Agricultural product planting environment detection method and system

Abstract

The invention relates to the technical field of planting environment detection, in particular to an agricultural product planting environment detection method and system. The method comprises the following steps: acquiring a soil layer state of a strawberry planting area through a soil monitoring sensor, and performing pH fluctuation analysis to obtain strawberry soil layer pH fluctuation data; obtaining strawberry plant morphology data, evaluating a root system extension state, simulating organic matter decomposition and decay based on soil layer acidity and alkalinity data, and analyzing the peracid development retardation of strawberry root systems; analyzing the soil layer over-alkaline fluctuation index, simulating the influence of the over-alkaline soil layer on the absorption of trace elements in the strawberry root system, and carrying out regression analysis on the nutrient uptake efficiency; and constructing an automatic planting environment detection model in combination with the root development retardation evolution data and the nutrient uptake efficiency regression data, and uploading the model to a cloud platform to execute agricultural product planting environment detection. According to the invention, the planting environment detection technology is optimized, so that the planting environment detection technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of planting environment detection, and in particular 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 failed to grasp the growth conditions of soil and crops in a timely and accurate manner, leading to problems such as waste of resources, environmental pollution and poor crop growth. Especially in the planting process of high-value fruits and vegetables such as strawberries, the influence of soil pH, nutrients and water conditions on crop growth is 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. The overly acidic or alkaline soil environment not only limits the absorption of water and nutrients by the strawberry roots, but also causes the root system to develop slowly, thereby affecting the growth and yield of the entire plant. At the same time, the decomposition of organic matter and the absorption of trace elements in the soil are also closely related to the soil pH, which in turn affects the nutritional supply and quality of strawberries. Therefore, how to accurately measure the changes in soil pH and optimize and regulate it in combination with the growth status of the strawberry root system has become an important direction for improving the efficiency and quality of strawberry planting. However, a traditional method for detecting the planting environment of agricultural products has the problem of inaccurate analysis of the impact on the development of strawberry roots, resulting in large errors 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 agricultural product planting environment to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for detecting the planting environment of agricultural products is provided, the method comprising the following steps: 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; 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; Step S3: performing an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; performing a soil trace element absorption loss simulation assessment on the strawberry root extension state based on the soil over-alkali fluctuation index to obtain over-alkali soil trace element absorption loss data; performing a nutrient uptake efficiency constraint regression analysis on the strawberry root extension state based on the over-alkali soil trace element absorption loss data to obtain nutrient uptake efficiency constraint regression data; Step S4: construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint 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.

[0005] Preferably, step S1 comprises the following steps: Step S11: monitoring the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; Step S12: performing data cleaning on the strawberry soil layer status monitoring data to obtain strawberry soil layer status monitoring cleaning data; Step S13: performing pH fluctuation analysis on the strawberry soil layer status monitoring and cleaning data to obtain pH fluctuation data of the strawberry soil layer.

[0006] Preferably, step S2 comprises the following steps: 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; 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; Step S23: quantifying the decomposition and decay of vertical permeable organic matter in the soil layer based on the soil layer acidity time series variation intensity data to obtain vertical permeable organic matter decomposition and decay data; Step S24: performing decay rate self-similar structure analysis on the vertical penetration organic matter decomposition decay data to obtain organic matter vertical decomposition decay self-similar data; 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; 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.

[0007] Preferably, step S23 includes the following steps: Step S231: performing spatial interpolation of soil layer vertical cross-section acidity on soil layer acidity time series variation intensity data to obtain vertical cross-section acidity interpolation data; Step S232: fitting the inverse decay relationship of the bacterial community according to the vertical section acidity interpolation data to obtain the inverse decay relationship data of the bacterial community; Step S233: simulate and infer the difference in decay rate of relative abundance of bacterial communities on the inverse decay relationship data of bacterial communities to obtain the difference in decay rate of relative abundance of bacterial communities; Step S234: performing enzyme configuration evolution catalytic efficiency weakening fitting based on the inverse decay relationship data of bacterial communities and the relative abundance decay rate difference of bacterial communities to obtain enzyme configuration evolution catalytic efficiency weakening data; Step S235: quantify the decomposition and decay of vertical infiltration organic matter in the soil layer according to the enzyme configuration evolution catalytic efficiency weakening data, the relative abundance decay rate difference of the bacterial community and the inverse decay relationship data of the bacterial community, and obtain the vertical infiltration organic matter decomposition and decay data.

[0008] Preferably, step S25 comprises the following steps: Step S251: performing multi-level frequency domain decomposition processing on the organic matter vertical decomposition decay self-similar data to obtain multi-layer spectrum decomposition decay intensity data; Step S252: analyzing the soil nitrification inhibition index based on the multi-layer spectrum decomposition decay intensity data to obtain the soil nitrification inhibition index; Step S253: Calculating the nitrogen release reduction index according to the multi-layer spectrum decomposition decay intensity data and the soil nitrification inhibition index to obtain the nitrogen release reduction index; Step S254: fitting the nitrogen conversion magnitude loss according to the nitrogen release reduction index to obtain nitrogen conversion magnitude loss data.

[0009] Preferably, step S253 includes the following steps: Drawing a multi-layer decay intensity fluctuation curve on the multi-layer spectrum decomposition decay intensity data to obtain a multi-layer decay intensity fluctuation curve; 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; Based on the multi-layer single-point attenuation mutation entropy value, the nonlinear mineralization rate attenuation interval of nitrogen element is deduced, and the nonlinear mineralization rate attenuation interval is obtained; The soil nitrification inhibition index is used to evaluate the reduction of nitrifying microbial activity, and the reduction of nitrifying microbial activity data is obtained; The nitrogen release reduction index was calculated based on the nonlinear mineralization rate attenuation interval and the nitrifying microbial activity reduction data to obtain the nitrogen release reduction index.

[0010] Preferably, step S3 comprises the following steps: Step S31: performing an alkalinity fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain an alkalinity fluctuation index of the soil layer; Step S32: simulating and evaluating the absorption and loss of trace elements in the soil layer based on the soil alkalinity fluctuation index of the strawberry root extension state to obtain the absorption and loss data of trace elements in the alkaline soil layer; Step S33: Calculating the weakening interval of soil water holding capacity according to the soil alkali fluctuation index to obtain the weakening interval of soil water holding capacity; Step S34: performing nutrient uptake efficiency constraint regression analysis on the strawberry root extension state according to the trace element absorption loss data of the over-alkaline soil layer and the weakened water holding capacity interval of the soil layer to obtain nutrient uptake efficiency constraint regression data.

[0011] Preferably, step S32 includes the following steps: Step S321: performing equal-interval discrete difference processing on the soil layer over-alkali fluctuation index to obtain an over-alkali disturbance amplitude variation sequence; Step S322: performing disordered differential processing of the decrease in the effective state content of soil trace elements based on the over-alkalinity disturbance amplitude change sequence to obtain disordered data of the decrease in the effective state content of trace elements; Step S323: performing inflection point decrease continuity rate analysis on the disordered data of effective state content decrease to obtain the content decrease inflection point continuity rate; Step S324: Based on the disordered data of the decrease in effective content and the continuity rate of the inflection point of the content decrease, the strawberry root extension state is simulated and evaluated for the absorption loss of trace elements in the soil layer to obtain the absorption loss data of trace elements in the over-alkaline soil layer.

[0012] Preferably, step S33 includes the following steps: Step S331: simulating the discrete deformation of the soil layer according to the soil layer alkali fluctuation index to obtain soil discrete deformation data; Step S332: performing soil pore structure enlargement mapping based on the soil discrete deformation data to obtain soil pore structure enlargement mapping data; Step S333: quantifying the anisotropic attenuation of soil capillary force according to the soil pore structure enlargement mapping data to obtain the anisotropic attenuation data of capillary force; Step S334: Calculate the weakening interval of soil layer water holding capacity according to the capillary force anisotropic attenuation data to obtain the weakening interval of soil layer water holding capacity.

