevant literature. By gradually sliding the convolution kernel to convolve with the abnormal data of soil nitrogen cycling, the weighted sum of each time point can be obtained, that is, the smoothed result of the soil nitrogen cycling characteristics in each time period. The convolution calculation obtains a smoother and more representative soil nitrogen cycling data by weighted superposition of soil nitrogen data at different time points, thereby revealing the overall trend of nitrogen cycling. Finally, the abnormal convolution data of soil nitrogen cycling obtained through convolution calculation provides a key input for the next step, has high temporal characteristics, and can effectively reflect the main laws of nitrogen changes in the soil. Based on the abnormal convolution data of soil nitrogen cycling and the nutrient leaching loss gradient data obtained in step S41, the soil water saturation is regulated. First, the change trend of nitrogen content in the soil is analyzed by using the abnormal convolution data of soil nitrogen cycling, and combined with the nutrient leaching loss gradient data, the relationship between water and nitrogen in the soil is deduced. In this process, it is assumed that there is a certain correlation between nitrogen loss and soil water saturation, and the relationship between soil nitrogen change and water content is determined through regression analysis. For different soil types and environmental conditions, a mathematical model is established to simulate the coupling mechanism between the change of soil water saturation and nitrogen cycling. The model uses a series of weight factors to reflect the influence of water saturation on nitrogen release rate and nutrient leaching. Specifically, by setting soil water thresholds and nitrogen loss critical points, the soil water saturation is dynamically regulated. In this step, by adjusting the water parameters, the nitrogen loss caused by soil water supersaturation is reduced, and the soil is ensured to maintain an appropriate nitrogen cycle in the optimal water state. The model calculation in the regulation process is realized through a dynamic balance equation, and the optimized soil water saturation regulation data is obtained, providing a basis for the analysis of subsequent steps. According to the soil water saturation regulation data and the abnormal convolution data of soil nitrogen cycling obtained in step S42, an intelligent controlled release analysis of soil water and fertilizer dosage for the degree of yellowing and curling of leaves is carried out. First, by using the soil water saturation regulation data and combining with the soil nitrogen cycling data, the influence of water and nitrogen on crop growth is analyzed, especially the influence on the leaf growth state. Through regression analysis, a mathematical model between soil water, nitrogen content and the degree of yellowing and curling of crop leaves is established, and the influence law of water and nitrogen at different levels on the leaf state of crops is obtained. Using the data of the degree of yellowing and curling of leaves, the water and fertilizer requirements of crops at different growth stages are determined, and intelligent controlled release calculation of soil water and fertilizer dosage is carried out according to these requirements.This step uses a data-driven method to combine the growth requirements of crops with the actual conditions of the soil, and employs a dynamic optimization algorithm (such as the Particle Swarm Optimization algorithm, PSO) to adjust the release pattern of soil water and fertilizer. During the specific calculation process, according to the real-time feedback information of the crop leaf state, the amounts of fertilization and irrigation are adjusted to maintain the optimal growth environment. By calculating the difference between the amounts of water and fertilizer in the soil and the crop's demand for water and fertilizer, the intelligent controlled release system can dynamically adjust the release rate of water and fertilizer, thereby providing sufficient water and fertilizer support for the crops and reducing nutrient waste. Finally, the intelligent controlled release data of the soil water and fertilizer usage obtained is transmitted to the crop management terminal for implementing the intelligent analysis of water and fertilizer for crop yield improvement and achieving precise fertilization and irrigation.

[0044] Step S43 includes the following steps: Step S431: Analyze the long-term cumulative effect of nutrient deficiency on the abnormally convolved data of soil nitrogen cycle to obtain the long-term cumulative effect data of nutrient deficiency; Step S432: Evaluate the degradation of nutrient absorption capacity based on the data of the degree of yellowing and curling of leaves to obtain the data of the degradation of crop nutrient absorption capacity; Step S433: Analyze the enhanced proportion of soil ventilation based on the soil water saturation regulation data to obtain the enhanced proportion of soil ventilation; Step S434: Perform multi-objective optimization of the stage water and fertilizer ratio on the data of the degradation of crop nutrient absorption capacity according to the long-term cumulative effect data of nutrient deficiency and the enhanced proportion of soil ventilation to obtain the multi-objective optimization data of the water and fertilizer ratio; Step S435: Conduct intelligent controlled release analysis of soil water and fertilizer usage based on the multi-objective optimization data of the water and fertilizer ratio to obtain the intelligent controlled release data of soil water and fertilizer usage, and send the intelligent controlled release data of soil water and fertilizer usage to the terminal to execute the intelligent analysis of water and fertilizer for crop yield improvement.

