An agricultural product planting environment detection method and system

Abstract

The present invention relates to the technical field of planting environment detection, and particularly to a method and system for detecting the planting environment of agricultural products. The method includes the following steps: obtaining the soil layer state of the strawberry planting area through soil monitoring sensors, and performing an analysis of the pH fluctuation to obtain the strawberry soil layer pH fluctuation data; obtaining the strawberry plant morphology data, evaluating the root extension state, and simulating the decomposition and decay of organic matter based on the soil layer pH data to analyze the acid-induced growth retardation of strawberry roots; analyzing the over-alkaline fluctuation index of the soil layer, simulating the influence of the over-alkaline soil layer on the absorption of trace elements by strawberry roots, and performing a regression analysis of the nutrient uptake efficiency; combining the root development retardation evolution data and the nutrient uptake efficiency regression data to construct an automated planting environment detection model, and uploading the model to the cloud platform to perform the detection of the planting environment of agricultural products. The present invention makes the planting environment detection technology more perfect through the optimization of the planting environment detection technology.

Description

Technical Field

[0001] The present invention relates to the technical field of planting environment detection, and particularly to a method and system for detecting the planting environment of agricultural products. Background Art

[0002] In the past, agricultural management methods usually relied on manual experience and extensive management, and often could not timely and accurately grasp the growth conditions of soil and crops, resulting in problems such as resource waste, environmental pollution, and poor crop growth. Especially in the planting process of high-value fruits and vegetables such as strawberries, the effects of soil pH, nutrients, and moisture conditions on crop growth are particularly important. Therefore, how to optimize the planting environment through precise monitoring and data analysis has become a key issue in modern agriculture. In particular, the fluctuation of soil pH will directly affect the healthy growth of strawberry roots. An overly acidic or alkaline soil environment not only restricts the absorption of water and nutrients by strawberry roots, but also leads to retarded root development, thus affecting the growth and yield of the entire plant. At the same time, the decomposition of soil organic matter and the absorption of trace elements are also closely related to soil pH, which in turn affects the nutrient supply and quality of strawberries. Therefore, how to accurately measure the change of soil pH and optimize the regulation in combination with the growth state of strawberry roots has become an important direction to improve the planting efficiency and quality of strawberries. However, there is a problem in a traditional method for detecting the planting environment of agricultural products that the analysis of the influence on the development of strawberry roots is inaccurate, resulting in a large error in the detection of the planting environment. Summary of the Invention

[0003] Based on this, it is necessary to provide a method and system for detecting the planting environment of agricultural products to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for detecting the planting environment of agricultural products, the method includes the following steps:

[0005] Step S1: Monitor the soil layer state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil layer state monitoring data; analyze the pH fluctuation of the strawberry soil layer state monitoring data to obtain strawberry soil layer pH fluctuation data;

[0006] Step S2: Obtain strawberry plant morphological data; evaluate the root extension state of the strawberry plant morphological data to obtain the strawberry root extension state; quantify the decay of the decomposition of vertically permeating organic matter based on the strawberry soil layer pH fluctuation data to obtain vertically permeating organic matter decomposition decay data; simulate and evolve the retarded development due to over-acidity of the strawberry root extension state based on the vertically permeating organic matter decomposition decay data to obtain strawberry root over-acid retarded development evolution data;

[0007] Step S3: Analyze the over-alkaline fluctuation index of the soil pH fluctuation data of strawberries to obtain the soil layer over-alkaline fluctuation index; based on the soil layer over-alkaline fluctuation index, conduct a simulation evaluation of the reduction in the absorption of trace elements in the soil layer for the root extension state of strawberries to obtain the data on the reduction in the absorption of trace elements in the over-alkaline soil layer; conduct a regression analysis of the nutrient uptake efficiency constraint for the root extension state of strawberries based on the data on the reduction in the absorption of trace elements in the over-alkaline soil layer to obtain the regression data on the nutrient uptake efficiency constraint.

[0008] Step S4: Based on the data on the retarded evolution of the over-acid root development of strawberries and the regression data on the nutrient uptake efficiency constraint, construct an automated planting environment detection model to obtain the automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform the detection of the planting environment of agricultural products.

[0009] Preferably, step S1 includes the following steps:

[0010] Step S11: Monitor the soil layer state of the strawberry planting area through a soil monitoring sensor to obtain the soil layer state monitoring data of strawberries.

[0011] Step S12: Clean the soil layer state monitoring data of strawberries to obtain the cleaned soil layer state monitoring data of strawberries.

[0012] Step S13: Conduct an analysis of the pH fluctuation of the cleaned soil layer state monitoring data of strawberries to obtain the soil layer pH fluctuation data of strawberries.

[0013] Preferably, step S2 includes the following steps:

[0014] Step S21: Obtain the morphological data of strawberry plants; evaluate the root extension state of the morphological data of strawberry plants to obtain the root extension state of strawberries.

[0015] Step S22: Analyze the intensity of the temporal variation of soil acidity for the soil layer pH fluctuation data of strawberries to obtain the data on the intensity of the temporal variation of soil acidity.

[0016] Step S23: Quantify the decomposition decay of vertically permeating organic matter based on the data on the intensity of the temporal variation of soil acidity to obtain the data on the decomposition decay of vertically permeating organic matter.

[0017] Step S24: Analyze the self-similar structure of the decay rate for the data on the decomposition decay of vertically permeating organic matter to obtain the self-similar data on the vertical decomposition decay of organic matter.

[0018] Step S25: Fit the loss of nitrogen conversion order of magnitude based on the self-similar data on the vertical decomposition decay of organic matter to obtain the data on the loss of nitrogen conversion order of magnitude.

[0019] Step S26: Based on the self-similar data of vertical decomposition and decay of organic matter and the data of the order-of-magnitude loss of nitrogen transformation, perform an over-acid development retardation simulation evolution on the strawberry root system extension state to obtain the over-acid development retardation evolution data of the strawberry root system.

[0020] Preferably, step S23 includes the following steps:

[0021] Step S231: Perform spatial interpolation of the soil layer acidity temporal change intensity data on the vertical section of the soil layer to obtain the vertical section acidity interpolation data;

[0022] Step S232: Fit the inverse decay relationship of the microbial community according to the vertical section acidity interpolation data to obtain the inverse decay relationship data of the microbial community;

[0023] Step S233: Perform a simulation inference on the difference in the attenuation rate of the relative abundance of the microbial community for the inverse decay relationship data of the microbial community to obtain the difference in the attenuation rate of the relative abundance of the microbial community;

[0024] Step S234: Based on the inverse decay relationship data of the microbial community and the difference in the attenuation rate of the relative abundance of the microbial community, perform a weakening fitting of the catalytic efficiency of enzyme configuration evolution to obtain the weakening data of the catalytic efficiency of enzyme configuration evolution;

[0025] Step S235: Quantify the decomposition and decay of organic matter vertically penetrating the soil layer according to the weakening data of the catalytic efficiency of enzyme configuration evolution, the difference in the attenuation rate of the relative abundance of the microbial community, and the inverse decay relationship data of the microbial community to obtain the decomposition and decay data of vertically penetrating organic matter.

[0026] Preferably, step S25 includes the following steps:

[0027] Step S251: Perform multi-level frequency domain decomposition processing on the self-similar data of vertical decomposition and decay of organic matter to obtain multi-level spectrum decomposition decay intensity data;

[0028] Step S252: Analyze the soil nitrification inhibition index based on the multi-level spectrum decomposition decay intensity data to obtain the soil nitrification inhibition index;

[0029] Step S253: Calculate the nitrogen release decline index according to the multi-level spectrum decomposition decay intensity data and the soil nitrification inhibition index to obtain the nitrogen release decline index;

[0030] Step S254: Fit the order-of-magnitude loss of nitrogen transformation according to the nitrogen release decline index to obtain the order-of-magnitude loss data of nitrogen transformation.

[0031] Preferably, step S253 includes the following steps:

[0032] Draw a multi-level decay intensity fluctuation curve for the multi-level spectrum decomposition decay intensity data to obtain the multi-level decay intensity fluctuation curve;

[0033] Perform multi-layer single-point decay mutation entropy value analysis on the multi-layer decay intensity fluctuation curve to obtain the multi-layer single-point decay mutation entropy value;

[0034] Deduce the decay interval of the non-linear mineralization rate of nitrogen based on the multi-layer single-point decay mutation entropy value to obtain the non-linear mineralization rate decay interval;

[0035] Evaluate the reduction of nitrifying microorganism activity on the soil nitrification inhibition index to obtain the data of the reduction of nitrifying microorganism activity;

[0036] Perform nitrogen release decline index calculation based on the non-linear mineralization rate decay interval and the data of the reduction of nitrifying microorganism activity to obtain the nitrogen release decline index.

[0037] Preferably, step S3 includes the following steps:

[0038] Step S31: Analyze the over-alkaline fluctuation index of the strawberry soil layer pH fluctuation data to obtain the soil layer over-alkaline fluctuation index;

[0039] Step S32: Based on the soil layer over-alkaline fluctuation index, perform a simulation evaluation on the reduction of trace element absorption in the soil layer for the strawberry root system extension state to obtain the data of the reduction of trace element absorption in the over-alkaline soil layer;

[0040] Step S33: Deduce the weakening interval of the soil water holding capacity according to the soil layer over-alkaline fluctuation index to obtain the weakening interval of the soil water holding capacity;

[0041] Step S34: Perform a regression analysis on the nutrient uptake efficiency restriction of the strawberry root system extension state according to the data of the reduction of trace element absorption in the over-alkaline soil layer and the weakening interval of the soil water holding capacity to obtain the regression data of the nutrient uptake efficiency restriction.

[0042] Preferably, step S32 includes the following steps:

[0043] Step S321: Perform equidistant discrete difference processing on the soil layer over-alkaline fluctuation index to obtain the over-alkaline disturbance amplitude change sequence;

[0044] Step S322: Perform disordered differential processing on the decrease of the available content of soil trace elements based on the over-alkaline disturbance amplitude change sequence to obtain the disordered data of the decrease of the available content of trace elements;

[0045] Step S323: Analyze the continuity rate of the inflection point decline of the disordered data of the decrease of the available content to obtain the continuity rate of the inflection point of the content decrease;

[0046] Step S324: Based on the disordered data of the decrease in available state content and the continuity rate of the inflection point of the content decrease, conduct a simulation evaluation of the trace element absorption reduction in the soil layer for the strawberry root system extension state, and obtain the trace element absorption reduction data in the over-alkaline soil layer.

[0047] Preferably, step S33 includes the following steps:

[0048] Step S331: Conduct a simulation of the discrete deformation of the soil layer in the soil layer according to the over-alkaline fluctuation index of the soil layer to obtain soil discrete deformation data;

[0049] Step S332: Based on the soil discrete deformation data, conduct an expansion mapping of the soil pore structure to obtain soil pore structure expansion mapping data;

[0050] Step S333: Quantify the anisotropic attenuation of soil capillary force according to the soil pore structure expansion mapping data to obtain capillary force anisotropic attenuation data;

[0051] Step S334: Conduct an interval calculation of the weakening of the water holding capacity of the soil layer according to the capillary force anisotropic attenuation data to obtain the interval of the weakening of the water holding capacity of the soil layer.