[0013] Preferably, the present invention further provides an agricultural product planting environment detection system for executing the agricultural product planting environment detection method as described above, the agricultural product planting environment detection system comprising: The pH fluctuation analysis module is used to monitor the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; perform pH fluctuation analysis on the strawberry soil state monitoring data to obtain strawberry soil pH fluctuation data; The module for stunting simulation and evolution is used to obtain the morphological data of strawberry plants; evaluate the root extension state of strawberry plant morphological data to obtain the root extension state of strawberry; quantify the decomposition and decay of vertical permeable organic matter in the soil layer based on the pH fluctuation data of strawberry soil layer to obtain the decomposition and decay data of vertical permeable organic matter; simulate the evolution of acid stunting of strawberry root extension state based on the decomposition and decay data of vertical permeable organic matter to obtain the acid stunting evolution data of strawberry root system; The nutrient uptake efficiency constraint analysis module is used to perform an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; simulate and evaluate the absorption and loss of trace elements in the soil layer on the extension state of the strawberry root system based on the over-alkali fluctuation index of the soil layer to obtain the absorption and loss data of trace elements in the over-alkali soil layer; perform a nutrient uptake efficiency constraint regression analysis on the extension state of the strawberry root system based on the absorption and loss data of trace elements in the over-alkali soil layer to obtain the nutrient uptake efficiency constraint regression data; The planting environment detection model construction module is used to construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint regression data to obtain an automated planting environment detection model; the automated planting environment detection model is sent to the cloud platform to perform agricultural product planting environment detection.

[0014] The beneficial effect of the present invention is that, by obtaining the soil state data of the strawberry planting area in real time through the soil monitoring sensor, the pH change of the soil can be accurately grasped. pH has a vital impact on the growth of strawberries, especially in the process of root absorption of water and nutrients, an overly acidic or overly alkaline soil environment will lead to limited growth of strawberries. By analyzing the soil pH fluctuation data, the abnormal fluctuation of soil pH can be discovered in time, providing data support for subsequent soil improvement, thereby ensuring that strawberry plants grow in a suitable environment and improving the yield and quality of strawberries. By obtaining strawberry plant morphological data and evaluating the extension state of the root system, the growth status of the root system under different soil conditions can be intuitively understood. The growth of the root system 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 root system. By analyzing the decomposition and decay of vertically permeable organic matter, the influence of organic matter decomposition in the soil on the growth of strawberry roots can be revealed, thereby predicting the slow effect of an overly acidic environment on root development, and providing a basis for optimizing soil and improving planting techniques. The over-alkalinity fluctuation index analysis of the pH fluctuation data of strawberry soil layer can provide a deep understanding of the impact of over-alkalinity environment on the absorption of trace elements in soil. Over-alkalinity soil often leads to the loss of trace element absorption, which in turn affects the growth and development of strawberries. Through the simulation and evaluation of trace element absorption loss based on the over-alkalinity fluctuation index, it can help identify and analyze the limiting factors of nutrient absorption by strawberry roots in over-alkalinity soil. In addition, the nutrient uptake efficiency constraint regression analysis can further clarify the key factors affecting strawberry growth and provide specific guidance for improving soil management and optimizing the nutrient supply of strawberries. Combining the evolution data of over-acid development retardation of strawberry roots and the nutrient uptake efficiency constraint regression data, an automated planting environment detection model is constructed to achieve comprehensive monitoring and intelligent management of the strawberry planting environment. By uploading the model to the cloud platform, farm managers can obtain real-time data such as soil status, root development, and nutrient uptake in the strawberry planting area, so as to accurately control the planting environment. This technology not only improves the intelligence level of strawberry planting, but also provides a replicable solution for large-scale agricultural planting, promoting agriculture to develop in a more efficient, environmentally friendly and precise direction. Therefore, the present invention optimizes a traditional method for detecting a planting environment for agricultural products, solves the problem that the traditional method for detecting a planting environment for agricultural products has an inaccurate analysis of the impact on the development of strawberry roots, thereby causing a large error in the detection of the planting environment, improves the accuracy of the analysis of the impact on the development of strawberry roots, and reduces the error in the detection of the planting environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of a method for detecting an agricultural product planting environment; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. DETAILED DESCRIPTION

[0016] See also Figures 1 to 3 , a method for detecting an agricultural product planting environment, the method comprising the following steps: 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; 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; Step S3: performing an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; performing a soil trace element absorption loss simulation assessment on the strawberry root extension state based on the soil over-alkali fluctuation index to obtain over-alkali soil trace element absorption loss data; performing a nutrient uptake efficiency constraint regression analysis on the strawberry root extension state based on the over-alkali soil trace element absorption loss data to obtain nutrient uptake efficiency constraint regression data; Step S4: construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint 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.

[0017] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for detecting an agricultural product planting environment of the present invention. In this example, the method for detecting an agricultural product planting environment includes the following steps: 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; 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.

[0018] 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; In an embodiment of the present invention, the morphological data of strawberry plants are obtained, and 5 images of the top and side of the plants are collected at 10 am and 4 pm every day by a high-definition multispectral camera, and the root neck diameter, stem and leaf expansion width, number of leaves, single leaf area and other morphological parameters of strawberry plants are extracted in combination with a machine vision algorithm (using a partition extraction technology based on edge detection and color segmentation). At least 30 groups of morphological data are recorded for each strawberry plant, and a preliminary evaluation of the root extension state is performed by setting a threshold value for the root neck diameter growth rate (0.05 cm / day) and a single leaf area expansion rate (2 square centimeters / day). The evaluation standard is that if the growth rate is lower than the above threshold for 5 consecutive days, it is determined to be in a state of restricted extension. Based on the pH fluctuation data of the strawberry soil layer, the acidity peak displacement tracking method (based on the direction of change of the daily minimum pH value, tracking the vertical displacement of the acidity peak of the soil profile) is used to quantify the decomposition and decay of organic matter in the vertical permeability of the soil layer. The specific method is to divide the soil profile from 0 to 30 cm into 5 cm layers, calculate the weighted average of the pH change rate of each layer, and then infer the attenuation trend of the organic matter decomposition rate with depth based on the downward shift rate of the acidity peak, and finally obtain the vertical penetration organic matter decomposition decay data. Subsequently, based on the vertical penetration organic matter decomposition decay data, the correlation strength between the standardized acidity cumulative impact (with the unit pH cumulative change per 5 cm depth as a factor) and the root extension state is modeled to simulate the evolution of acid stunting, and the results output the evolution data of acid stunting of strawberry roots.

[0019] Step S3: performing an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; performing a soil trace element absorption loss simulation assessment on the strawberry root extension state based on the soil over-alkali fluctuation index to obtain over-alkali soil trace element absorption loss data; performing a nutrient uptake efficiency constraint regression analysis on the strawberry root extension state based on the over-alkali soil trace element absorption loss data to obtain nutrient uptake efficiency constraint regression data; In an embodiment of the present invention, the pH fluctuation data of the strawberry soil layer is processed by a moving weighted sliding average method (the weighting factor is set to 0.6 weight for the data of the last 5 days and 0.4 weight for the previous data), and then an over-alkali fluctuation index analysis is performed. The over-alkali fluctuation index is defined as the daily pH higher than 7.5 time proportion and amplitude comprehensive score, and the scoring standard is 2 points for each unit exceeding 7.5, and 1 point for each 10% increase in the time proportion. A comprehensive score higher than 8 points is determined to be a high-risk fluctuation area. According to the obtained soil over-alkali fluctuation index, the effective state concentration change rate of trace elements is estimated by the method of inference (monitoring the soluble state concentration change rate of elements such as iron, zinc, and manganese in the rhizosphere 0-10 cm soil layer) to deduce the degree of trace element absorption loss of strawberry roots. The determination method is to use ICP-MS (inductively coupled plasma mass spectrometer) to measure the effective state concentration of trace elements once a week, combine the soil over-alkali fluctuation index to perform multivariate linear regression fitting, and output the over-alkali soil layer trace element absorption loss data. Next, based on the trace element absorption loss data, the nutrient uptake efficiency constraint coefficient regression analysis technique was used. That is, the absorption change rate per unit root length of the strawberry plant was used as an indicator to regress and analyze the restrictive effect of trace element deficiency on nutrient uptake efficiency, and finally the nutrient uptake efficiency constraint regression data was formed.

[0020] Step S4: construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint 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.