[0045] In the embodiment of the present invention, based on the abnormally convolved data of soil nitrogen cycle obtained in step S41, the long-term cumulative effect analysis of nutrient deficiency is carried out. This step aims to analyze the long-term impact of long-term nutrient deficiency on soil and crop growth through the changes in the nitrogen cycle in the soil. To achieve this goal, by performing multi-period cumulative analysis on the soil nitrogen cycle data, the correlation between nitrogen loss in the soil and soil nutrient deficiency is established. The specific method is to calculate the nitrogen loss value in each time period and accumulate it to evaluate the consumption trend of long-term deficiency on soil nutrients. This process uses the cumulative effect analysis formula: , where represents the cumulative effect of nutrient deficiency in the th time period, is the nitrogen concentration in the th time period, is the The loss rate during a period. Through the analysis of the long-term cumulative effect, the cumulative effect data of nutrient deficiency can be obtained, that is, the gradual impact of nitrogen loss on soil nutrients over a long period, providing data support for subsequent nutrient regulation. Based on step S431, the degradation of the crop's nutrient absorption capacity is evaluated using the data on the degree of leaf yellowing and curling. The health status of the leaves directly reflects the crop's nutrient absorption capacity. The phenomena of leaf yellowing and curling are usually caused by nutrient deficiency or absorption disorders. First, through image processing technology, the degree of leaf yellowing and curling is quantitatively analyzed to obtain the yellowing area and curling angle of the leaves. On this basis, combined with the nutrient content such as nitrogen in the soil, a regression analysis method is used to construct a mathematical model between the nutrient absorption capacity and the leaf health status. This model estimates the degradation degree of the crop's nutrient absorption capacity through the multivariate regression of the visual characteristics of the leaves and the soil nutrient data. Specifically, the following linear regression model is used to describe the degradation of the nutrient absorption capacity: ; where, represents the degradation score of the crop's nutrient absorption capacity, is the area of the yellowing area of the leaves, is the curling angle of the leaves, is the nitrogen content in the soil, , , , are regression coefficients (for example, = 2.5, = 0.3, = 0.5, = 0.1). Through this analysis, the degradation data of the crop's nutrient absorption capacity are obtained, providing data support for subsequent optimization of the water-fertilizer ratio. Based on the soil water saturation regulation data in step S42, the analysis of the soil air permeability enhancement ratio is carried out. The air permeability of the soil plays a crucial role in the respiration and nutrient absorption of the roots. Especially when the soil saturation is too high or too low, the air permeability will decrease significantly, affecting the growth of the crops. Therefore, first, through the real-time monitoring of the soil water saturation data, the current soil saturation is determined, and the analysis is carried out by establishing a mathematical relationship model between the soil air permeability and the water saturation. The physical and chemical model is used to calculate the soil air permeability enhancement ratio, and the formula is as follows: ; where, Let \(\Delta K\) be the soil air permeability enhancement ratio, \(K_{sat}\) be the hydraulic conductivity of the soil in the saturated state, \(\theta\) be the soil water saturation, and \(K_{ref}\) be the reference soil air permeability constant. By calculating the soil air permeability enhancement ratio in real time, the aeration capacity of the soil under different moisture conditions can be evaluated, providing effective data support for subsequent optimization of the water-fertilizer ratio. This step performs stage-based multi-objective optimization of the water-fertilizer ratio based on the long-term cumulative effect data of nutrient deficiency, the data of nutrient uptake capacity degradation, and the data of soil air permeability enhancement ratio obtained in steps S431, S432, and S433. The optimization objective is to comprehensively consider the soil nutrient status, the nutrient requirements of the crop, and the soil air permeability, and dynamically adjust the water-fertilizer ratio to achieve the best crop growth effect. In this process, a multi-objective particle swarm optimization algorithm (PSO) is used to solve the problem. The optimization objective function considers multiple objectives such as crop growth, nutrient use efficiency, and water-fertilizer loss. Through optimization, the optimal water-fertilizer ratio plan for each stage is obtained, providing a scientific basis for nutrient supplementation and water management of the crop. Based on the multi-objective optimization data of the water-fertilizer ratio obtained in step S434, an intelligent controlled release analysis of the soil water-fertilizer application amount is carried out. The purpose of the intelligent controlled release analysis is to dynamically adjust the time and amount of fertilization and irrigation according to the growth requirements of the crop and the soil moisture conditions to ensure the precise supply of water and fertilizer. In this process, a fuzzy control algorithm is used to real-time control the soil water-fertilizer application amount, and the irrigation and fertilization strategies are dynamically adjusted according to the real-time data. The specific control strategy adjusts the fertilization amount and irrigation amount for each period through the control system algorithm to make them highly match the growth requirements of the crop. Finally, the intelligent controlled release data of the soil water-fertilizer application amount is sent to the terminal device to execute the optimized water-fertilizer management strategy in real time and achieve an accurate increase in crop yield per unit area.