[0052] Preferably, the present invention also provides an agricultural product planting environment detection system for implementing the agricultural product planting environment detection method described above. The agricultural product planting environment detection system includes:

[0053] A pH fluctuation analysis module for monitoring the soil layer state in the strawberry planting area through a soil monitoring sensor to obtain strawberry soil layer state monitoring data; and conducting a pH fluctuation analysis on the strawberry soil layer state monitoring data to obtain strawberry soil layer pH fluctuation data;

[0054] A developmental retardation simulation evolution module for obtaining strawberry plant morphology data; evaluating the root system extension state of the strawberry plant morphology data to obtain the strawberry root system extension state; quantifying the decay of the vertical penetration of organic matter decomposition based on the strawberry soil layer pH fluctuation data to obtain vertical penetration organic matter decomposition decay data; and conducting an over-acid developmental retardation simulation evolution on the strawberry root system extension state based on the vertical penetration organic matter decomposition decay data to obtain strawberry root system over-acid developmental retardation evolution data;

[0055] A nutrient uptake efficiency restriction analysis module for analyzing the over-alkaline fluctuation index of the strawberry soil layer pH fluctuation data to obtain the over-alkaline fluctuation index of the soil layer; conducting a simulation evaluation of the trace element absorption reduction in the soil layer for the strawberry root system extension state based on the over-alkaline fluctuation index of the soil layer to obtain trace element absorption reduction data in the over-alkaline soil layer; and conducting a nutrient uptake efficiency restriction regression analysis on the strawberry root system extension state according to the trace element absorption reduction data in the over-alkaline soil layer to obtain nutrient uptake efficiency restriction regression data;

[0056] The planting environment detection model construction module is used to construct an automated planting environment detection model based on the data of the stunted evolution of strawberry roots due to excessive acidity and the regression data of nutrient uptake efficiency constraints, and obtain the automated planting environment detection model; the automated planting environment detection model is sent to the cloud platform to perform the detection of the planting environment of agricultural products.

[0057] The beneficial effects of the present invention are as follows: By using the soil monitoring sensor to obtain the soil layer state data of the strawberry planting area in real time, the change of soil pH can be accurately grasped. The pH has a crucial impact on the growth of strawberries. Especially during the process of root absorption of water and nutrients, an overly acidic or alkaline soil environment will limit the growth of strawberries. By analyzing the fluctuation data of soil pH, the abnormal fluctuations of soil pH can be detected in time, providing data support for subsequent soil improvement, and then ensuring that strawberry plants grow in a suitable environment and improving the yield and quality of strawberries. By obtaining the morphological data of strawberry plants and evaluating the stretching state of the roots, the growth status of the roots under different soil conditions can be intuitively understood. The growth of the roots is affected by factors such as soil pH and nutrient content, and the fluctuation of pH has a direct relationship with the development of the roots. By analyzing the decomposition and decay of vertically permeating organic matter, the impact of the decomposition of organic matter in the soil on the growth of strawberry roots can be revealed, thereby predicting the retardation effect of the overly acidic environment on root development and providing a basis for optimizing the soil and improving planting techniques. By analyzing the overly alkaline fluctuation index of the soil layer pH fluctuation data of strawberries, the impact of the overly alkaline environment on the absorption of trace elements in the soil can be deeply understood. Overly alkaline soil often leads to a reduction in the absorption of trace elements, which in turn affects the growth and development of strawberries. Through the simulation evaluation of the reduction in the absorption of trace elements based on the overly alkaline fluctuation index, the limiting factors for the absorption of nutrients by strawberry roots in overly alkaline soil can be identified and analyzed. In addition, the regression analysis of nutrient uptake efficiency constraints can further clarify the key factors affecting the growth of strawberries, providing specific guidance for improving soil management and optimizing the nutrient supply of strawberries. Combining the data of the stunted evolution of strawberry roots due to excessive acidity and the regression data of nutrient uptake efficiency constraints to construct an automated planting environment detection model can realize the comprehensive monitoring and intelligent management of the strawberry planting environment. By uploading this model to the cloud platform, farm managers can obtain real-time data on the soil status, root development, and nutrient uptake in the strawberry planting area, so as to precisely regulate the planting environment. This technology not only improves the intelligent level of strawberry planting, but also provides a replicable solution for large-scale agricultural planting, promoting the development of agriculture towards a more efficient, environmentally friendly, and precise direction. Therefore, the present invention is an optimized treatment of a traditional method for detecting the planting environment of agricultural products, solving the problem that the traditional method for detecting the planting environment of agricultural products has inaccurate analysis of the impact on the development of strawberry roots, resulting in large errors in the detection of the planting environment, improving the accuracy of the analysis of the impact on the development of strawberry roots, and reducing the errors in the detection of the planting environment. Description of the Drawings

[0058] Figure 1 It is a schematic diagram of the step flow of a method for detecting the planting environment of agricultural products;

[0059] Figure 2 It is Figure 1 a schematic diagram of the detailed implementation steps of step S2 in

[0060] Figure 3 It is Figure 1 a schematic diagram of the detailed implementation steps of step S3 in Specific implementation manner

[0061] Please refer to Figures 1 to 3 , a method for detecting the planting environment of agricultural products, the method includes the following steps:

[0062] Step S1: Monitor the soil layer state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil layer state monitoring data; analyze the pH fluctuation of the strawberry soil layer state monitoring data to obtain strawberry soil layer pH fluctuation data;

[0063] Step S2: Obtain strawberry plant morphological data; evaluate the root extension state of the strawberry plant morphological data to obtain the strawberry root extension state; quantify the decomposition decay of vertically permeating organic matter based on the strawberry soil layer pH fluctuation data to obtain vertically permeating organic matter decomposition decay data; simulate and evolve the over-acid growth retardation of the strawberry root extension state based on the vertically permeating organic matter decomposition decay data to obtain strawberry root over-acid growth retardation evolution data;

[0064] Step S3: Analyze the over-alkaline fluctuation index of the strawberry soil layer pH fluctuation data to obtain the soil layer over-alkaline fluctuation index; simulate and evaluate the reduction of trace element absorption in the soil layer of the strawberry root extension state based on the soil layer over-alkaline fluctuation index to obtain over-alkaline soil layer trace element absorption reduction data; perform a regression analysis on the nutrient uptake efficiency restriction of the strawberry root extension state according to the over-alkaline soil layer trace element absorption reduction data to obtain nutrient uptake efficiency restriction regression data;

[0065] Step S4: Construct an automated planting environment detection model based on the strawberry root over-acid growth retardation evolution data and the nutrient uptake efficiency restriction regression data to obtain an automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform the detection of the agricultural product planting environment.

[0066] In the embodiment of the present invention, referring to Figure 1 described above, it is a schematic diagram of the step flow of a method for detecting the planting environment of agricultural products of the present invention. In this example, the method for detecting the planting environment of agricultural products includes the following steps:

[0067] Step S1: monitoring the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; performing pH fluctuation analysis on the strawberry soil state monitoring data to obtain strawberry soil pH fluctuation data;

[0068] In an embodiment of the present invention, soil monitoring sensors with multi-point layout are evenly implanted into the 0-30 cm soil layer of the strawberry planting area, and soil temperature, water content, conductivity and pH value data are collected in real time according to the standard of arranging 4 sensor nodes per square meter. The soil monitoring sensor adopts a high-sensitivity electrochemical pH sensor module with a resolution of 0.01 units and a response time of less than 2 seconds, and synchronously records soil temperature and humidity. By setting the daily sampling frequency to once every 15 minutes and continuously monitoring for 7 days, a total of 672 groups of strawberry soil layer status monitoring data are obtained. For the collected strawberry soil layer status monitoring data, data cleaning is first performed to eliminate abnormal mutation values (values with a rate of change greater than 3 times the standard deviation of the average value) and data missing parts during abnormal device disconnection. The cleaned data is pre-processed using a method based on time series smoothing filtering (the sliding window size is set to 5 groups of data). Subsequently, the pH fluctuation analysis of the strawberry soil layer status monitoring cleaning data is performed according to the daily time series, and the local extreme value extraction method (i.e., extracting the maximum and minimum pH changes within 24 hours and recording the difference) is adopted to form a pH fluctuation amplitude sequence within a continuous time period. Based on this sequence, the fluctuation trend change rate, that is, the difference in the fluctuation amplitude between two adjacent time points, is further calculated to form the pH fluctuation data of the strawberry soil layer.

[0069] Step S2: obtaining strawberry plant morphological data; evaluating the root extension state of the strawberry plant morphological data to obtain the root extension state of the strawberry; quantifying the decomposition and decay of vertical permeable organic matter in the soil layer based on the pH fluctuation data of the strawberry soil layer to obtain the vertical permeable organic matter decomposition and decay data; simulating the evolution of the acid stunting of the strawberry root extension state based on the vertical permeable organic matter decomposition and decay data to obtain the acid stunting evolution data of the strawberry root system;

[0070] In the embodiments of the present invention, morphological data of strawberry plants are obtained. Five top and five side images of the plants are collected daily at 10:00 am and 4:00 pm respectively by a high-definition multispectral camera, and morphological parameters such as the root collar diameter, the spread width of stems and leaves, the number of leaves, and the single leaf area of strawberry plants are extracted by combining a machine vision algorithm (using a partition extraction technique based on edge detection and color segmentation). At least 30 groups of morphological data are recorded for each strawberry plant, and the initial assessment of the root system extension state is carried out by setting a threshold for the root collar diameter growth rate (0.05 cm / day) and the single leaf area expansion rate (2 cm² / day). The evaluation criterion is that if the growth rate is lower than the above thresholds for five consecutive days, it is determined to be in a state of restricted extension. Based on the fluctuating data of the soil layer pH of strawberries, the acid peak displacement tracking method (tracking the vertical displacement of the acid peak in the soil profile based on the change direction of the lowest daily pH value) is used to quantify the decay of the organic matter decomposition in the vertical infiltration of the soil layer. The specific method is to divide the soil profile of 0-30 cm into layers of 5 cm each, calculate the weighted average of the pH change rate of each layer, and then infer the decay trend of the organic matter decomposition rate with depth based on the downward movement rate of the acid wave peak, and finally obtain the decay data of the vertical infiltration of the organic matter decomposition. Subsequently, based on the decay data of the vertical infiltration of the organic matter decomposition, a model of the correlation strength between the standardized acid accumulation impact amount (using the cumulative change amount of the unit pH value per 5 cm depth as a factor) and the root system extension state is established to simulate the evolution of acid-induced growth retardation, and the evolution data of acid-induced growth retardation of strawberry roots are output.

[0071] Step S3: Analyze the over-alkaline fluctuation index of the fluctuating data of the soil layer pH of strawberries to obtain the over-alkaline fluctuation index of the soil layer; based on the over-alkaline fluctuation index of the soil layer, conduct a simulation evaluation of the reduction in the absorption of soil trace elements in the root system extension state of strawberries to obtain the data of the reduction in the absorption of soil trace elements in the over-alkaline soil layer; conduct a regression analysis of the nutrient uptake efficiency restriction on the root system extension state of strawberries based on the data of the reduction in the absorption of soil trace elements in the over-alkaline soil layer to obtain the regression data of the nutrient uptake efficiency restriction.