[0021] In an embodiment of the present invention, based on the aforementioned strawberry root peracid stunted development evolution data and nutrient uptake efficiency constraint regression data, an automated planting environment detection model is constructed by combining integrated feature hierarchical clustering with discriminant analysis. Specifically, the peracid stunted development evolution data and nutrient uptake efficiency constraint regression data are first standardized (mean normalization), and then the environmental abnormality risk level is divided according to the data density based on the K-means++ clustering algorithm, and then the discriminant analysis method (LDA linear discriminant analysis) is combined to establish the discriminant boundaries corresponding to different levels, thereby forming 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. The automated planting environment detection model finally trained 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 using the MQTT protocol, and the cloud platform is connected to the planting management system to achieve real-time detection and abnormal warning of the strawberry agricultural product planting environment.

[0022] Step S1 includes the following steps: Step S11: monitoring the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; Step S12: performing data cleaning on the strawberry soil layer status monitoring data to obtain strawberry soil layer status monitoring cleaning data; Step S13: performing pH fluctuation analysis on the strawberry soil layer status monitoring and cleaning data to obtain pH fluctuation data of the strawberry soil layer.

[0023] In an embodiment of the present invention, soil state monitoring in a strawberry planting area is implemented by laying out soil monitoring sensors in a standard grid manner in the planting area. The soil monitoring sensor selects a time domain reflection principle monitoring device of the TDR300 type, and the burial depth is within the range of 0-30 cm, a monitoring node is set every 5 cm, and 6 layers are arranged vertically as a whole, and the horizontal spacing of each layer is 1 meter, ensuring that 1 vertical sensor point array is covered every 5 square meters. Each node simultaneously collects four parameters of soil temperature, moisture content, conductivity and pH value, and the sampling frequency is fixedly set to once every 10 minutes. The data storage format adopts binary encoding for fast batch processing. All sensors are connected to the field concentrator via the RS485 bus protocol, and the concentrator synchronizes once an hour and uploads data to the local server. The collection cycle is set to 30 consecutive days, and more than 300,000 groups of strawberry soil state monitoring data are accumulated. In order to ensure the stability and accuracy of the monitoring data, the probe baseline data is automatically calibrated by the concentrator before each collection, and the current cycle data is automatically eliminated if the calibration deviation exceeds the set threshold (0.5%). Through the above methods, complete soil status monitoring data of the strawberry planting area can be constructed, providing basic support for subsequent data processing.

[0024] 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.

[0025] Step S2 includes the following steps: 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; 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; Step S23: quantifying the decomposition and decay of vertical permeable organic matter in the soil layer based on the soil layer acidity time series variation intensity data to obtain vertical permeable organic matter decomposition and decay data; Step S24: performing decay rate self-similar structure analysis on the vertical penetration organic matter decomposition decay data to obtain organic matter vertical decomposition decay self-similar data; 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; 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.

[0026] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: 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; In an 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 is spirally ascended to make a circle to ensure that the entire plant is covered without dead angles. To avoid interference from ambient light, the scanning operation is completed from 6 to 8 in the morning, and the ambient light intensity is controlled below 10000 lux. The point cloud data obtained by scanning is subjected to noise filtering, and interference outside the plant (such as weeds, brackets, etc.) is eliminated to generate a net plant point cloud model. Subsequently, a segmentation algorithm based on the regional growth method (setting the neighborhood radius to 0.02 meters and the growth threshold to 10%) is used in the point cloud processing software to separate the strawberry root neck part and the aboveground stem and leaf structure. The main axis extraction algorithm (using the least squares method to fit the main trunk curve) is used to obtain the root extension direction and morphological characteristics of the root neck part, and the root extension density is evaluated in combination with the point cloud density distribution analysis (point number density per cubic centimeter). The root length, number of branches, and taproot thickness are all extracted automatically and quantified, ultimately forming the strawberry root extension status data, which includes five indicators: taproot length, maximum horizontal extension range, root branch density, taproot average diameter, and root neck curvature, and are uniformly stored in a standardized structured data format.

[0027] 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; In an embodiment of the present invention, the acidity time series change intensity analysis is performed on the pH fluctuation data of the strawberry soil layer. First, the time series data of pH changes within 30 days of each monitoring point are selected, and multi-scale decomposition is performed using the wavelet transform method (Daubechies 4 mother wavelets are selected, and the number of decomposition layers is set to 3 layers). The wavelet coefficients of scale one (high frequency part) and scale two (medium frequency part) are extracted, and their energy proportions are calculated respectively to evaluate the acidity fluctuation intensity of short-term and medium-term periods. After normalizing the short-term fluctuation energy and medium-term fluctuation energy of each monitoring point to the interval of 0-1, the weighted synthesis acidity change intensity value is weighted, wherein the short-term fluctuation weight is 0.7 and the medium-term fluctuation weight is 0.3. In this way, the soil acidity time series change intensity data covering the entire planting area is formed. Afterwards, combined with GIS spatial interpolation (using ordinary kriging method, the spherical model is selected for the variation function model, and the optimal number of neighbors is 12), regional distribution mapping is performed to form a spatial continuous layer of acidity change intensity, which provides input basis for subsequent organic matter decomposition and decay analysis.

[0028] Step S23: quantifying the decomposition and decay of vertical permeable organic matter in the soil layer based on the soil layer acidity time series variation intensity data to obtain vertical permeable organic matter decomposition and decay data; In an embodiment of the present invention, the decomposition and decay of vertical permeable organic matter in the soil layer is quantified based on the intensity data of the time-series change of soil acidity. First, the time-series change intensity values ​​of the acidity at each level of 0-30 cm are extracted at each vertical profile monitoring point. For each layer, the spline interpolation method is used to reconstruct the continuous acidity change profile curve, and the curve smoothing factor is set to 0.001. Then, the acidity change gradient calculation is applied to each profile, that is, the intensity difference between the upper and lower layers is calculated every 5 cm. Taking the intensity difference as input, the organic matter decomposition rate is assigned in combination with the known empirical data of organic matter decomposition rate (rate range 0.5%-2% / day, based on the linear normalization mapping of the acidity change intensity). Finally, the decomposition rate values ​​of each layer are integrated along the vertical profile to obtain the cumulative decay of the profile. After the cumulative decay is standardized, the vertical permeable organic matter decomposition decay data is generated, with a resolution of one level per 5 cm, and the unit is percentage / %, forming a complete quantitative description of the decomposition and decay of organic matter in the vertical profile.

[0029] Step S24: performing decay rate self-similar structure analysis on the vertical penetration organic matter decomposition decay data to obtain organic matter vertical decomposition decay self-similar data; 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.

[0030] 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; 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.

[0031] 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.

[0032] In an embodiment of the present invention, the strawberry root extension state is simulated and evolved based on the self-similar data of vertical decomposition and decay of organic matter and the nitrogen conversion magnitude loss data. First, the self-similarity index is used as the acidification rate influencing factor, and the nitrogen conversion magnitude loss is used as the nutrient supply attenuation factor to construct a binary input root development inhibition function. At each monitoring point, according to the initial root extension speed (according to the quantified data of step S21, the unit is mm / day), the dynamic changes of root extension are iteratively simulated by applying the dual inhibition of acidification and nutrient supply decline. Each iteration cycle is set to 1 day, and the root growth rate is updated every day. When the inhibition factor exceeds the threshold (set as the acidification rate influence factor>1.2 and the nutrient attenuation>20%), the root extension speed decreases by 30%. If the inhibition condition is met for five consecutive days, it is recorded as a root retardation event. Finally, the simulated evolution results of all monitoring points are combined to form a complete strawberry root acid retardation evolution data, including the start time, duration, cumulative extension loss and distribution range of retardation.

[0033] Step S23 includes the following steps: Step S231: performing spatial interpolation of soil layer vertical cross-section acidity on soil layer acidity time series variation intensity data to obtain vertical cross-section acidity interpolation data; Step S232: fitting the inverse decay relationship of the bacterial community according to the vertical section acidity interpolation data to obtain the inverse decay relationship data of the bacterial community; Step S233: simulate and infer the difference in decay rate of relative abundance of bacterial communities on the inverse decay relationship data of bacterial communities to obtain the difference in decay rate of relative abundance of bacterial communities; Step S234: performing enzyme configuration evolution catalytic efficiency weakening fitting based on the inverse decay relationship data of bacterial communities and the relative abundance decay rate difference of bacterial communities to obtain enzyme configuration evolution catalytic efficiency weakening data; Step S235: quantify the decomposition and decay of vertical infiltration organic matter in the soil layer according to the enzyme configuration evolution catalytic efficiency weakening data, the relative abundance decay rate difference of the bacterial community and the inverse decay relationship data of the bacterial community, and obtain the vertical infiltration organic matter decomposition and decay data.