[0046] The present invention also provides a water-fertilizer intelligent analysis system for improving crop yield per unit area in a farmland area, which is used to execute the water-fertilizer intelligent analysis method for improving crop yield per unit area in a farmland area as described above. The water-fertilizer intelligent analysis system for improving crop yield per unit area in a farmland area includes: An irrigation basin farmland state monitoring module, which is used to obtain farmland area structure data; extract the irrigation water flow direction from the farmland area structure data to obtain farmland irrigation water flow direction data; deploy sensors in multiple directions based on the farmland irrigation water flow direction data, and perform real-time monitoring of the irrigation basin farmland state, thereby generating irrigation basin farmland state monitoring data; Soil volume moisture saturation extraction module, which is used to collect crop morphological images through an electronic monitoring device and based on the farmland irrigation water flow direction data, so as to obtain crop morphological images in the water flow direction area; evaluate the degree of yellowing and curling of leaves in the crop morphological images in the water flow direction area to obtain data on the degree of yellowing and curling of leaves; extract the soil volume moisture saturation of the yellowing and curling crops from the farmland status monitoring data in the irrigation basin according to the data on the degree of yellowing and curling of leaves, so as to obtain the soil volume moisture saturation of the yellowing and curling crops. Soil nitrogen cycle anomaly analysis module, which is used to extract the change in nutrient element content from the farmland status monitoring data in the irrigation basin according to the soil volume moisture saturation to obtain data on the change in soil nutrient element content; quantify the nutrient leaching loss gradient for the data on the change in soil nutrient element content to obtain data on the nutrient leaching loss gradient; perform nitrogen cycle anomaly simulation quantification based on the data on the nutrient leaching loss gradient to obtain soil nitrogen cycle anomaly data. Intelligent analysis and regulation module for water and fertilizer dosage, which is used to perform intelligent controlled release analysis of soil water and fertilizer dosage on the data on the degree of yellowing and curling of leaves based on the soil nitrogen cycle anomaly data to obtain intelligent controlled release data on soil water and fertilizer dosage, and send the intelligent controlled release data on soil water and fertilizer dosage to the terminal to execute the intelligent analysis of water and fertilizer for improving crop yield per unit area.

[0047] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement, characterized in that: The following steps are involved: Step S1: Acquire farmland regional structure data; extract irrigation water flow direction from the farmland regional structure data to obtain farmland irrigation water flow direction data; deploy multi-directional sensors based on the farmland irrigation water flow direction data, and conduct real-time monitoring of farmland status in the irrigation basin, thereby generating irrigation basin farmland status monitoring data; Step S2: using electronic monitoring equipment and based on the farmland irrigation water flow direction data, crop morphology images are collected to obtain crop morphology images in the water flow direction area; the degree of leaf yellowing and curling of the crop morphology images in the water flow direction area is evaluated to obtain leaf yellowing and curling degree data; based on the leaf yellowing and curling degree data, the soil volume moisture saturation of the crop with yellowing and curling leaves is extracted from the irrigation basin farmland status monitoring data to obtain the soil volume moisture saturation of the crop with yellowing and curling leaves; Step S3: extracting the changes in nutrient content of the irrigation basin farmland status monitoring data according to the soil volume water saturation to obtain soil nutrient content change data; quantifying the nutrient leaching loss gradient of the soil nutrient content change data to obtain nutrient leaching loss gradient data; simulating and quantifying the nitrogen cycle anomaly based on the nutrient leaching loss gradient data to obtain soil nitrogen cycle anomaly data; Step S4: Based on the soil nitrogen cycle abnormality data, the leaf yellowing and curling degree data is analyzed for soil water and fertilizer intelligent controlled release, and the soil water and fertilizer intelligent controlled release data is obtained, and the soil water and fertilizer intelligent controlled release data is sent to the terminal to perform water and fertilizer intelligent analysis for increasing crop yield.

2. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: using electronic monitoring equipment and based on the farmland irrigation water flow direction data, crop morphology images are collected to obtain crop morphology images in the water flow direction area; Step S22: performing growth inhibition distribution recognition on the crop morphology image in the water flow area to obtain crop growth inhibition distribution data; Step S23: evaluating the degree of leaf yellowing and curling of the crop morphological image in the water flow area based on the crop growth inhibition distribution data to obtain leaf yellowing and curling degree data; Step S24: extracting the soil volume moisture saturation of crops with yellowing and curling leaves from the irrigation basin farmland status monitoring data according to the leaf yellowing and curling degree data, and obtaining the soil volume moisture saturation of crops with yellowing and curling leaves.

3. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Calculate the soil particle dispersion density based on the soil volume water saturation to obtain soil particle dispersion density data; Step S32: extracting the nutrient element content change of the irrigation basin farmland status monitoring data according to the soil volume water saturation to obtain soil nutrient element content change data; Step S33: quantifying the nutrient leaching loss gradient of the soil nutrient element content change data according to the soil particle dispersion density data and the farmland irrigation water flow direction data to obtain the nutrient leaching loss gradient data; Step S34: Perform nitrogen cycle anomaly simulation and quantification based on nutrient leaching loss gradient data and soil volume water saturation to obtain soil nitrogen cycle anomaly data.

4. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 3 is characterized in that: Step S33 includes the following steps: Step S331: evaluating the soil particle size interval of the soil particle dispersion density data to obtain the soil particle size interval; Step S332: performing hydrodynamic soil porosity fluctuation calculation according to the soil particle size range and farmland irrigation water flow direction data to obtain hydrodynamic soil porosity fluctuation data; Step S333: performing soil profile nutrient loss numerical iteration on soil nutrient element content change data based on hydrodynamic soil porosity fluctuation data to obtain soil profile nutrient loss iteration data; Step S334: evaluating the expansion amount of nutrient sinking range on the iterative data of nutrient loss in the soil profile to obtain the expansion amount of nutrient sinking range; Step S335: quantify the nutrient leaching loss gradient based on the soil profile nutrient loss iteration data and the nutrient sinking range expansion amount to obtain the nutrient leaching loss gradient data.

5. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 3 is characterized in that: Step S333 includes the following steps: The hydrodynamic nonlinear pore expansion relationship is analyzed for the hydrodynamic soil porosity fluctuation data to obtain the hydrodynamic nonlinear pore expansion relationship; The nonlinear pore expansion relationship of hydrodynamics is analyzed by water flow shear stress in soil profile to obtain the pore water flow stress data in soil profile. The velocity difference of different directions of the pore water flow stress data of the soil profile is deduced to obtain the velocity difference of different directions of the pore penetration of the profile; Based on the hydrodynamic nonlinear pore expansion relationship and the velocity difference of the cross-section pores at different seepage directions, the seepage convection pressure is evaluated to obtain the cross-section pore seepage convection pressure data; According to the Richards equation, the velocity difference of different cross-section pore infiltration directions and the cross-section pore infiltration convection pressure data, the soil nutrient element content change data was numerically iterated to obtain the soil profile nutrient loss iterative data.

6. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 3 is characterized in that: Step S34 includes the following steps: Step S341: performing soil oxygen content decrease gradient analysis according to soil volume water saturation to obtain soil oxygen content decrease gradient data; Step S342: performing an anaerobic microbial activity enhancement function relationship analysis based on the nutrient leaching loss gradient data and the soil oxygen content decrease gradient data to obtain an anaerobic microbial activity enhancement relationship function; Step S343: performing denitrification rate enhancement coupling according to the anaerobic microbial activity enhancement relationship function to obtain denitrification rate enhancement coupling data; Step S344: performing asymptotic fitting estimation of nitrogen release on the denitrification rate enhancement coupling data to obtain nitrogen release fitting estimation data; Step S345: Perform nitrogen cycle anomaly simulation and quantification based on the nitrogen release fitting estimation data to obtain soil nitrogen cycle anomaly data.

7. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 6 is characterized in that: Step S344 includes the following steps: Based on the denitrification rate enhanced coupling data, nitrogen release isotropic mapping is performed to obtain rate-matched nitrogen release mapping data; According to the denitrification rate enhanced coupling data, the rate-matched nitrogen release mapping data was analyzed for multiple extreme values ​​of ammonia release, and multiple extreme values ​​of rate-matched ammonia release were obtained; Perform time delay calculation on multiple extreme values ​​of rate-matched ammonia release to obtain multiple extreme value time delay data; Based on multiple extreme value time delay data and rate matching of multiple extreme values ​​of ammonia release, the mean difference of cyclic repeatability release is calculated to obtain the extreme value mean difference of ammonia release cycle; The nitrogen release asymptotic fitting estimation was performed on the extreme mean difference of the ammonia release cycle according to the maximum likelihood estimation method to obtain the nitrogen release fitting estimation data.

8. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing convolution calculation on the soil nitrogen cycle abnormal data to obtain soil nitrogen cycle abnormal convolution data; Step S42: performing soil water saturation control on the soil volume water saturation according to the soil nitrogen cycle abnormal convolution data and the nutrient leaching loss gradient data to obtain soil water saturation control data; Step S43: Based on the soil moisture saturation control data and the soil nitrogen cycle abnormal convolution data, the leaf yellowing and curling degree data is analyzed for soil water and fertilizer intelligent controlled release, and the soil water and fertilizer intelligent controlled release data is obtained, and the soil water and fertilizer intelligent controlled release data is sent to the terminal to perform water and fertilizer intelligent analysis for improving crop yield.

9. The water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement according to claim 8 is characterized in that: Step S43 includes the following steps: Step S431: analyzing the long-term cumulative effect of nutrient deficiency on the soil nitrogen cycle abnormal convolution data to obtain the long-term cumulative effect data of nutrient deficiency; Step S432: evaluating the degradation of nutrient absorption capacity of leaves on the data of yellowing and curling degree of leaves to obtain the degradation data of nutrient absorption capacity of crops; Step S433: analyzing the soil air permeability enhancement ratio based on the soil water saturation control data to obtain the soil air permeability enhancement ratio; Step S434: performing phased multi-objective optimization of water-fertilizer ratio on the crop nutrient absorption capacity degradation data according to the long-term cumulative effect data of nutrient deficiency and the soil permeability enhancement ratio, and obtaining multi-objective optimization data of water-fertilizer ratio; Step S435: Perform intelligent controlled-release analysis of soil water and fertilizer usage based on the multi-objective optimization data of water-fertilizer ratio to obtain soil water and fertilizer usage intelligent controlled-release data, and send the soil water and fertilizer usage intelligent controlled-release data to the terminal to perform water and fertilizer intelligent analysis for improving crop yield.

10. An intelligent water and fertilizer analysis system based on regionalized crop yield improvement in farmland, characterized in that: Used to execute the water and fertilizer intelligent analysis method based on farmland regionalization crop yield improvement as claimed in claim 1, the water and fertilizer intelligent analysis system based on farmland regionalization crop yield improvement comprises: The irrigation basin farmland status monitoring module is used to obtain farmland regional structure data; extract irrigation water flow direction from farmland regional structure data to obtain farmland irrigation water flow direction data; deploy multi-directional sensors based on farmland irrigation water flow direction data, and conduct real-time monitoring of the irrigation basin farmland status, thereby generating irrigation basin farmland status monitoring data; The soil volumetric water saturation extraction module is used to collect crop morphological images based on farmland irrigation water flow direction data through electronic monitoring equipment to obtain crop morphological images in the water flow direction area; evaluate the degree of leaf yellowing and curling of the crop morphological images in the water flow direction area to obtain leaf yellowing and curling degree data; extract the soil volumetric water saturation of crops with yellowing and curling leaves from the irrigation basin farmland status monitoring data according to the leaf yellowing and curling degree data to obtain the soil volumetric water saturation of crops with yellowing and curling leaves; The soil nitrogen cycle anomaly analysis module is used to extract the changes in nutrient content of the irrigation basin farmland status monitoring data according to the soil volume water saturation to obtain soil nutrient content change data; quantify the nutrient leaching loss gradient of the soil nutrient content change data to obtain nutrient leaching loss gradient data; simulate and quantify the nitrogen cycle anomaly based on the nutrient leaching loss gradient data to obtain soil nitrogen cycle anomaly data; The intelligent analysis and control module for water and fertilizer usage is used to perform intelligent controlled release analysis of soil water and fertilizer usage on the data of leaf yellowing and curling degree based on the abnormal data of soil nitrogen cycle, obtain the intelligent controlled release data of soil water and fertilizer usage, and send the intelligent controlled release data of soil water and fertilizer usage to the terminal to perform intelligent water and fertilizer analysis for improving crop yield.

Images