[0072] In the embodiments of the present invention, after processing the strawberry soil layer pH fluctuation data by using the moving weighted sliding average method (the weighting factor is set such that the data of the most recent 5 days accounts for 0.6 weight and the previous data accounts for 0.4 weight), the over-alkaline fluctuation index analysis is carried out. The over-alkaline fluctuation index is defined as the comprehensive score of the time proportion and amplitude that the daily pH is higher than 7.5. The scoring standard is that 2 points are obtained for each unit exceeding 7.5, and 1 point is added for every 10% increase in the time proportion. A comprehensive score higher than 8 points is determined as a high-risk fluctuation area. According to the obtained soil layer over-alkaline fluctuation index, the method of inferring the change rate of the available state concentration of trace elements (monitoring the change rate of the soluble state concentration of elements such as iron, zinc, and manganese in the 0-10 cm soil layer of the rhizosphere) is used to deduce the degree of reduction in the absorption of trace elements by strawberry roots. The measurement method is to measure the available state concentration of trace elements once a week by using ICP-MS (Inductively Coupled Plasma Mass Spectrometer), and perform multiple linear regression fitting in combination with the soil layer over-alkaline fluctuation index to output the data of the reduction in the absorption of trace elements in the over-alkaline soil layer. Then, based on the data of the reduction in the absorption of trace elements, the regression analysis technology of the nutrient uptake efficiency constraint coefficient is adopted, that is, taking the change rate of the absorption amount corresponding to each unit root length of the strawberry plant as an index, and the restrictive effect of trace element deficiency on the nutrient uptake efficiency is analyzed by regression, and finally the regression data of the nutrient uptake efficiency constraint is formed.

[0073] Step S4: Based on the data of the evolution of the stunted growth due to over-acidity of strawberry roots and the regression data of the nutrient uptake efficiency constraint, construct an automated planting environment detection model to obtain the automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform the detection of the planting environment of agricultural products.

[0074] In the embodiments of the present invention, based on the above-obtained data of the evolution of the stunted growth due to over-acidity of strawberry roots and the regression data of the nutrient uptake efficiency constraint, a method combining integrated feature hierarchical clustering and discriminant analysis is used to construct an automated planting environment detection model. Specifically, first, the data of the evolution of the stunted growth due to over-acidity and the regression data of the nutrient uptake efficiency constraint are standardized (mean normalization), then the environmental anomaly risk levels are divided according to the data density based on the K-means++ clustering algorithm, and then the discriminant boundaries corresponding to different levels are established in combination with the discriminant analysis method (LDA linear discriminant analysis) to form an environmental detection rule system. During the model training process, the initial learning sample size is set to 1000 groups of strawberry plant sample data, and each group of data contains at least 30 consecutive days of time series records. Finally, the trained automated planting environment detection model is compressed and stored locally through an embedded data interface, and then automatically uploaded to the cloud platform at a frequency of once an hour by using the MQTT protocol. The cloud platform is connected to the planting management system to realize the real-time detection and abnormal warning of the planting environment of strawberry agricultural products.

[0075] Step S1 includes the following steps:

[0076] Step S11: Monitor the soil layer status of the strawberry planting area through soil monitoring sensors to obtain strawberry soil layer status monitoring data;

[0077] Step S12: Clean the strawberry soil layer status monitoring data to obtain strawberry soil layer status monitoring cleaned data;

[0078] Step S13: Analyze the pH value fluctuation of the strawberry soil layer status monitoring cleaned data to obtain strawberry soil layer pH value fluctuation data.

[0079] In the embodiment of the present invention, the monitoring of the soil layer status in the strawberry planting area is implemented by deploying soil monitoring sensors in a standard grid manner in the planting area. The soil monitoring sensor selects a time domain reflectometry monitoring device of model TDR300. The burial depth is set with a monitoring node every 5 cm within the range of 0 - 30 cm, and a total of 6 layers are vertically arranged, with a horizontal spacing of 1 m for each layer, ensuring that 1 vertical sensor point array is covered every 5 square meters. Each node simultaneously collects four parameters: soil temperature, moisture content, conductivity, and pH value. The sampling frequency is fixed at once every 10 minutes, and the data storage format adopts binary coding for fast batch processing. All sensors are connected to the field concentrator through the RS485 bus protocol. The concentrator synchronizes and uploads data to the local server once an hour. The collection period is set to 30 consecutive days, and more than 300,000 groups of strawberry soil layer status monitoring data are accumulated. To ensure the stability and accuracy of the monitoring data, the concentrator automatically calibrates the probe baseline data before each collection. If the calibration deviation exceeds the set threshold (0.5%), the current cycle data will be automatically excluded. Through the above method, the complete soil layer status monitoring data of the strawberry planting area is constructed, providing a basic support for subsequent data processing.

[0080] Based on the collected strawberry soil state monitoring data, pH fluctuation analysis was performed to obtain the pH fluctuation data of strawberry soil. During the analysis, the pH value data sequence was first cleaned to remove the jump value caused by sensor failure. The elimination rule was that if the change amplitude of two consecutive measurements exceeded 1.0 pH unit, it was considered abnormal and eliminated. After cleaning, the data was processed by local weighted regression smoothing (LOWESS method, smoothing parameter set to 0.25) to weaken the interference of accidental fluctuations on the overall trend. Subsequently, the piecewise linear fitting method (each 24 hours is a segment) was used to extract the daily pH change trend, record the daily maximum and minimum values and their corresponding time points, and calculate the daily pH amplitude. The daily pH amplitude is defined as the difference between the maximum and minimum values. The pH amplitude data for 30 consecutive days were plotted into a time series curve, and the fluctuation rate change trend was analyzed by first-order difference processing. The first-order difference absolute value greater than 1.5 times the average difference value of the previous 7 days was marked as a fluctuation abnormal point, and the continuous occurrence of abnormal points was marked as a significant fluctuation period. Finally, based on the density of fluctuation anomaly points, the mean fluctuation amplitude and the maximum daily fluctuation rate, the standardized pH fluctuation index is formed after comprehensive normalization, which is the pH fluctuation data of strawberry soil. According to the pH fluctuation data of strawberry soil, the pH abnormal sections are further extracted and the distribution analysis is carried out. First, the sliding window statistical method (the window width is set to 5 days) is used to calculate the local mean of the pH fluctuation index and extract the fluctuation abnormal sudden increase section. If the mean value of the fluctuation index in the sliding window exceeds the benchmark value (the benchmark value is set as the 30-day average value plus the standard deviation of the whole area), it is defined as the acid-base abnormal period. After extracting the abnormal period, the abnormal time and spatial distribution of each monitoring node are visualized by combining the geographic information system (GIS). For the mapped abnormal high-incidence areas, classification and clustering analysis are further carried out according to the spatial density distribution (the abnormal frequency is counted in units of 10 square meters), and the DBSCAN algorithm (the density threshold is set to ≥5 abnormal points per 10 square meters, and the neighborhood radius is set to 2 meters) is used to divide the abnormal area. Finally, the abnormal sections are numbered and the corresponding time, spatial position, fluctuation intensity and fluctuation duration are recorded to form a complete database of abnormal pH fluctuations in strawberry planting areas, providing high-precision basic data support for subsequent strawberry root development analysis and soil quality evaluation.

[0081] Step S2 includes the following steps:

[0082] Step S21: obtaining strawberry plant morphological data; evaluating the root extension state of the strawberry plant morphological data to obtain the root extension state of the strawberry;

[0083] Step S22: analyzing the time-series variation intensity of the acidity of the strawberry soil layer on the pH fluctuation data to obtain the time-series variation intensity data of the soil layer acidity;

[0084] Step S23: Quantify the decomposition decay of vertically permeated organic matter based on the intensity data of the temporal variation of soil layer acidity, and obtain the decomposition decay data of vertically permeated organic matter;

[0085] Step S24: Analyze the self-similar structure of the decay rate of the decomposition decay data of vertically permeated organic matter to obtain the self-similar data of the vertical decomposition decay of organic matter;

[0086] Step S25: Fit the magnitude loss of nitrogen conversion according to the self-similar data of the vertical decomposition decay of organic matter to obtain the magnitude loss data of nitrogen conversion;

[0087] Step S26: Based on the self-similar data of the vertical decomposition decay of organic matter and the magnitude loss data of nitrogen conversion, simulate the evolution of the slow development due to over-acidity of the strawberry root system extension state, and obtain the evolution data of the slow development of the strawberry root system due to over-acidity.

[0088] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0089] Step S21: Obtain the morphological data of strawberry plants; evaluate the root system extension state of the morphological data of strawberry plants to obtain the root system extension state of strawberries;

[0090] In the embodiment of the present invention, the morphological data of strawberry plants are obtained by a high-precision three-dimensional imaging device. The scanning distance is controlled within 0.3 meters, the resolution is set to 0.05 mm, and the scanning path adopts a spiral upward winding for one week to ensure that the entire plant is covered without dead angles. To avoid environmental light interference, the scanning operation is completed from 6 am to 8 am, and the environmental light intensity is controlled below 10000 lux. The scanned point cloud data is filtered for noise, and the interference objects outside the plant (such as weeds, brackets, etc.) are removed to generate a net plant point cloud model. Subsequently, in the point cloud processing software, a segmentation algorithm based on the region growing method (setting the neighborhood radius to 0.02 m and the growth threshold to 10%) is used to separate the strawberry root neck part and the above-ground stem and leaf structure. For the root neck part, the main axis extraction algorithm (fitting the main trunk curve by the least squares method) is used to obtain the root system extension direction and morphological characteristics, and the root system extension density is evaluated by combining the point cloud density distribution analysis (the number of points per cubic centimeter). The root length, the number of branches, and the thickness of the main root are all automatically quantified and extracted, and finally, the strawberry root system extension state data is formed, including five indicators: the main root length, the maximum horizontal extension amplitude, the root system branch density, the average diameter of the main root, and the root neck bending rate, which are uniformly stored in a standardized structured data format.

[0091] Step S22: Analyze the intensity of the temporal variation of acidity for the strawberry soil layer pH fluctuation data to obtain the intensity data of the temporal variation of soil layer acidity;

[0092] In the embodiments of the present invention, the intensity of the temporal variation of the acidity of the strawberry soil layer acidity fluctuation data is analyzed. First, the time series data of the pH change within 30 days at each monitoring point is selected, and multi-scale decomposition is performed using the wavelet transform method (selecting the Daubechies 4 mother wavelet and setting the decomposition level to 3 levels). The wavelet coefficients of scale one (high-frequency part) and scale two (medium-frequency part) are extracted, and their energy ratios are calculated respectively to evaluate the intensity of the acidity fluctuation in the short cycle and the medium cycle. After normalizing the short-cycle fluctuation energy and the medium-cycle fluctuation energy of each monitoring point to the 0-1 interval, the acidity change intensity value is synthesized by weighting, where the weight of the short-cycle fluctuation is 0.7 and the weight of the medium-cycle fluctuation is 0.3. In this way, the data of the temporal variation intensity of the soil layer acidity covering the entire planting area is formed. Then, combined with GIS spatial interpolation (using the ordinary Kriging method, selecting the spherical model for the variogram model, and the optimal number of neighboring points is 12), regional distribution mapping is carried out to form a spatially continuous layer of the acidity change intensity, providing an input basis for the subsequent analysis of the decomposition and decay of organic matter.