[0034] In an embodiment of the present invention, the soil acidity time series change intensity data is interpolated for the acidity of the vertical section of the soil layer. First, for the soil pH monitoring points that have been deployed in the strawberry planting area, the acidity time series change intensity values ​​of each monitoring point at depths of 0 cm, 5 cm, 10 cm, 15 cm, 20 cm, 25 cm and 30 cm are selected, and the daily average value in the 30-day time window is extracted as the vertical section acidity sample data. The sample data is organized into a three-dimensional point set, including horizontal coordinates (X, Y) and depth coordinates (Z) and corresponding acidity intensity values ​​(pH change intensity values). Ordinary Kriging interpolation method is used for three-dimensional spatial interpolation, the variogram model is set to a spherical model, the base parameter is set to 10 meters, the range is set to 5 meters, the micro effect is set to 0.01, the number of neighboring points is set to 12, and the spatial search radius is set to 8 meters. The interpolation process is performed in a unified grid, and the grid resolution is 0.5 meters in the horizontal direction and 2 centimeters in the vertical direction to ensure that the details of the acidity change are accurately reflected in the vertical section. The interpolated vertical cross-section acidity interpolation data is saved in a standard three-dimensional grid format, and each grid unit corresponds to a specific spatial position (X, Y, Z) and its acidity change intensity value. In order to verify the interpolation quality, the ten-fold cross-validation method is used for error assessment, and the root mean square error (RMSE) is calculated, requiring the RMSE to be less than 0.3 intensity units. After the interpolation is completed, the acidity vertical profile data is extracted at each specified position (for example, a profile is taken every 2 meters in the X direction) through a fixed cross-section extraction method to form a continuous visual soil vertical cross-section acidity change distribution layer.

[0035] The inverse decay relationship of the bacterial community was fitted based on the acidity interpolation data of the vertical section. First, on each vertical section, the acidity interpolation value of the corresponding layer was extracted according to the depth layer (one layer every 2 cm). Then, the acidity value was classified according to the size of the acidity value, and the pH change intensity less than 0.2 was set 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. The initial bacterial community relative abundance standard value was set for each acidity fluctuation layer (refer to the original soil microbial community data), the low acidity fluctuation layer was set to 100%, the medium acidity fluctuation layer was set to 80%, and the high acidity fluctuation layer was set to 50%. Then, the relative abundance value of the bacterial community in each section was paired with the corresponding acidity interpolation intensity to form a two-dimensional data set of bacterial community abundance-acidity intensity. The power law function was used to fit the inverse relationship. The fitting model was set as the relative abundance of the bacterial community equal to a constant multiplied by the negative first power of the acidity change intensity. The least squares method was used to fit the parameters. The outlier points with a residual greater than 20% were removed during the fitting process. Each profile was fitted separately to obtain the inverse decay fitting curve of the bacterial community in each profile and its goodness of fit index (R² required to be greater than 0.85). Finally, a data set of the inverse decay relationship of the bacterial community was formed. Each profile stored the fitting parameters, curve morphological characteristics and fitting error information. After the fitting was completed, the spatial response gradient characteristics of the bacterial community to the acidity change were analyzed by longitudinally comparing the differences in fitting parameters of different profiles. The inverse decay relationship data of the bacterial community was simulated and inferred by the difference in the decay rate of the relative abundance of the bacterial community. First, the relative abundance decrease rate of the bacterial community in different acidity intensity intervals was extracted from the inverse decay fitting curve of each profile. The rate was defined as the percentage of decrease in bacterial abundance under the increase of unit acidity change intensity. The intensity of acidity change is divided into five intervals: 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8, and above 0.8. The local decay rate is estimated in each interval using the derivative approximation method, that is, the local rate value is obtained by calculating the tangent slope of the curve at the midpoint of the interval. Subsequently, the local decay rates in different intervals are normalized to make the rate values ​​between different profiles comparable. Then, the standard deviation of the decay rate of the relative abundance of the flora in the same interval between each profile is calculated, and the standard deviation is the difference in the decay rate of the relative abundance of the flora between different profiles in the interval. In order to ensure the accuracy of the inference, the elimination criteria are set during the inference process: if the number of profiles in a certain interval is less than 5, the data in that interval is discarded. Finally, a complete dataset of the relative abundance decay rate difference of the flora is formed, which includes the rate difference, sample number, and rate difference change trend in each interval of acidity change intensity. In order to further analyze the depth effect of the difference in microbial community response, the rate difference of each profile was weighted averaged according to the profile depth to obtain the microbial community response difference curve that changes with depth, providing a quantitative basis for the subsequent soil ecological stability analysis.

[0036] 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.

[0037] Step S25 includes the following steps: Step S251: performing multi-level frequency domain decomposition processing on the organic matter vertical decomposition decay self-similar data to obtain multi-layer spectrum decomposition decay intensity data; Step S252: analyzing the soil nitrification inhibition index based on the multi-layer spectrum decomposition decay intensity data to obtain the soil nitrification inhibition index; Step S253: Calculating the nitrogen release reduction index according to the multi-layer spectrum decomposition decay intensity data and the soil nitrification inhibition index to obtain the nitrogen release reduction index; Step S254: fitting the nitrogen conversion magnitude loss according to the nitrogen release reduction index to obtain nitrogen conversion magnitude loss data.

[0038] In an embodiment of the present invention, multi-level frequency domain decomposition processing is performed on the self-similar data of vertical decomposition decay of organic matter to obtain multi-level spectrum decomposition decay intensity data. First, the input self-similar data of vertical decomposition decay of organic matter is preprocessed, including data normalization processing, unifying the dimensions of each data point to a dimensionless ratio value, and the normalization interval is set to 0 to 1. Subsequently, the normalized data is decomposed at multiple scales by applying the wavelet transform method, the wavelet basis function uses Daubechies wavelet db4, the number of wavelet decomposition layers is set to 5 layers, and the decomposition process is strictly carried out from top to bottom according to the time scale, and each layer extracts frequency feature information at different scales. At each decomposition layer, the wavelet detail coefficient is extracted, and the energy density formula is used to analyze the energy intensity of the detail coefficient, and the energy density is calculated by dividing the square sum of each coefficient by the number of coefficients. The energy density value obtained at each decomposition layer is the spectrum decomposition decay intensity data of the corresponding level. This processing process strictly retains the local extreme value change characteristics at each scale to ensure the integrity and independence of frequency domain information at different scales. The final output data structure is five sets of spectrum decomposition decay intensity sets, each set corresponds to a decomposition scale, and the unit is dimensionless energy density value. The soil nitrification inhibition index is analyzed based on the multi-layer spectrum decomposition decay intensity data. First, for each layer of spectrum decomposition decay intensity data, the maximum value, mean and standard deviation of the energy density value are extracted to construct the frequency domain feature vector. Then, according to the spectrum intensity distribution characteristics, the spectrum layer characterized by abnormal increase of energy density in the low-frequency interval is screened out. The judgment standard is that the mean energy density in the low-frequency area is more than 1.5 times higher than the mean energy density in the medium and high frequency areas. The selected low-frequency energy density values ​​are extracted and converted to the range of 0 to 1 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 index value, the greater the degree of inhibition of soil nitrification. During the analysis process, the data elimination rules are set to eliminate the data points whose abnormal fluctuation of low-frequency energy density exceeds the mean ±2 times the standard deviation to ensure the stability and representativeness of the analysis results. The final soil nitrification inhibition index is output in the form of dimensionless numerical values ​​ranging from 0 to 1, and each profile position corresponds to a soil nitrification inhibition index value. The nitrogen release reduction index is calculated based on the multi-layer spectrum decomposition decay intensity data and the soil nitrification inhibition index. First, a joint feature matrix is ​​constructed by combining the energy density mean in the spectrum decomposition decay intensity data of each profile with the soil nitrification inhibition index. The first principal component is extracted by principal component analysis of the feature matrix as the soil comprehensive activity index. Subsequently, the nitrogen release reduction index is defined as the weighted product of the soil comprehensive activity index and the soil nitrification inhibition index, with weighting coefficients of 0.6 and 0.4, respectively. After the weighted product, it is normalized to the range of 0 to 1. During the calculation process, the spectrum data is required to be aligned with the nitrification inhibition index data, that is, the two data sources at the same profile depth are strictly corresponding, and the profiles with asynchronous data will be eliminated.The larger the value of the nitrogen release reduction index, the more serious the decline in nitrogen bioavailability in the soil of the profile. The final calculation outputs the nitrogen release reduction index data table corresponding to each profile depth position. The nitrogen conversion order of magnitude loss is fitted according to the nitrogen release reduction index. First, for the nitrogen release reduction index, the index interval is divided into ten level intervals with a step size of 0.1. The historical measured nitrogen conversion rate data corresponding to each index interval are collected, and the rate unit is milligrams per kilogram per hour, and a corresponding table of nitrogen conversion rate and nitrogen release reduction index is established. Subsequently, the nitrogen release reduction index is used as the independent variable and the logarithm of the nitrogen conversion rate is used as the dependent variable. Linear regression is used for fitting. During the regression analysis, the determination coefficient R² is required to be greater than 0.85, otherwise the index interval division parameters are readjusted until they meet the requirements. The regression equation is used to infer the nitrogen conversion rate order of magnitude loss corresponding to any nitrogen release reduction index value. The order of magnitude is defined as the logarithmic difference between the inferred rate and the standard rate (the average nitrogen conversion rate measured under non-inhibition conditions). The final nitrogen conversion order-of-magnitude loss data include the nitrogen release decrease index, estimated rate value and corresponding order-of-magnitude loss value corresponding to each depth position of the profile, which are organized and saved in a tabular form for use in subsequent strawberry root retardation simulation evolution steps.

[0039] Step S253 includes the following steps: Drawing a multi-layer decay intensity fluctuation curve on the multi-layer spectrum decomposition decay intensity data to obtain a multi-layer decay intensity fluctuation curve; 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; Based on the multi-layer single-point attenuation mutation entropy value, the nonlinear mineralization rate attenuation interval of nitrogen element is deduced, and the nonlinear mineralization rate attenuation interval is obtained; The soil nitrification inhibition index is used to evaluate the reduction of nitrifying microbial activity, and the reduction of nitrifying microbial activity data is obtained; The nitrogen release reduction index was calculated based on the nonlinear mineralization rate attenuation interval and the nitrifying microbial activity reduction data to obtain the nitrogen release reduction index.

[0040] In an embodiment of the present invention, a multi-layer decay intensity fluctuation curve is drawn for the multi-layer spectrum decomposition decay intensity data to obtain a multi-layer decay intensity fluctuation curve. Specifically, the input multi-layer spectrum decomposition decay intensity data is classified and sorted according to the decomposition scale, and each layer of spectrum data is separately classified into a group, and each group of data is sorted in depth order to ensure that the data of each depth point corresponds to each other. Subsequently, the depth is used as the horizontal coordinate and the spectrum energy density value is used as the vertical coordinate. The fluctuation curve is drawn by point-by-point connection. The curve is not smoothed during the drawing process to retain the original fluctuation characteristics. In order to enhance the resolution of curve details, the horizontal coordinate step is fixed to 1 cm, and the vertical coordinate adopts a logarithmic scaling method to enhance the visual recognition effect of small change segments. Each scale decomposition layer generates a fluctuation curve separately, and each curve is numbered independently, and the number is arranged in ascending order according to the scale size, that is, the smaller the scale, the smaller the number. The multi-layer decay intensity fluctuation curve data finally output is saved in the form of a standard two-dimensional coordinate data point set, and each group of curves contains the coordinate values ​​of continuous data points of all depth layers. The multi-layer single-point attenuation mutation entropy value analysis is performed on the multi-layer decay intensity fluctuation curve to obtain the multi-layer single-point attenuation mutation entropy value. The specific implementation is that, first, for each decay intensity fluctuation curve, the energy density change between adjacent depth points is calculated in a single-point difference manner, and the single-point difference is defined as the energy density of the next depth point minus the energy density of the previous depth point. Subsequently, the absolute values ​​of all single-point differences are taken to construct a sequence of single-point change absolute values. The sequence is locally normalized, and every five consecutive depth points are taken as a group and normalized to the range of 0 to 1. Then, the local entropy value is calculated based on each group of normalized sequences. The entropy value is defined as the negative sum of the product of the probability logarithm corresponding to the frequency of occurrence of the normalized difference. The specific operation is to count the number of data points in each normalized difference interval, calculate the proportion of data points in the interval, take the logarithm of each proportion, multiply it by the proportion itself, and then sum and take the negative, that is, the local entropy value is obtained. A high local entropy value indicates a drastic single-point difference, and a low local entropy value indicates a stable change. Each local entropy value corresponds to the overall depth profile according to its central depth, and finally a multi-layer single-point attenuation mutation entropy value data set is obtained, and each scale decomposition layer corresponds to a set of entropy value profile data. Based on the multi-layer single-point attenuation mutation entropy value, the nonlinear mineralization rate attenuation interval of nitrogen is deduced to obtain the nonlinear mineralization rate attenuation interval. The specific implementation is to first screen the mutation area in each layer of entropy value profile data. The screening criteria are the depth points where the local entropy value is greater than the mean of the entropy value of the whole profile plus 2 times the standard deviation. The screened depth points are regarded as potential nonlinear attenuation trigger points. Subsequently, with each mutation trigger point as the center, it is extended 5 cm upward and downward respectively, and defined as the attenuation sensitive area. For each attenuation sensitive area, the initial value and terminal value of the spectral decomposition decay intensity of the corresponding depth are extracted, and the spectral energy density decrease rate is calculated. The sensitive area with a decrease rate of more than 30% is defined as the effective nonlinear mineralization rate attenuation interval. For sensitive areas where multiple consecutive mutation trigger points overlap, the union process is taken to merge into a larger attenuation interval.The final output is the nonlinear mineralization rate attenuation interval data, including the starting depth, ending depth and the corresponding decline rate value. All intervals are recorded in ascending depth order, and the data at each scale level are saved independently.

[0041] In the specific implementation process of evaluating the loss of nitrifying microbial activity by soil nitrification inhibition index to obtain the data of loss of nitrifying microbial activity, the soil nitrification inhibition index is first extracted, which is calculated by the ratio of the actual measured value of soil ammonia oxidation rate to the measured value of ammonia oxidation rate of the control group without inhibition. The specific operation is to set the ammonia oxidation rate measurement cycle to 48 hours, record the change 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 samples and the control samples without inhibitors are cultured under the same conditions, and the complete rate data curve is measured. The average ammonia oxidation rate of each time period is calculated, and then the ratio of the actual soil ammonia oxidation rate to the ammonia oxidation rate of the control group is taken, which is defined as the soil nitrification inhibition index. Subsequently, according to the quantitative description standard of the activity of nitrifying microorganisms in soil microbiology, the activity loss classification threshold is set, and samples with an inhibition index less than 0.7 are calibrated as activity loss, samples with an inhibition index between 0.7 and 0.9 are calibrated as slightly weakened activity, and samples with an inhibition index greater than 0.9 are calibrated as normal activity. Each sampling point is evaluated and classified separately, and the results are organized into nitrifying microorganism activity reduction data, including sampling location, measurement time, inhibition index value and activity state classification. In the specific implementation process of calculating the nitrogen release reduction index based on the nonlinear mineralization rate attenuation interval and the nitrifying microorganism activity reduction data to obtain the nitrogen release reduction index, firstly, the corresponding depth range is extracted according to the nonlinear mineralization rate attenuation interval data determined in the previous step, and the classification of nitrifying microorganism activity reduction at the corresponding depth is counted in each attenuation interval. For each attenuation interval, the ratio of the number of activity reduction samples to the total number of samples is counted, which is defined as the activity reduction ratio of the attenuation interval. Subsequently, the spectral energy reduction rate and the activity reduction ratio of each attenuation interval are weighted and comprehensively calculated. The calculation process is that the spectral reduction rate and the activity reduction ratio are multiplied by the set weight factor, where the spectral reduction rate weight is set to 0.6 and the activity reduction ratio weight is set to 0.4, and the weighted addition of the two is used to obtain the original value of the nitrogen release reduction index. Afterwards, the original values ​​of the nitrogen release reduction index of all attenuation intervals are normalized so that the final nitrogen release reduction index is in the range of 0 to 1, where the smaller the value, the more severe the nitrogen release attenuation. The final output nitrogen release reduction index data includes the start and end depths of the attenuation interval, the spectrum decline rate, the activity reduction ratio, and the normalized nitrogen release reduction index. All data are arranged in a table and saved in ascending depth order. Quantitative calculation methods are used throughout the calculation process, without introducing empirical parameters or manual adjustments, to ensure that the data processing process has complete traceability and consistency.