[0093] Step S23: Quantify the decomposition and decay of the vertically permeating organic matter in the soil layer based on the data of the temporal variation intensity of the soil layer acidity to obtain the data of the decomposition and decay of the vertically permeating organic matter;

[0094] In the embodiments of the present invention, the decomposition and decay of the vertically permeating organic matter in the soil layer is quantified based on the data of the temporal variation intensity of the soil layer acidity. First, the values of the temporal variation intensity of the acidity of each layer from 0 to 30 cm are extracted at each vertical profile monitoring point. For each layer, the continuous acidity change profile curve is reconstructed using the spline interpolation method, and the curve smoothing factor is set to 0.001. Subsequently, the acidity change gradient calculation is applied to each profile, that is, the intensity difference between the upper and lower layers is calculated at intervals of 5 cm. Using the intensity difference as the input, combined with the known empirical data of the organic matter decomposition rate (the rate range is 0.5%-2% / day, linearly normalized according to the acidity change intensity), the organic matter decomposition rate is assigned. Finally, the decomposition rate values of each layer are integrated along the vertical profile to obtain the cumulative decay amount of the profile. After the cumulative decay amount is standardized, the data of the decomposition and decay of the vertically permeating organic matter is generated, with a resolution of one level per 5 cm and the unit of percentage / %, forming a complete quantitative description of the decomposition and decay of the organic matter in the vertical profile.

[0095] Step S24: Analyze the self-similar structure of the decay rate of the data of the decomposition and decay of the vertically permeating organic matter to obtain the self-similar data of the vertical decomposition and decay of the organic matter;

[0096] In an embodiment of the present invention, the self-similar structure of decay rate is analyzed based on the vertical penetration organic matter decomposition decay data. First, a piecewise logarithmic linear fitting is used for the cumulative decay curve of each profile, and the 0-30 cm interval of the profile is divided into three sub-intervals of 0-10 cm, 10-20 cm, and 20-30 cm. Linear regression is performed after logarithmic transformation, and the goodness of fit requires R² to be greater than 0.95. The regression slope of each interval is extracted as the decay rate index, and its variation law at different scales (10 cm scale) is analyzed. The ratio of the slopes of adjacent scales is calculated and the slope scale relationship diagram is drawn. If the ratio shows a power law distribution characteristic, it is defined as self-similarity. The power law function is fitted using the least squares method, and the fitting index is used as the self-similarity index, and the index range is set between 0.5 and 2. Finally, the self-similarity index of each monitoring profile is used as a descriptive parameter to form self-similar data of vertical decomposition decay of organic matter, providing basic support for the subsequent fitting of the order of magnitude loss of nitrogen conversion.

[0097] Step S25: fitting the nitrogen conversion magnitude loss according to the self-similar data of vertical decomposition decay of organic matter to obtain nitrogen conversion magnitude loss data;

[0098] In an embodiment of the present invention, the nitrogen conversion order of magnitude loss is fitted based on the self-similar data of organic matter vertical decomposition decay. First, the self-similar index sequence of each monitoring point is subjected to multi-level frequency domain decomposition processing, and the empirical mode decomposition (EMD) method is used to decompose it into several intrinsic mode functions (IMF components), and the first three IMF components with the highest energy are selected for reconstruction to form multi-layer spectrum decomposition decay intensity data. Subsequently, for the multi-layer spectrum data, the local maximum and minimum sequences are extracted respectively, and the nitrogen release inhibition intensity between each local peak and valley is calculated, which is defined as the soil nitrification inhibition index (unit: % / day). According to the reconstructed spectrum decay intensity curve and the nitrification inhibition index, the downward trend of nitrogen release rate is analyzed. The rate decline index is calculated by the sliding window average method (window width 3 days), and the nitrogen release decline slope is obtained by linear regression fitting. Finally, based on the proportional relationship between the nitrogen release decline slope and the initial nitrogen release rate, the nitrogen conversion order of magnitude loss is calculated to form standardized nitrogen conversion order of magnitude loss data, in units of %, to fully quantify the dynamic nitrogen attenuation process.

[0099] Step S26: Based on the self-similar data of vertical decomposition and decay of organic matter and the data of nitrogen conversion magnitude loss, the strawberry root extension state is simulated and evolved under acid stunting to obtain the strawberry root acid stunting evolution data.

[0100] In the embodiments of the present invention, based on the self-similar data of the vertical decomposition and decay of organic matter and the data of the order-of-magnitude loss of nitrogen transformation, a simulation evolution of the retarded development due to over-acidification of the strawberry root system is carried out. First, taking the self-similarity index as the influencing factor of the acidification rate and the order-of-magnitude loss of nitrogen transformation as the attenuation factor of nutrient supply, a root system development inhibition function with binary inputs is constructed. At each monitoring point, according to the initial stretching speed of the root system (quantified data according to step S21, unit: mm / day), by applying the dual inhibition of acidification influence and nutrient supply decline, the dynamic change of the root system stretching is iteratively simulated. Each iteration period is set to 1 day, and the root growth speed is updated every day. When the inhibition factor exceeds the threshold (set as the acidification rate influencing factor > 1.2 and nutrient attenuation > 20%), the root stretching speed decreases by 30%. If the inhibition condition holds for five consecutive days, it is recorded as a root system development retardation event. Finally, based on the simulation evolution results of all monitoring points, complete data on the retarded development due to over-acidification of the strawberry root system are formed, including the starting time, duration, cumulative stretching loss amount, and distribution range of the development retardation.

[0101] Step S23 includes the following steps:

[0102] Step S231: Perform spatial interpolation of the soil layer vertical section acidity on the time-series change intensity data of the soil layer acidity to obtain the vertical section acidity interpolation data;

[0103] Step S232: Fit the inverse decline relationship of the microbial community according to the vertical section acidity interpolation data to obtain the inverse decline relationship data of the microbial community;

[0104] Step S233: Perform simulation inference on the difference in the attenuation rate of the relative abundance of the microbial community on the inverse decline relationship data of the microbial community to obtain the difference in the attenuation rate of the relative abundance of the microbial community;

[0105] Step S234: Perform fitting on the weakening of the catalytic efficiency of the enzyme configuration evolution based on the inverse decline relationship data of the microbial community and the difference in the attenuation rate of the relative abundance of the microbial community to obtain the data on the weakening of the catalytic efficiency of the enzyme configuration evolution;

[0106] Step S235: Quantify the decomposition and decay of the vertically permeating organic matter in the soil layer according to the data on the weakening of the catalytic efficiency of the enzyme configuration evolution, the difference in the attenuation rate of the relative abundance of the microbial community, and the inverse decline relationship data of the microbial community to obtain the data on the decomposition and decay of the vertically permeating organic matter.

[0107] In the embodiments of the present invention, spatial interpolation of soil layer vertical section acidity is performed on the time series change intensity data of soil layer acidity. First, for the soil pH monitoring points arranged in the strawberry planting area, the time series change intensity values of acidity at depths of 0 cm, 5 cm, 10 cm, 15 cm, 20 cm, 25 cm, and 30 cm of each monitoring point are selected, and the daily average value within a 30-day time window is extracted as the vertical profile acidity sample data. The sample data is organized into a three-dimensional point set, including horizontal coordinates (X, Y), depth coordinates (Z), and the corresponding acidity intensity value (pH change intensity value). The ordinary Kriging interpolation method is used for three-dimensional spatial interpolation. The variogram model is set as the spherical model, the sill parameter is set to 10 m, the range is set to 5 m, the nugget effect is set to 0.01, the number of neighboring points is taken as 12, and the spatial search radius is set to 8 m. The interpolation process is executed within a unified grid. The grid resolution is 0.5 m in the horizontal plane direction and 2 cm in the vertical direction to ensure that the details of acidity changes are accurately reflected in the vertical profile. The interpolated vertical section acidity interpolation data is saved in the standard three-dimensional grid format, and each grid cell corresponds to a specific spatial position (X, Y, Z) and its acidity change intensity value. To verify the interpolation quality, a ten-fold cross-validation method is used for error evaluation, and the root mean square error (RMSE) is calculated, requiring the RMSE to be less than 0.3 intensity units. After interpolation, through the fixed cross-section extraction method, the acidity vertical profile data is extracted at each specified position (for example, taking a profile every 2 m in the X direction) to form a continuously visualized soil vertical section acidity change distribution layer.

[0108] Fitting the inverse decline relationship of the microbial community based on the acidity interpolation data of the vertical section. First, on each vertical section, stratify by depth (one level every 2 cm) and extract the acidity interpolation values of the corresponding layers. Then, classify according to the magnitude of the acidity values. Set the pH change intensity less than 0.2 as the low acidity fluctuation layer, 0.2 - 0.5 as the medium acidity fluctuation layer, and greater than 0.5 as the high acidity fluctuation layer. Set the initial relative abundance standard values of the microbial community for each acidity fluctuation layer (refer to the original soil microbial community data). Set the low acidity fluctuation layer as 100%, the medium acidity fluctuation layer as 80%, and the high acidity fluctuation layer as 50%. Then, pair the relative abundance values of the microbial community within each section with the corresponding acidity interpolation intensity to form a two-dimensional dataset of microbial abundance - acidity intensity. Use the power-law function for inverse relationship fitting. Set the fitting model as the relative abundance of the microbial community equal to a constant multiplied by the negative first power of the acidity change intensity. Use the least squares method to fit the parameters, and remove the outlier points with residuals greater than 20% during the fitting process. Fit each section separately to obtain the inverse decline fitting curve of the microbial community of each section and its goodness-of-fit index (require R² to be greater than 0.85), and finally form a dataset of the inverse decline relationship of the microbial community. Each section stores the fitting parameters, curve morphological characteristics, and fitting error information. After fitting, analyze the spatial response gradient characteristics of the microbial community to acidity changes by longitudinally comparing the differences in fitting parameters of different sections. Simulate and infer the difference in the decay rate of the relative abundance of the microbial community for the inverse decline relationship data. First, extract the decline rates of the relative abundance of the microbial community in different acidity intensity intervals from the inverse decline fitting curves of each section. The rate is defined as the percentage decrease in the microbial abundance under the increase of the unit acidity change intensity. Divide the acidity change intensity into five intervals: 0 - 0.2, 0.2 - 0.4, 0.4 - 0.6, 0.6 - 0.8, above 0.8. Use the derivative approximation method to estimate the local decay rate within each interval, that is, obtain the local rate value by calculating the tangent slope of the curve at the midpoint of the interval. Subsequently, normalize the local decay rates of different intervals so that the rate values between different sections are comparable. Then, calculate the standard deviation of the decay rates of the relative abundance of the microbial community in the same interval between each section. The standard deviation is the difference in the decay rates of the relative abundance of the microbial community between different sections within this interval. To ensure the inference accuracy, set the exclusion criterion during the inference process: If the number of sections in a certain interval is less than 5, the data in this interval is discarded. Finally, form a complete dataset of the difference in the decay rate of the relative abundance of the microbial community, including the rate difference, sample quantity, and the change trend of the rate difference in each acidity change intensity interval. To further analyze the depth effect of the microbial response difference, weight-average the rate differences of each section according to the section depth to obtain the curve of the microbial response difference varying with depth, providing a quantitative basis for the subsequent analysis of the ecological stability of soil layers.