[0042] Step S3 includes the following steps: Step S31: performing an alkalinity fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain an alkalinity fluctuation index of the soil layer; Step S32: simulating and evaluating the absorption and loss of trace elements in the soil layer based on the soil alkalinity fluctuation index of the strawberry root extension state to obtain the absorption and loss data of trace elements in the alkaline soil layer; Step S33: Calculating the weakening interval of soil water holding capacity according to the soil alkali fluctuation index to obtain the weakening interval of soil water holding capacity; Step S34: performing nutrient uptake efficiency constraint regression analysis on the strawberry root extension state according to the trace element absorption loss data of the over-alkaline soil layer and the weakened water holding capacity interval of the soil layer to obtain nutrient uptake efficiency constraint regression data.

[0043] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: performing an alkalinity fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain an alkalinity fluctuation index of the soil layer; In an embodiment of the present invention, during the specific implementation of the over-alkali fluctuation index analysis of the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer, soil samples are first collected at intervals of 2 cm in the depth range of 0 cm to 30 cm in the strawberry planting area, and the pH value of each sample is measured respectively using the glass electrode method, and the pH value corresponding to each sampling depth is recorded. Subsequently, the pH fluctuation curve of the soil layer is drawn according to the continuous sampling depth as the horizontal axis and the pH value as the vertical axis, and the peaks higher than pH8.0 are screened out using the local maximum recognition method, and the fluctuation amplitude is calculated for each peak interval, that is, the peak pH value minus the mean of the lowest pH value before and after the peak. All peak fluctuation amplitudes are averaged, and the result is defined as the over-alkali fluctuation index. If the number of peaks detected is less than 3, the mean of the regional fluctuation amplitudes all higher than pH8.0 is used as supplementary data to ensure that the number of statistical samples is stable.

[0044] Step S32: simulating and evaluating the absorption and loss of trace elements in the soil layer based on the soil alkalinity fluctuation index of the strawberry root extension state to obtain the absorption and loss data of trace elements in the alkaline soil layer; In an embodiment of the present invention, in the specific implementation process of simulating and evaluating the absorption and loss of trace elements in the soil layer based on the soil layer over-alkali fluctuation index of the strawberry root extension state to obtain the absorption and loss data of trace elements in the over-alkali soil layer, firstly, according to the obtained soil layer over-alkali fluctuation index, the effective trace element content data of each layer of soil in the corresponding depth range is extracted, and the effective trace elements include iron, manganese, zinc, and copper, which are extracted by DTPA extraction method and 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 to be absorption loss, and the specific depth and element type are recorded. Then, a linear fit is performed based on the size of the over-alkali fluctuation index and the absorption loss ratio. The absorption and loss data of trace elements in the complete over-alkali soil layer are deduced according to the relationship that the over-alkali fluctuation index increases by 0.1 and the absorption loss ratio increases by 5%.

[0045] Step S33: Calculating the weakening interval of soil water holding capacity according to the soil alkali fluctuation index to obtain the weakening interval of soil water holding capacity; In an embodiment of the present invention, in the specific implementation process of calculating the weakened interval of the water-holding capacity of the soil layer according to the soil layer alkalinity fluctuation index to obtain the weakened interval of the water-holding capacity of the soil layer, firstly, the soil layer section with a pH greater than 8.0 is extracted, and the change of soil moisture content in the corresponding section is detected. The moisture content data is measured by the weight method, and the mass change is recorded every 4 hours. The monitoring period is 48 hours. The rate of decrease of the moisture content is fitted by linear regression, and the percentage of the decrease of the moisture content per hour is calculated. If the rate of decrease of the moisture content in a certain interval is greater than 0.5% per hour, it is marked as a weakened interval of water holding capacity. The section with more than two layers in a row and the decrease rate meets the conditions is recorded as a complete weakened interval, and the start and end depths and the average decrease rate are recorded, and finally the data of the weakened interval of the water-holding capacity of the soil layer is output.

[0046] Step S34: performing nutrient uptake efficiency constraint regression analysis on the strawberry root extension state according to the trace element absorption loss data of the over-alkaline soil layer and the weakened water holding capacity interval of the soil layer to obtain nutrient uptake efficiency constraint regression data.

[0047] In the embodiment of the present invention, in the specific implementation process of performing nutrient uptake efficiency constraint regression analysis on the extension state of strawberry root system according to the absorption loss data of trace elements in the over-alkaline soil layer and the weakened water holding capacity interval of the soil layer to obtain the nutrient uptake efficiency constraint regression data, the absorption loss ratio of each element in the absorption loss data of trace elements in the over-alkaline soil layer is first standardized so that it is between 0 and 1, and the average decline rate of each water holding capacity weakened interval is also standardized. Subsequently, the absorption loss ratio is set as the independent variable, the water holding capacity decline rate is set as the auxiliary independent variable, and the nutrient absorption amount actually measured by the strawberry root system is set as the dependent variable, and a multivariate linear regression analysis is performed. During the analysis process, the least squares method is used to fit the influence weight of each variable on the dependent variable. A single sample unit (per 10 cm depth section) is used as the basic unit for regression analysis, and the data volume per unit is not less than 30 groups to ensure regression stability. Finally, the nutrient uptake efficiency constraint regression data is output, including the regression coefficient of each variable, the determination coefficient R square value and the statistical data of the fitted residual distribution. No non-mathematical inference means are introduced in the entire analysis process, and all actual measured data are used for regression processing.

[0048] Step S32 includes the following steps: Step S321: performing equal-interval discrete difference processing on the soil layer over-alkali fluctuation index to obtain an over-alkali disturbance amplitude variation sequence; Step S322: performing disordered differential processing of the decrease in the effective state content of soil trace elements based on the over-alkalinity disturbance amplitude change sequence to obtain disordered data of the decrease in the effective state content of trace elements; Step S323: performing inflection point decrease continuity rate analysis on the disordered data of effective state content decrease to obtain the content decrease inflection point continuity rate; Step S324: Based on the disordered data of the decrease in effective content and the continuity rate of the inflection point of the content decrease, the strawberry root extension state is simulated and evaluated for the absorption loss of trace elements in the soil layer to obtain the absorption loss data of trace elements in the over-alkaline soil layer.

[0049] In an embodiment of the present invention, in the specific implementation process of performing equally spaced discrete difference processing on the soil layer over-alkali fluctuation index to obtain an over-alkali disturbance amplitude change sequence, firstly, the over-alkali fluctuation index data corresponding to every 2 cm depth point within the depth range of 0 cm to 30 cm in the strawberry planting area are selected to form a preliminary over-alkali fluctuation index sequence. Then, according to the depth sequence order, a first-order difference operation is performed in units of 2 cm, that is, the over-alkali fluctuation index of the current point is subtracted from the over-alkali fluctuation index of the previous depth point to obtain the disturbance amplitude change amount between continuous depths. The disturbance amplitude changes of all depth points are arranged in order to form a complete over-alkali disturbance amplitude change sequence. For example, if the over-alkali fluctuation index at the depth points of 0 cm, 2 cm, and 4 cm are 0.3, 0.5, and 0.4, respectively, the change at 2 cm is 0.2, and the change at 4 cm is -0.1. In the specific implementation process of performing disordered differential processing on the decrease of effective state content of soil trace elements based on the over-alkaline disturbance amplitude change sequence to obtain disordered data on the decrease of effective state content of trace elements, firstly, the effective state content data of four trace elements of soil iron, manganese, zinc and copper corresponding to each of the above-mentioned depth points are extracted, and the data are obtained by DTPA extraction method and atomic absorption spectroscopy. Then, the change rate of each element content between every two consecutive depth points is calculated according to the order of the over-alkaline disturbance amplitude change sequence, that is, the element content of the next depth point is subtracted from the element content of the previous depth point, and then divided by the depth interval of 2 cm. In order to reflect the disorder, disturbance adjustment is introduced into the above-mentioned change rate sequence, that is, the absolute value of the difference between two adjacent change rates is superimposed on each change rate, thereby forming disordered data on the decrease of effective state content. For example, if the iron content at 4 cm is 3.8 mg / kg and at 2 cm is 4.0 mg / kg, the initial change rate is -0.1. 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 analyzing the continuity rate of the inflection point decrease of the disordered data of the decrease in effective content to obtain the continuity rate of the inflection point of the content decrease, the local minimum detection algorithm is first used to identify the inflection point position of the downward trend in the disordered data sequence of the decrease in effective content, that is, the local minimum point relative to the downward trend on both sides. For each pair of disordered change data between adjacent inflection points, the continuity of the change rate is calculated, that is, the proportion of the change rate signs that remain consistent in the interval is counted, and the proportion is multiplied by the average decline rate of the interval to obtain the continuity rate of the inflection point of the content decrease. For example, if 4 of the 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, which is -0.096. This processing method can accurately reflect the stability and strength of the downward trend of trace element content.In the specific implementation process of simulating and evaluating the loss of trace element absorption in the soil layer based on the disordered data of the decrease in effective content and the continuity rate of the inflection point of the content decrease to obtain the data of trace element absorption loss in the over-alkaline soil layer, the disordered data of the decrease in effective content at each depth point and the corresponding inflection point continuity rate data were first combined to set a standardized evaluation rule, that is, the depth section with a disordered decrease value higher than 0.1 and an absolute value of the inflection point continuity rate greater than 0.08 was determined as a trace element absorption loss zone. Subsequently, each trace element determined as a loss zone was cumulatively counted, and the cumulative decrease ratio of the four elements of iron, manganese, zinc, and copper in each depth section was calculated. The calculation method was the percentage of the decrease in content in each depth section to the standard content, and the weighted average of the loss ratios of all depth sections was used to form the data of trace element absorption loss in the over-alkaline soil layer.

[0050] Step S33 includes the following steps: Step S331: simulating the discrete deformation of the soil layer according to the soil layer alkali fluctuation index to obtain soil discrete deformation data; Step S332: performing soil pore structure enlargement mapping based on the soil discrete deformation data to obtain soil pore structure enlargement mapping data; Step S333: quantifying the anisotropic attenuation of soil capillary force according to the soil pore structure enlargement mapping data to obtain the anisotropic attenuation data of capillary force; Step S334: Calculate the weakening interval of soil layer water holding capacity according to the capillary force anisotropic attenuation data to obtain the weakening interval of soil layer water holding capacity.

[0051] In this massage embodiment, in the specific implementation process of simulating the discrete deformation of the soil layer according to the soil layer over-alkali fluctuation index to obtain the discrete deformation data of the soil, firstly, according to the over-alkali fluctuation index sequence measured at intervals of 2 cm in 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-alkali fluctuation index value of the corresponding depth, and the deformation coefficient is positively correlated with the over-alkali fluctuation index. When the over-alkali fluctuation index is 0, the deformation coefficient is set to 0, and when the over-alkali 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, and the unit pairs with a difference value exceeding 0.05 are defined as generating discrete deformations, and the discrete intensity levels are marked. The discrete intensity levels are 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 soil pore structure expansion mapping based on soil discrete deformation data to obtain soil pore structure expansion mapping data, the points marked as discrete units in the soil discrete deformation data are first screened, and the corresponding pore expansion increment is assigned to each discrete unit according to the discrete intensity level. Slightly discrete units correspond to a 2% increase in porosity, moderately discrete units correspond to a 5% increase in porosity, and severely discrete units correspond to an 8% increase in porosity. Then, with each unit as the center, a 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 according to the Manhattan distance of 1, and a weight of 0.25 according to the Manhattan distance of 2. The final porosity change of each unit is obtained by cumulative superposition calculation to form the soil pore structure expansion mapping data. Taking a specific experiment as an example, if the original porosity is 45%, the porosity of the slightly discrete unit can be increased to about 47% after expansion and diffusion superposition. In the specific implementation process of quantifying the anisotropic attenuation of soil capillary force according to the soil pore structure expansion mapping data to obtain the anisotropic attenuation data of capillary force, firstly, according to the soil porosity change, the porosity change gradient is extracted in the horizontal and vertical directions respectively. The gradient of the porosity expansion mapping data is calculated in the horizontal and vertical directions respectively using a two-dimensional difference operator, and the gradient value is the anisotropic expansion rate. Then, according to the principle of the inverse relationship between capillary force and porosity, the anisotropic expansion rate is multiplied by the attenuation coefficient constant 0.6 to obtain the anisotropic attenuation of capillary force. Taking the specific data as an example, if the lateral expansion rate is 0.04 and the vertical expansion rate is 0.02, the lateral capillary force attenuation is 0.024 and the vertical capillary force attenuation is 0.012. The anisotropic capillary force attenuation data of all units constitute the soil capillary force anisotropic attenuation data matrix.In the specific implementation process of calculating the weakened interval of soil water holding capacity according to the anisotropic attenuation data of capillary force to obtain the weakened interval of soil water holding capacity, the anisotropic attenuation data of capillary force is firstly layered and statistically analyzed by depth, with each layer of 2 cm, and the average attenuation of each layer in the horizontal and vertical directions is calculated respectively. Then the water holding capacity weakening judgment standard is set, and the layer with the average attenuation of capillary force in the horizontal or vertical direction exceeding 0.015 is defined as the weakened water holding capacity zone. The adjacent and continuous layers judged as weakened water holding capacity are further merged to form a complete weakened water holding capacity interval. Taking the specific experiment as an example, in strawberry soil, the average attenuation of capillary force in the depth range of 6 cm to 12 cm is 0.018, 0.021, 0.019, and 0.016 respectively. After judgment, the 6 cm to 12 cm layer is classified as a weakened water holding capacity interval. The final output of the weakened interval data of soil water holding capacity fully records the start and end depths and attenuation amplitude information of each interval.

[0052] The present invention also provides an agricultural product planting environment detection system, which is used to execute the agricultural product planting environment detection method as described above, and the agricultural product planting environment detection system comprises: The pH fluctuation analysis module is used to monitor the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; perform pH fluctuation analysis on the strawberry soil state monitoring data to obtain strawberry soil pH fluctuation data; The module for stunting simulation and evolution is used to obtain the morphological data of strawberry plants; evaluate the root extension state of strawberry plant morphological data to obtain the root extension state of strawberry; quantify the decomposition and decay of vertical permeable organic matter in the soil layer based on the pH fluctuation data of strawberry soil layer to obtain the decomposition and decay data of vertical permeable organic matter; simulate the evolution of acid stunting of strawberry root extension state based on the decomposition and decay data of vertical permeable organic matter to obtain the acid stunting evolution data of strawberry root system; The nutrient uptake efficiency constraint analysis module is used to perform an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; simulate and evaluate the absorption and loss of trace elements in the soil layer on the extension state of the strawberry root system based on the over-alkali fluctuation index of the soil layer to obtain the absorption and loss data of trace elements in the over-alkali soil layer; perform a nutrient uptake efficiency constraint regression analysis on the extension state of the strawberry root system based on the absorption and loss data of trace elements in the over-alkali soil layer to obtain the nutrient uptake efficiency constraint regression data; The planting environment detection model construction module is used to construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint regression data to obtain an automated planting environment detection model; the automated planting environment detection model is sent to the cloud platform to perform agricultural product planting environment detection.