[0109] The weakening fitting of the catalytic efficiency of enzyme configuration evolution is performed based on the inverse decay relationship data of the bacterial community and the relative abundance decay rate difference of the bacterial community. The specific implementation process is to first extract the bacterial abundance decline coefficient corresponding to each acidity change interval from the inverse decay relationship data of the bacterial community, and at the same time, combine the relative abundance decay rate difference data of the bacterial community to construct the bacterial community dynamic decay function. Subsequently, under laboratory conditions, the exogenous enzymes (such as cellulase, peroxidase and polyphenol oxidase) of the microbial community were extracted from strawberry soil samples, and their catalytic activities under different pH conditions were measured. The catalytic activity was determined by enzyme kinetics, and the substrate conversion rate was recorded in micromoles per minute. The experimentally obtained enzyme catalytic activity was paired with the bacterial community decay function, and the exponential decay model was used to fit the change law of enzyme activity with bacterial community decay. The enzyme catalytic efficiency weakening rate was defined as the percentage of enzyme activity decrease caused by the decrease in unit bacterial community abundance. The nonlinear least squares method was used to optimize the model parameters during the fitting process, and the fitting residual was required to be less than 5%. On this basis, the fitting model was used to deduce the corresponding attenuation amplitude of the enzyme catalytic efficiency when the bacterial community abundance decreased by 10%. The weakening rate of catalytic efficiency of each enzyme is summarized, and weighted according to the importance of the enzyme (for example, cellulase weight 0.4, peroxidase weight 0.3, polyphenol oxidase weight 0.3), and the weakening index of catalytic efficiency of overall enzyme configuration evolution is calculated. Finally, the weakening data of catalytic efficiency of enzyme configuration evolution is formed, and the data format includes the weakening curve of catalytic efficiency of each enzyme, the overall weakening index and the rate of decrease of catalytic efficiency in each acidity interval. The decomposition decay of organic matter in vertical infiltration of soil layer is quantified according to the weakening data of catalytic efficiency of enzyme configuration evolution, the decay rate difference of relative abundance of bacterial community and the inverse decay relationship data of bacterial community. The specific implementation is that, first, at each depth level of the vertical profile, the baseline value of bacterial community abundance is determined in combination with the inverse decay relationship data of bacterial community, and the decay rate of bacterial community in the layer within a certain time window is deduced using the decay rate difference of relative abundance of bacterial community. Subsequently, the decay rate is used as input and substituted into the weakening model of catalytic efficiency of enzyme configuration evolution obtained in step S234 to deduce the decline curve of enzyme catalytic efficiency of the layer. Based on the decrease in enzyme catalytic efficiency, the empirical organic matter decomposition rate constant (the baseline value is 2% / day, which is halved when the catalytic efficiency decreases by 50%) is used to adjust the organic matter decomposition rate of each layer. During the calculation process, the decomposition rate of each layer is weighted and summed according to the layer thickness to obtain the vertical penetration organic matter decomposition decay of the entire profile. In order to capture the temporal changes, the iterative simulation is performed with a daily step length, and the simulation is continued for 30 days, and the decomposition decay of each day is recorded. Finally, the decay of each profile is standardized, and the vertical penetration organic matter decomposition decay data is output, which includes the decay rate of each depth layer, the total decay amount and its change trend over time.

[0110] Step S25 includes the following steps:

[0111] Step S251: Perform multi-level frequency domain decomposition processing on the self-similar data of organic matter vertical decomposition decay to obtain multi-layer spectrum decomposition decay intensity data;

[0112] Step S252: Analyze the soil nitrification inhibition index based on the multi-layer spectrum decomposition decay intensity data to obtain the soil nitrification inhibition index;

[0113] Step S253: Calculate the nitrogen release decline index according to the multi-layer spectrum decomposition decay intensity data and the soil nitrification inhibition index to obtain the nitrogen release decline index;

[0114] Step S254: Fit the nitrogen conversion order of magnitude loss according to the nitrogen release decline index to obtain the nitrogen conversion order of magnitude loss data.

[0115] In the embodiments of the present invention, multi-level frequency domain decomposition processing is performed on the self-similar data of the vertical decomposition and decay of organic matter to obtain multi-layer spectral decomposition decay intensity data. First, the input self-similar data of the vertical decomposition and decay of organic matter is preprocessed, including data normalization processing to unify the dimension of each data point to a dimensionless ratio value, and the normalization interval is set from 0 to 1. Subsequently, the wavelet transform method is applied to perform multi-scale decomposition on the normalized data. The wavelet basis function selects the Daubechies wavelet db4, and the number of wavelet decomposition layers is set to 5 layers. The decomposition process is strictly carried out from top to bottom according to the time scale, and the frequency feature information at different scales is extracted for each layer. At each decomposition layer, the wavelet detail coefficients are extracted, and the energy density formula is used to analyze the energy intensity of the detail coefficients. The energy density calculation method is the sum of the squares of each coefficient divided by the number of coefficients. The energy density values obtained for each decomposition layer are the spectral decomposition decay intensity data corresponding to the corresponding levels. This processing process strictly retains the local extreme value change characteristics at each scale to ensure the integrity and independence of the frequency domain information at different scales. The finally output data structure is a set of five groups of spectral decomposition decay intensity sets, each group corresponding to a decomposition scale, and the unit is the dimensionless energy density value. Based on the multi-layer spectral decomposition decay intensity data, the soil nitrification inhibition index is analyzed. First, for each layer of spectral decomposition decay intensity data, the maximum value, mean value, and standard deviation of the energy density value are extracted to construct a frequency domain feature vector. Subsequently, according to the spectral intensity distribution characteristics, the spectral layer characterized by an abnormal increase in the energy density in the low-frequency range is screened out. The judgment criterion is that the mean value of the energy density in the low-frequency region is more than 1.5 times higher than the mean value of the energy density in the medium and high-frequency regions. The extracted low-frequency energy density values are converted to the 0 to 1 interval using the logarithmic normalization method. Subsequently, the soil nitrification inhibition index is defined as 1 minus the normalized low-frequency energy density value. The higher the value of this index, the greater the degree of inhibition of soil nitrification. During the analysis process, a data rejection rule is set to reject the data points where the abnormal fluctuation of the low-frequency energy density exceeds the mean value ±2 times the standard deviation to ensure the stability and representativeness of the analysis results. The finally obtained soil nitrification inhibition index is output in the form of a dimensionless numerical value from 0 to 1, and each profile position corresponds to a soil nitrification inhibition index value. According to the multi-layer spectral decomposition decay intensity data and the soil nitrification inhibition index, the nitrogen release decline index is calculated. First, a joint feature matrix is constructed by combining the energy density mean value in the spectral decomposition decay intensity data of each profile with the soil nitrification inhibition index. Principal component analysis is performed on this feature matrix to extract the first principal component as the soil comprehensive activity index. Subsequently, the nitrogen release decline index is defined as the weighted product of the soil comprehensive activity index and the soil nitrification inhibition index, and the weighted coefficients are 0.6 and 0.4 respectively. After the weighted product, it is normalized to the 0 to 1 interval. During the calculation process, it is required that the spectral data and the data of the nitrification inhibition index are aligned, that is, the two data sources at the same profile depth are strictly corresponding, and the profiles with asynchronous data will be excluded.The larger the value of the nitrogen release decline index, the more severe the decline in the bioavailability of nitrogen in the soil of that profile. Finally, a data table of the nitrogen release decline index corresponding to each profile depth position is calculated and output. The nitrogen conversion order-of-magnitude loss is fitted based on the nitrogen release decline index. First, for the nitrogen release decline index, the index range is divided into ten grade intervals with a step of 0.1. The historical measured nitrogen conversion rate data corresponding to each index interval is collected, with the rate unit being milligrams per kilogram per hour, and a correspondence table between the nitrogen conversion rate and the nitrogen release decline index is established. Subsequently, with the nitrogen release decline index as the independent variable and the logarithm value of the nitrogen conversion rate as the dependent variable, linear regression is used for fitting. During the regression analysis, it is required that the coefficient of determination R² is greater than 0.85, otherwise the index interval division parameters are readjusted until the requirements are met. The regression equation is used to calculate the order-of-magnitude loss of the nitrogen conversion rate corresponding to any value of the nitrogen release decline index. The order of magnitude is defined as the logarithmic difference between the calculated rate and the standard rate (the average nitrogen conversion rate measured under non-inhibited conditions). The finally obtained nitrogen conversion order-of-magnitude loss data includes the nitrogen release decline index, the calculated rate value, and the corresponding order-of-magnitude loss value corresponding to each depth position of the profile, which are organized and saved in tabular form for subsequent use in the simulation and evolution steps of strawberry root growth retardation.

[0116] Step S253 includes the following steps:

[0117] Draw a multi-layer decay intensity fluctuation curve for the multi-layer spectrum decomposition decay intensity data to obtain a multi-layer decay intensity fluctuation curve;

[0118] Perform multi-layer single-point weakening mutation entropy value analysis on the multi-layer decay intensity fluctuation curve to obtain multi-layer single-point weakening mutation entropy values;

[0119] Deduce the non-linear mineralization rate decay interval based on the multi-layer single-point weakening mutation entropy value to obtain the non-linear mineralization rate decay interval;

[0120] Evaluate the reduction in nitrifying microorganism activity for the soil nitrification inhibition index to obtain data on the reduction in nitrifying microorganism activity;

[0121] Calculate the nitrogen release decline index based on the non-linear mineralization rate decay interval and the data on the reduction in nitrifying microorganism activity to obtain the nitrogen release decline index.

[0122] In the embodiments of the present invention, multi-layer decay intensity fluctuation curves are plotted for multi-layer spectral decomposition decay intensity data to obtain multi-layer decay intensity fluctuation curves. The specific implementation is as follows: First, the input multi-layer spectral decomposition decay intensity data is sorted and classified according to the decomposition scale. Each layer of spectral data is separately grouped into a set, and the data within each set is sorted in depth order to ensure that the data at each depth point corresponds one by one. Subsequently, with the depth as the abscissa and the spectral energy density value as the ordinate, the fluctuation curve is plotted by connecting points one by one, and no curve smoothing process is performed during the plotting process to retain the original fluctuation characteristics. To enhance the curve detail resolution, the abscissa step size is fixedly set to 1 cm, and the ordinate uses logarithmic scaling to enhance the visualization recognition effect of the small change segment. A separate fluctuation curve is generated for each scale decomposition layer, and each curve maintains an independent number, and the numbers are arranged in ascending order according to the scale size, that is, the smaller the scale, the smaller the number. The finally output multi-layer decay intensity fluctuation curve data is saved in the form of a standard two-dimensional coordinate data point set, and each group of curves contains the continuous data point coordinate values of all depth layers. Multi-layer single-point decay mutation entropy value analysis is performed on the multi-layer decay intensity fluctuation curve to obtain multi-layer single-point decay mutation entropy values. The specific implementation is as follows: First, for each decay intensity fluctuation curve, the energy density change amount between adjacent depth points is calculated according to the single-point difference method. The single-point difference is defined as the energy density of the latter depth point minus the energy density of the former depth point. Subsequently, the absolute values of all single-point differences are taken to construct a single-point change absolute value sequence. Local normalization processing is performed on this sequence, and every five consecutive depth points are used as a group and normalized to the interval from 0 to 1. Then, based on each group of normalized sequences, the local entropy value is calculated. The entropy value is defined as the negative sum of the product of the logarithm of the probability corresponding to the occurrence frequency of the normalized difference. The specific operation is to count the number of data points in each normalized difference interval, calculate the proportion of the data points in this interval, take the logarithm of each proportion, multiply it by the proportion itself, and then sum and take the negative to obtain the local entropy value. A high local entropy value indicates a sharp single-point difference, and a low local entropy value indicates a stable change. Each local entropy value is mapped to the overall depth profile according to its central depth, and finally a multi-layer single-point decay mutation entropy value data set is obtained. Each scale decomposition layer corresponds to a set of entropy profile data. Based on the multi-layer single-point decay mutation entropy value, the non-linear mineralization rate decay interval is deduced to obtain the non-linear mineralization rate decay interval. The specific implementation is as follows: First, the mutation regions are screened in each layer of entropy profile data. The screening criterion is the depth points where the local entropy value is greater than the mean value of the full profile entropy value plus 2 times the standard deviation. The screened depth points are regarded as potential non-linear decay trigger points. Subsequently, with each mutation trigger point as the center, it is extended 5 cm upward and downward respectively, which is defined as the decay sensitive area. Inside each decay sensitive area, the initial value and the end value of the spectral decomposition decay intensity corresponding to the depth are extracted, and the spectral energy density decline rate is calculated. The sensitive area with a decline rate exceeding 30% is defined as the effective non-linear mineralization rate decay interval. For the sensitive areas where multiple consecutive mutation trigger points overlap, the union operation is performed to merge them into a larger decay interval.Finally output the non-linear mineralization rate decay interval data, including the starting depth, ending depth and the corresponding decline rate values. All intervals are recorded in ascending order of depth, and the data at each scale level are saved independently.

[0123] In the specific implementation process of evaluating the reduction of nitrifying microorganism activity to obtain nitrifying microorganism activity reduction data for the soil nitrification inhibition index, first, the soil nitrification inhibition index is extracted, which is calculated as the ratio of the actual measured value of the soil ammonia oxidation rate to the measured value of the ammonia oxidation rate in the control non-inhibited group. The specific operation is as follows: Set the ammonia oxidation rate measurement period to 48 hours, record the changes in ammonia nitrogen and nitrate nitrogen concentrations every 6 hours, and calculate the ammonia oxidation amount per unit time as the ammonia oxidation rate. The actual soil sample and the control sample without inhibitor are cultured under the same conditions, and a complete rate data curve is measured. Calculate the average value of the ammonia oxidation rate for each time period, and then take the ratio of the actual soil ammonia oxidation rate to the control group ammonia oxidation rate, which is defined as the soil nitrification inhibition index. Subsequently, according to the quantitative description standard of the activity of nitrifying microorganism groups in soil microbiology, set the activity reduction classification threshold. Samples with an inhibition index less than 0.7 are labeled as having activity reduction, samples with an inhibition index between 0.7 and 0.9 are labeled as having slightly reduced activity, and samples with an inhibition index greater than 0.9 are labeled as having normal activity. Evaluate and classify each sampling point separately, and organize the results into nitrifying microorganism activity reduction data, including sampling location, measurement time, inhibition index value, and activity status classification. In the specific implementation process of calculating the nitrogen release decline index based on the non-linear mineralization rate decay interval and nitrifying microorganism activity reduction data to obtain the nitrogen release decline index, first, extract the corresponding depth range according to the non-linear mineralization rate decay interval data determined in the previous steps. Within each decay interval, count the classification of nitrifying microorganism activity reduction at the corresponding depth. For each decay interval, calculate the ratio of the number of samples with activity reduction to the total number of samples, which is defined as the activity reduction ratio of this decay interval. Subsequently, perform a weighted comprehensive calculation on the spectral energy decline rate and the activity reduction ratio of each decay interval. The calculation process is as follows: Multiply the spectral decline rate and the activity reduction ratio by the set weight factors respectively, where the weight of the spectral decline rate is set to 0.6 and the weight of the activity reduction ratio is set to 0.4, and add the two weighted values to obtain the original value of the nitrogen release decline index. Then, normalize the original values of the nitrogen release decline index for all decay intervals so that the final nitrogen release decline index is in the range of 0 to 1, where the smaller the value, the more severe the nitrogen release attenuation. The finally output nitrogen release decline index data includes the start and end depths of the decay interval, spectral decline rate, activity reduction ratio, and the normalized nitrogen release decline index. All data are arranged in a table and saved in ascending order of depth with numbers. Throughout the calculation process, quantitative calculation methods are used, no empirical parameters are introduced, and no manual adjustment is made to ensure the complete traceability and consistency of the data processing process.

[0124] Step S3 includes the following steps:

[0125] Step S31: Analyze the over-alkali fluctuation index of the soil layer acidity and alkalinity fluctuation data of strawberries to obtain the over-alkali fluctuation index of the soil layer;

[0126] Step S32: Based on the over-alkali fluctuation index of the soil layer, conduct a simulation evaluation of the reduction in the absorption of soil trace elements in the strawberry root system extension state to obtain the data on the reduction in the absorption of trace elements in the over-alkali soil layer;

[0127] Step S33: Perform a calculation of the weakening interval of the soil water-holding capacity according to the over-alkali fluctuation index of the soil layer to obtain the weakening interval of the soil water-holding capacity;

[0128] Step S34: Conduct a regression analysis on the nutrient uptake efficiency restriction of the strawberry root system extension state according to the data on the reduction in the absorption of trace elements in the over-alkali soil layer and the weakening interval of the soil water-holding capacity to obtain the regression data on the nutrient uptake efficiency restriction.

[0129] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0130] Step S31: Analyze the over-alkali fluctuation index of the soil layer acidity and alkalinity fluctuation data of strawberries to obtain the over-alkali fluctuation index of the soil layer;

[0131] In the embodiment of the present invention, in the specific implementation process of analyzing the over-alkali fluctuation index of the soil layer acidity and alkalinity fluctuation data of strawberries to obtain the over-alkali fluctuation index of the soil layer, first, soil samples are collected at intervals of 2 cm in depth within the range of 0 cm to 30 cm in depth in the strawberry planting area. The pH values of each sample are measured using the glass electrode method, and the pH values corresponding to each sampling depth are recorded. Subsequently, a soil layer acidity and alkalinity fluctuation curve is plotted with the continuous sampling depth as the horizontal axis and the pH value as the vertical axis. The local maximum value recognition method is used to screen out the peaks above pH 8.0, and the fluctuation amplitude is calculated for each peak interval, that is, the mean value of the lowest pH values before and after the peak pH value is subtracted from the peak pH value. The average of all peak fluctuation amplitudes is defined as the over-alkali fluctuation index. If the number of detected peaks is less than 3, the average value of the fluctuation amplitude of all regions above pH 8.0 is used as supplementary data to ensure the stability of the statistical sample size.

[0132] Step S32: Based on the over-alkali fluctuation index of the soil layer, conduct a simulation evaluation of the reduction in the absorption of soil trace elements in the strawberry root system extension state to obtain the data on the reduction in the absorption of trace elements in the over-alkali soil layer;

[0133] In the embodiment of the present invention, in the specific implementation process of simulating and evaluating the reduction of trace element absorption in the soil layer for the strawberry root system extension state based on the over-alkaline fluctuation index of the soil layer to obtain the over-alkaline soil layer trace element absorption reduction data, first, according to the obtained over-alkaline fluctuation index of the soil layer, the available trace element content data of each soil layer within the corresponding depth range are extracted. The available trace elements include iron, manganese, zinc, and copper. After extraction by the DTPA extraction method, they are measured by atomic absorption spectrometry. For each element, a standard content reference value is set, such as 4.5 mg / kg for iron, 5.0 mg / kg for manganese, 1.2 mg / kg for zinc, and 0.8 mg / kg for copper. If the detected value is lower than 80% of the corresponding standard content value, it is determined as absorption reduction, and the specific depth and element type are recorded. Then, a linear fit is performed based on the over-alkaline fluctuation index size and the absorption reduction ratio. According to the relationship that for every 0.1 increase in the over-alkaline fluctuation index, the absorption reduction ratio increases by 5%, the complete over-alkaline soil layer trace element absorption reduction data are deduced.

[0134] Step S33: Calculate the weakening interval of the soil layer water holding capacity according to the over-alkaline fluctuation index of the soil layer to obtain the weakening interval of the soil layer water holding capacity;

[0135] In the embodiment of the present invention, in the specific implementation process of calculating the weakening interval of the soil layer water holding capacity according to the over-alkaline fluctuation index of the soil layer to obtain the weakening interval of the soil layer water holding capacity, first, the soil layer section with a pH greater than 8.0 is extracted, and the change in soil moisture content of the corresponding section is detected. The moisture content data are measured by the gravimetric method, and the mass change is recorded every 4 hours, with a monitoring period of 48 hours. The rate of decrease in moisture content is calculated by linear regression fitting, and the percentage of decrease in moisture content per hour is calculated. If the rate of decrease in moisture content in a certain interval is greater than 0.5% per hour, it is marked as a weakening interval of the water holding capacity. The section with more than two consecutive layers and a rate of decrease that meets the conditions is recorded as a complete weakening interval, and the starting and ending depths and the average rate of decrease are recorded. Finally, the weakening interval data of the soil layer water holding capacity are output.

[0136] Step S34: Perform a regression analysis on the nutrient uptake efficiency restriction of the strawberry root system extension state according to the over-alkaline soil layer trace element absorption reduction data and the weakening interval of the soil layer water holding capacity to obtain the regression data of the nutrient uptake efficiency restriction.

[0137] In the embodiments of the present invention, in the specific implementation process of performing a regression analysis on the nutrient uptake efficiency restriction of the strawberry root system extension state based on the trace element absorption reduction data in the over-alkaline soil layer and the water-holding capacity weakening interval of the soil layer to obtain the regression data of the nutrient uptake efficiency restriction, first, the absorption reduction ratio of each element in the trace element absorption reduction data in the over-alkaline soil layer is standardized to be between 0 and 1. At the same time, the average decline rate of each water-holding capacity weakening interval is also standardized. Subsequently, the absorption reduction ratio is set as the independent variable, the water-holding capacity decline rate is set as the auxiliary independent variable, and the actually measured nutrient absorption amount of the strawberry root system is set as the dependent variable for multiple linear regression analysis. In the analysis process, the least squares method is used to fit the influence weights of each independent variable on the dependent variable. Taking a single sample unit (each 10 cm depth segment) as the regression analysis basic unit, the data volume of each unit is not less than 30 groups to ensure the regression stability. Finally, the regression data of the nutrient uptake efficiency restriction is output, including the regression coefficients of each independent variable, the coefficient of determination R-squared value, and the statistical data of the fitting residual distribution. No non-mathematical inference means are introduced during the entire analysis process, and all regression processing is performed using the actually measured data.

[0138] Step S32 includes the following steps:

[0139] Step S321: Perform equidistant discrete difference processing on the over-alkaline fluctuation index of the soil layer to obtain the over-alkaline disturbance amplitude change sequence;

[0140] Step S322: Based on the over-alkaline disturbance amplitude change sequence, perform disordered differential processing on the available content decline of soil trace elements to obtain the disordered data of the available content decline of trace elements;

[0141] Step S323: Analyze the continuity rate of the inflection point decline of the disordered data of the available content decline to obtain the continuity rate of the inflection point of the content decline;

[0142] Step S324: Based on the disordered data of the available content decline and the continuity rate of the inflection point of the content decline, perform a simulation evaluation on the trace element absorption reduction in the over-alkaline soil layer for the strawberry root system extension state to obtain the trace element absorption reduction data in the over-alkaline soil layer.

[0143] In the embodiments of the present invention, in the specific implementation process of performing equally spaced discrete difference processing on the soil over-alkalinity fluctuation index to obtain the over-alkaline disturbance amplitude change sequence, first, the over-alkalinity fluctuation index data corresponding to each depth point at intervals of 2 cm within the depth range of 0 cm to 30 cm in the strawberry planting area are selected to form a preliminary over-alkalinity fluctuation index sequence. Then, in the order of the depth sequence, first-order difference operation is performed in units of 2 cm, that is, the over-alkalinity fluctuation index of the current point is subtracted from the over-alkalinity fluctuation index of the previous depth point to obtain the disturbance amplitude change amount between consecutive depths. The disturbance amplitude change amounts of all depth points are arranged in sequence to form a complete over-alkaline disturbance amplitude change sequence. For example, if the over-alkalinity fluctuation indices at the depth points of 0 cm, 2 cm, and 4 cm are 0.3, 0.5, and 0.4 respectively, the change amount at 2 cm is 0.2, and the change amount at 4 cm is -0.1. In the specific implementation process of performing disordered differential processing on the available state content decline of soil trace elements based on the over-alkaline disturbance amplitude change sequence to obtain the disordered data of the available state content decline of trace elements, first, the available state content data of four soil trace elements, namely iron, manganese, zinc, and copper, corresponding to each of the above depth points are extracted, and this data is obtained by the DTPA extraction method and using atomic absorption spectrometry. Subsequently, corresponding to the available state content of trace elements in the order of the over-alkaline disturbance amplitude change sequence, the change rate of each element content between every two consecutive depth points is calculated, that is, the element content of the latter depth point is subtracted from the element content of the previous depth point, and then divided by the depth interval of 2 cm. To reflect the disorder, a disturbance adjustment is introduced to the above change rate sequence, that is, the absolute value of the difference between adjacent two change rates is superimposed on each change rate, thereby forming the disordered data of the available state content decline. For example, if the iron content at 4 cm is 3.8 mg / kg and at 2 cm is 4.0 mg / kg, the preliminary change rate is -0.1, and if the difference between the change rate from 2 cm to 4 cm and the change rate from 4 cm to 6 cm is 0.05, the disordered change value is adjusted to -0.15. In the specific implementation process of performing inflection point decline continuity rate analysis on the disordered data of the available state content decline to obtain the content decline inflection point continuity rate, first, a local minimum detection algorithm is used to identify the inflection point positions of the decline trend in the disordered data sequence of the available state content decline, that is, the local minimum points that are in a declining trend relative to both sides. For the disordered change data between each pair of adjacent inflection points, the change rate continuity is calculated, that is, the proportion of the change rates with the same sign within this interval is statistically counted, and this proportion is multiplied by the average decline rate of the interval to obtain the content decline inflection point continuity rate. For example, if 4 out of 5 data points in a certain interval have a negative change rate and the average change rate is -0.12, then the inflection point continuity rate is 0.8 multiplied by -0.12, resulting in -0.096. This processing method can accurately reflect the stability and intensity of the decline trend of trace element content.In the specific implementation process of simulating and evaluating the reduction of trace element absorption in the soil layer of strawberry root system extension state based on the disordered data of available state content decline and the continuity rate of the inflection point of content decline to obtain the data of trace element absorption reduction in the over-alkaline soil layer, first, combine the disordered data of available state content decline at each depth point with the corresponding inflection point continuity rate data, and set the standardized evaluation rule, that is, the depth section with a disordered decline value higher than 0.1 and the absolute value of the inflection point continuity rate greater than 0.08 is determined as the trace element absorption reduction area. Subsequently, cumulative statistics are carried out on each trace element determined to be a reduction area, and the cumulative decline ratios of four elements, iron, manganese, zinc, and copper, in each depth section are calculated respectively. The calculation method is the percentage of the content decline amount in each depth section to the standard content, and the reduction ratios of all depth sections are weighted and averaged to form the data of trace element absorption reduction in the over-alkaline soil layer.

[0144] Step S33 includes the following steps:

[0145] Step S331: Perform soil discrete deformation simulation according to the over-alkaline fluctuation index of the soil layer to obtain soil discrete deformation data;

[0146] Step S332: Perform soil pore structure expansion mapping based on the soil discrete deformation data to obtain soil pore structure expansion mapping data;

[0147] Step S333: Quantify the anisotropic attenuation of soil capillary force according to the soil pore structure expansion mapping data to obtain capillary force anisotropic attenuation data;

[0148] Step S334: Perform soil water holding capacity weakening interval calculation according to the capillary force anisotropic attenuation data to obtain the soil water holding capacity weakening interval.

[0149] In this massage embodiment, in the specific implementation process of simulating the discrete deformation of soil in the soil layer according to the over-alkalinity fluctuation index of the soil layer to obtain soil discrete deformation data, first, based on the over-alkalinity fluctuation index sequence measured at 2-cm intervals within the depth range of 0 cm to 30 cm in the strawberry planting soil layer, the discrete cell division method is used to divide the soil layer space into regular small units of 2 cm × 2 cm. For each small unit, its initial deformation coefficient is set according to the over-alkalinity fluctuation index value at the corresponding depth. The deformation coefficient has a positive correlation with the over-alkalinity fluctuation index. It is set that when the over-alkalinity fluctuation index is 0, the deformation coefficient is 0, and when the over-alkalinity fluctuation index reaches 1, the deformation coefficient is the maximum value of 0.3. Subsequently, the difference in deformation coefficients between adjacent units is calculated by the first-order difference method. The unit pairs with a difference value exceeding 0.05 are defined as generating discrete deformation, and the discrete intensity level is marked. The discrete intensity level is divided into slight (0.05 - 0.10), moderate (0.10 - 0.20), and severe (0.20 - 0.30). A complete soil discrete deformation data matrix is formed. In the specific implementation process of performing soil pore structure expansion mapping based on the soil discrete deformation data to obtain soil pore structure expansion mapping data, first, the points marked as discrete units in the soil discrete deformation data are screened. For each discrete unit, the corresponding pore expansion increment is assigned according to the discrete intensity level. Slight discrete corresponds to a 2% increase in porosity, moderate discrete corresponds to a 5% increase in porosity, and severe discrete corresponds to an 8% increase in porosity. Then, with each unit as the center, the two-dimensional convolution diffusion algorithm is applied to diffuse the expansion effect to the surrounding units according to a 3×3 neighborhood. The diffusion weight decreases according to the distance from the center. The weight of the central unit is 1, and the surrounding units are assigned a weight of 0.5 when the Manhattan distance is 1 and a weight of 0.25 when the Manhattan distance is 2. The final porosity change amount of each unit is obtained through cumulative superposition calculation, forming the soil pore structure expansion mapping data. Taking a specific experiment as an example, if the original porosity is 45%, after expansion and diffusion superposition of the slight discrete unit, the porosity can be increased to approximately 47%. In the specific implementation process of quantifying the anisotropic attenuation of soil capillary force based on the soil pore structure expansion mapping data to obtain capillary force anisotropic attenuation data, first, according to the soil porosity change amount, the porosity change gradients are extracted separately in the horizontal and vertical directions. The two-dimensional difference operator is used to calculate the gradient of the porosity expansion mapping data in the horizontal and vertical directions respectively, and the gradient value is the anisotropic expansion rate. Subsequently, according to the principle of the inverse relationship between capillary force and porosity, the anisotropic expansion rate is multiplied by the attenuation coefficient constant of 0.6 to obtain the capillary force anisotropic attenuation amount. Taking specific data as an example, if the horizontal expansion rate is 0.04 and the vertical expansion rate is 0.02, then the horizontal capillary force attenuation amount is 0.024 and the vertical capillary force attenuation amount is 0.012. The anisotropic capillary force attenuation amount data of all units constitute the soil capillary force anisotropic attenuation data matrix.In the specific implementation process of calculating the weakening interval of the water holding capacity of the soil layer based on the capillary force anisotropy decay data to obtain the weakening interval of the water holding capacity of the soil layer, first, the capillary force anisotropy decay data is stratified and statistically analyzed according to the depth, with each layer being 2 cm thick, and the average decay amounts in the horizontal and vertical directions of each layer are calculated respectively. Then, the criteria for judging the weakening of the water holding capacity are set, and the layer with an average decay amount of the capillary force in the horizontal or vertical direction exceeding 0.015 is defined as the weakening area of the water holding capacity. Further, the adjacent layers continuously judged to be the weakening areas of the water holding capacity are merged to form a complete weakening interval of the water holding capacity. Taking a specific experiment as an example, in the strawberry soil, the average decay amounts of the capillary force in the depth range of 6 cm to 12 cm are 0.018, 0.021, 0.019, and 0.016 respectively. After judgment, the layer segment from 6 cm to 12 cm is classified as a weakening interval of the water holding capacity. The finally output data of the weakening interval of the water holding capacity of the soil layer completely records the starting and ending depths and the decay amplitude information of each interval.

[0150] The present invention also provides an agricultural product planting environment detection system for implementing the agricultural product planting environment detection method as described above. The agricultural product planting environment detection system includes:

[0151] A pH fluctuation analysis module for monitoring the soil layer state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil layer state monitoring data; and performing pH fluctuation analysis on the strawberry soil layer state monitoring data to obtain strawberry soil layer pH fluctuation data;

[0152] A developmental retardation simulation evolution module for obtaining strawberry plant morphological data; evaluating the root extension state of the strawberry plant based on the strawberry plant morphological data to obtain the strawberry root extension state; quantifying the decomposition decay of vertically permeating organic matter based on the strawberry soil layer pH fluctuation data to obtain vertically permeating organic matter decomposition decay data; and performing an over-acid developmental retardation simulation evolution on the strawberry root extension state based on the vertically permeating organic matter decomposition decay data to obtain strawberry root over-acid developmental retardation evolution data;

[0153] A nutrient uptake efficiency restriction analysis module for performing an over-alkaline fluctuation index analysis on the strawberry soil layer pH fluctuation data to obtain the soil layer over-alkaline fluctuation index; performing a simulation evaluation of the reduction of trace element absorption in the soil layer on the strawberry root extension state based on the soil layer over-alkaline fluctuation index to obtain over-alkaline soil layer trace element absorption reduction data; and performing a nutrient uptake efficiency restriction regression analysis on the strawberry root extension state based on the over-alkaline soil layer trace element absorption reduction data to obtain nutrient uptake efficiency restriction regression data;

[0154] The planting environment detection model construction module is used to construct an automated planting environment detection model based on the data of the stunted evolution of strawberry roots due to excessive acidity and the regression data of the restriction of nutrient uptake efficiency, and obtain the automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform the detection of the planting environment of agricultural products.

[0155] 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 will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for detecting the planting environment of agricultural products, characterized in that, It includes the following steps: Step S1: Monitor the soil layer status of the strawberry planting area through soil monitoring sensors to obtain strawberry soil layer status monitoring data; Conduct an analysis of the pH fluctuation of the strawberry soil layer status monitoring data to obtain strawberry soil layer pH fluctuation data; Step S2: Obtain strawberry plant morphology data; evaluate the root extension status of the strawberry plant morphology data to obtain the strawberry root extension status; quantify the decomposition decay of vertically permeating organic matter based on the strawberry soil layer pH fluctuation data to obtain vertically permeating organic matter decomposition decay data; Based on the vertically permeating organic matter decomposition decay data, conduct a simulation evolution of the over-acid growth retardation of the strawberry root extension status to obtain strawberry root over-acid growth retardation evolution data; Step S3: Conduct an analysis of the over-alkali fluctuation index of the strawberry soil layer pH fluctuation data to obtain the soil layer over-alkali fluctuation index; based on the soil layer over-alkali fluctuation index, conduct a simulation evaluation of the reduction in the absorption of soil trace elements by the strawberry root extension status to obtain over-alkali soil layer trace element absorption reduction data; according to the over-alkali soil layer trace element absorption reduction data, conduct a regression analysis of the nutrient uptake efficiency restriction of the strawberry root extension status to obtain nutrient uptake efficiency restriction regression data; Step S4: Based on the strawberry root over-acid growth retardation evolution data and the nutrient uptake efficiency restriction regression data, construct an automated planting environment detection model to obtain an automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform agricultural product planting environment detection.

2. The agricultural product planting environment detection method according to claim 1, wherein, Step S1 includes the following steps: Step S11: Monitor the soil layer status of the strawberry planting area through soil monitoring sensors to obtain strawberry soil layer status monitoring data; Step S12: Clean the strawberry soil layer status monitoring data to obtain strawberry soil layer status monitoring cleaned data; Step S13: Conduct an analysis of the pH fluctuation of the strawberry soil layer status monitoring cleaned data to obtain strawberry soil layer pH fluctuation data.

3. The agricultural product planting environment detection method according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Obtain strawberry plant morphology data; evaluate the root extension status of the strawberry plant morphology data to obtain the strawberry root extension status; Step S22: Conduct an analysis of the intensity of the temporal change of the soil layer acidity of the strawberry soil layer pH fluctuation data to obtain soil layer acidity temporal change intensity data; Step S23: Quantify the decomposition decay of vertically permeating organic matter based on the soil layer acidity temporal change intensity data to obtain vertically permeating organic matter decomposition decay data; Step S24: Analyze the self-similar structure of the decay rate of the vertically permeating organic matter decomposition decay data to obtain self-similar data of the vertical decomposition decay of organic matter; Step S25: Fit the nitrogen conversion order of magnitude loss based on the self-similar data of the vertical decomposition decay of organic matter to obtain nitrogen conversion order of magnitude loss data; Step S26: Based on the self-similar data of the vertical decomposition decay of organic matter and the nitrogen conversion order of magnitude loss data, conduct a simulation evolution of the over-acid growth retardation of the strawberry root extension status to obtain strawberry root over-acid growth retardation evolution data.

4. The agricultural product planting environment detection method according to claim 3, characterized in that, Step S23 includes the following steps: Step S231: Perform spatial interpolation of the acidity in the vertical section of the soil layer on the time-series change intensity data of the soil layer acidity to obtain the interpolated data of the acidity in the vertical section; Step S232: Fit the inverse decline relationship of the microbial community based on the interpolated data of the acidity in the vertical section to obtain the data of the inverse decline relationship of the microbial community; Step S233: Conduct a simulation inference on the difference in the attenuation rate of the relative abundance of the microbial community for the data of the inverse decline relationship of the microbial community to obtain the difference in the attenuation rate of the relative abundance of the microbial community; Step S234: Perform a fitting of the weakening of the catalytic efficiency of the enzyme configuration evolution based on the data of the inverse decline relationship of the microbial community and the difference in the attenuation rate of the relative abundance of the microbial community to obtain the data of the weakening of the catalytic efficiency of the enzyme configuration evolution; Step S235: Quantify the decomposition decay of the organic matter vertically permeating the soil layer based on the data of the weakening of the catalytic efficiency of the enzyme configuration evolution, the difference in the attenuation rate of the relative abundance of the microbial community, and the data of the inverse decline relationship of the microbial community to obtain the data of the decomposition decay of the vertically permeating organic matter; 5. The method for detecting the planting environment of agricultural products according to claim 3, wherein Step S25 includes the following steps: Step S251: Perform a multi-level frequency domain decomposition on the self-similar data of the vertical decomposition decay of the organic matter to obtain the data of the decay intensity of the multi-level spectrum decomposition; Step S252: Analyze the soil nitrification inhibition index based on the data of the decay intensity of the multi-level spectrum decomposition to obtain the soil nitrification inhibition index; Step S253: Calculate the nitrogen release decline index based on the data of the decay intensity of the multi-level spectrum decomposition and the soil nitrification inhibition index to obtain the nitrogen release decline index; Step S254: Fit the nitrogen conversion order-of-magnitude loss based on the nitrogen release decline index to obtain the data of the nitrogen conversion order-of-magnitude loss; 6. The agricultural product planting environment detection method according to claim 5, wherein, Step S253 includes the following steps: Plot the multi-level decay intensity fluctuation curve for the data of the decay intensity of the multi-level spectrum decomposition to obtain the multi-level decay intensity fluctuation curve; Conduct a multi-level single-point weakening mutation entropy value analysis on the multi-level decay intensity fluctuation curve to obtain the multi-level single-point weakening mutation entropy value; Deduce the attenuation interval of the non-linear mineralization rate of nitrogen based on the multi-level single-point weakening mutation entropy value to obtain the attenuation interval of the non-linear mineralization rate; Evaluate the reduction in the activity of nitrifying microorganisms for the soil nitrification inhibition index to obtain the data of the reduction in the activity of nitrifying microorganisms; Calculate the nitrogen release decline index based on the attenuation interval of the non-linear mineralization rate and the data of the reduction in the activity of nitrifying microorganisms to obtain the nitrogen release decline index; 7. The agricultural product planting environment detection method according to claim 1, characterized in that Step S3 includes the following steps: Step S31: Analyze the over-alkaline fluctuation index for the strawberry soil layer pH fluctuation data to obtain the soil layer over-alkaline fluctuation index; Step S32: Based on the soil layer over-alkaline fluctuation index, perform a simulation evaluation of the reduction in the absorption of trace elements in the soil layer for the strawberry root system extension state to obtain the data of the reduction in the absorption of trace elements in the over-alkaline soil layer; Step S33: Calculate the weakening interval of the water holding capacity of the soil layer based on the soil layer over-alkaline fluctuation index to obtain the weakening interval of the water holding capacity of the soil layer; Step S34: Conduct a regression analysis of the nutrient uptake efficiency constraint on the strawberry root system extension state based on the data of the reduction in the absorption of trace elements in the over-alkaline soil layer and the weakening interval of the water holding capacity of the soil layer to obtain the data of the nutrient uptake efficiency constraint regression; 8. The agricultural product planting environment detection method according to claim 7, characterized in that Step S32 includes the following steps: Step S321: Perform equally spaced discrete difference processing on the soil layer over-alkalinity fluctuation index to obtain the over-alkalinity disturbance amplitude change sequence; Step S322: Perform disordered differential processing on the decrease in the available content of soil trace elements based on the over-alkalinity disturbance amplitude change sequence to obtain disordered data on the decrease in the available content of trace elements; Step S323: Analyze the inflection point decrease continuity rate of the disordered data on the decrease in the available content to obtain the inflection point decrease continuity rate of the content; Step S324: Based on the disordered data on the decrease in the available content and the inflection point decrease continuity rate of the content, perform a simulation evaluation on the strawberry root system extension state for the reduction of trace element absorption in the soil layer to obtain data on the reduction of trace element absorption in the over-alkaline soil layer.

9. The agricultural product planting environment detection method according to claim 7, wherein, Step S33 includes the following steps: Step S331: Perform a simulation of discrete soil deformation in the soil layer according to the soil layer over-alkalinity fluctuation index to obtain soil discrete deformation data; Step S332: Based on the soil discrete deformation data, perform an expansion mapping of the soil pore structure to obtain soil pore structure expansion mapping data; Step S333: Quantify the anisotropic attenuation of soil capillary force according to the soil pore structure expansion mapping data to obtain capillary force anisotropic attenuation data; Step S334: Perform an interval calculation on the weakening of the soil layer water holding capacity according to the capillary force anisotropic attenuation data to obtain the interval of the weakening of the soil layer water holding capacity.

10. An agricultural product planting environment detection system, characterized in that, For implementing the agricultural product planting environment detection method as described in claim 1, the agricultural product planting environment detection system includes: An acidity and alkalinity fluctuation analysis module, configured to monitor the soil layer state in the strawberry planting area through a soil monitoring sensor to obtain strawberry soil layer state monitoring data; perform acidity and alkalinity fluctuation analysis on the strawberry soil layer state monitoring data to obtain strawberry soil layer acidity and alkalinity fluctuation data; A growth retardation simulation evolution module, configured to obtain strawberry plant morphology data; evaluate the root system extension state of the strawberry plant morphology data to obtain the strawberry root system extension state; perform quantification of the decomposition decay of vertically permeating organic matter based on the strawberry soil layer acidity and alkalinity fluctuation data to obtain vertically permeating organic matter decomposition decay data; perform an over-acid growth retardation simulation evolution on the strawberry root system extension state based on the vertically permeating organic matter decomposition decay data to obtain strawberry root system over-acid growth retardation evolution data; A nutrient uptake efficiency restriction analysis module, configured to perform an over-alkalinity fluctuation index analysis on the strawberry soil layer acidity and alkalinity fluctuation data to obtain the soil layer over-alkalinity fluctuation index; perform a simulation evaluation on the strawberry root system extension state for the reduction of trace element absorption in the soil layer based on the soil layer over-alkalinity fluctuation index to obtain over-alkaline soil layer trace element absorption reduction data; perform a nutrient uptake efficiency restriction regression analysis on the strawberry root system extension state according to the over-alkaline soil layer trace element absorption reduction data to obtain nutrient uptake efficiency restriction regression data; A planting environment detection model construction module, configured to construct an automated planting environment detection model based on the strawberry root system over-acid growth retardation evolution data and the nutrient uptake efficiency restriction regression data to obtain an automated planting environment detection model; send the automated planting environment detection model to the cloud platform to perform agricultural product planting environment detection.

Images