[0053] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may 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 the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for detecting an agricultural product planting environment, characterized in that: The following steps are involved: Step S1: monitoring the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; The pH fluctuation analysis of strawberry soil layer status monitoring data was performed to obtain the pH fluctuation data of strawberry soil layer; 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 decomposition and decay data of vertical permeable organic matter; Based on the vertical infiltration organic matter decomposition and decay data, the acid stunting evolution of strawberry root extension state was simulated, and the acid stunting evolution data of strawberry root system was obtained. Step S3: performing an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; performing a soil trace element absorption loss simulation assessment on the strawberry root extension state based on the soil over-alkali fluctuation index to obtain over-alkali soil trace element absorption loss data; performing a nutrient uptake efficiency constraint regression analysis on the strawberry root extension state based on the over-alkali soil trace element absorption loss data to obtain nutrient uptake efficiency constraint regression data; Step S4: construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint 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.

2. The method for detecting the agricultural product planting environment according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: monitoring the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; Step S12: performing data cleaning on the strawberry soil layer status monitoring data to obtain strawberry soil layer status monitoring cleaning data; Step S13: performing pH fluctuation analysis on the strawberry soil layer status monitoring and cleaning data to obtain pH fluctuation data of the strawberry soil layer.

3. The method for detecting the agricultural product planting environment according to claim 1, characterized in that: Step S2 includes the following steps: 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; 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; Step S23: quantifying the decomposition and decay of vertical permeable organic matter in the soil layer based on the soil layer acidity time series variation intensity data to obtain vertical permeable organic matter decomposition and decay data; Step S24: performing decay rate self-similar structure analysis on the vertical infiltration organic matter decomposition decay data to obtain organic matter vertical decomposition decay self-similar data; 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; 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.

4. The method for detecting the agricultural product planting environment according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: performing spatial interpolation of soil layer vertical cross-section acidity on soil layer acidity time series variation intensity data to obtain vertical cross-section acidity interpolation data; Step S232: fitting the inverse decay relationship of the bacterial community according to the vertical section acidity interpolation data to obtain the inverse decay relationship data of the bacterial community; Step S233: simulate and infer the difference in decay rate of relative abundance of bacterial communities on the inverse decay relationship data of bacterial communities to obtain the difference in decay rate of relative abundance of bacterial communities; Step S234: performing enzyme configuration evolution catalytic efficiency weakening fitting based on the inverse decay relationship data of bacterial communities and the relative abundance decay rate difference of bacterial communities to obtain enzyme configuration evolution catalytic efficiency weakening data; Step S235: quantify the decomposition and decay of vertical infiltration organic matter in the soil layer according to the enzyme configuration evolution catalytic efficiency weakening data, the relative abundance decay rate difference of the bacterial community and the inverse decay relationship data of the bacterial community, and obtain the vertical infiltration organic matter decomposition and decay data.

5. The method for detecting the agricultural product planting environment according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: performing multi-level frequency domain decomposition processing on the organic matter vertical decomposition decay self-similar data to obtain multi-layer spectrum decomposition decay intensity data; Step S252: analyzing the soil nitrification inhibition index based on the multi-layer spectrum decomposition decay intensity data to obtain the soil nitrification inhibition index; Step S253: Calculating the nitrogen release reduction index according to the multi-layer spectrum decomposition decay intensity data and the soil nitrification inhibition index to obtain the nitrogen release reduction index; Step S254: fitting the nitrogen conversion magnitude loss according to the nitrogen release reduction index to obtain nitrogen conversion magnitude loss data.

6. The method for detecting the agricultural product planting environment according to claim 5, characterized in that: Step S253 includes the following steps: Drawing a multi-layer decay intensity fluctuation curve on the multi-layer spectrum decomposition decay intensity data to obtain a multi-layer decay intensity fluctuation curve; 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; Based on the multi-layer single-point attenuation mutation entropy value, the nonlinear mineralization rate attenuation interval of nitrogen element is deduced, and the nonlinear mineralization rate attenuation interval is obtained; The soil nitrification inhibition index is used to evaluate the reduction of nitrifying microbial activity, and the reduction of nitrifying microbial activity data is obtained; The nitrogen release reduction index was calculated based on the nonlinear mineralization rate attenuation interval and the nitrifying microbial activity reduction data to obtain the nitrogen release reduction index.

7. The method for detecting the agricultural product planting environment according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing an alkalinity fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain an alkalinity fluctuation index of the soil layer; Step S32: simulating and evaluating the absorption and loss of trace elements in the soil layer based on the soil alkalinity fluctuation index of the strawberry root extension state to obtain the absorption and loss data of trace elements in the alkaline soil layer; Step S33: Calculating the weakening interval of soil water holding capacity according to the soil alkali fluctuation index to obtain the weakening interval of soil water holding capacity; Step S34: performing nutrient uptake efficiency constraint regression analysis on the strawberry root extension state according to the trace element absorption loss data of the over-alkaline soil layer and the weakened water holding capacity interval of the soil layer to obtain nutrient uptake efficiency constraint regression data.

8. The method for detecting the agricultural product planting environment according to claim 7, characterized in that: Step S32 includes the following steps: Step S321: performing equal-interval discrete difference processing on the soil layer over-alkali fluctuation index to obtain an over-alkali disturbance amplitude variation sequence; Step S322: performing disordered differential processing of the decrease in the effective state content of soil trace elements based on the over-alkalinity disturbance amplitude change sequence to obtain disordered data of the decrease in the effective state content of trace elements; Step S323: performing inflection point decrease continuity rate analysis on the disordered data of effective state content decrease to obtain the content decrease inflection point continuity rate; Step S324: Based on the disordered data of the decrease in effective content and the continuity rate of the inflection point of the content decrease, the strawberry root extension state is simulated and evaluated for the absorption loss of trace elements in the soil layer to obtain the absorption loss data of trace elements in the over-alkaline soil layer.

9. The method for detecting the agricultural product planting environment according to claim 7, characterized in that: Step S33 includes the following steps: Step S331: simulating the discrete deformation of the soil layer according to the soil layer alkali fluctuation index to obtain soil discrete deformation data; Step S332: performing soil pore structure enlargement mapping based on the soil discrete deformation data to obtain soil pore structure enlargement mapping data; Step S333: quantifying the anisotropic attenuation of soil capillary force according to the soil pore structure enlargement mapping data to obtain the anisotropic attenuation data of capillary force; Step S334: Calculate the weakening interval of soil layer water holding capacity according to the capillary force anisotropic attenuation data to obtain the weakening interval of soil layer water holding capacity.

10. A system for detecting an agricultural product planting environment, characterized in that: Used to execute the agricultural product planting environment detection method as claimed in claim 1, the agricultural product planting environment detection system comprises: The pH fluctuation analysis module is used to monitor the soil state of the strawberry planting area through a soil monitoring sensor to obtain strawberry soil state monitoring data; perform pH fluctuation analysis on the strawberry soil state monitoring data to obtain strawberry soil pH fluctuation data; The module for stunting simulation and evolution is used to obtain the morphological data of strawberry plants; evaluate the root extension state of strawberry plant morphological data to obtain the root extension state of strawberry; quantify the decomposition and decay of vertical permeable organic matter in the soil layer based on the pH fluctuation data of strawberry soil layer to obtain the decomposition and decay data of vertical permeable organic matter; simulate the evolution of acid stunting of strawberry root extension state based on the decomposition and decay data of vertical permeable organic matter to obtain the acid stunting evolution data of strawberry root system; The nutrient uptake efficiency constraint analysis module is used to perform an over-alkali fluctuation index analysis on the pH fluctuation data of the strawberry soil layer to obtain the over-alkali fluctuation index of the soil layer; simulate and evaluate the absorption and loss of trace elements in the soil layer on the extension state of the strawberry root system based on the over-alkali fluctuation index of the soil layer to obtain the absorption and loss data of trace elements in the over-alkali soil layer; perform a nutrient uptake efficiency constraint regression analysis on the extension state of the strawberry root system based on the absorption and loss data of trace elements in the over-alkali soil layer to obtain the nutrient uptake efficiency constraint regression data; The planting environment detection model construction module is used to construct an automated planting environment detection model based on the strawberry root acid stunted development evolution data and nutrient uptake efficiency constraint regression data to obtain an automated planting environment detection model; the automated planting environment detection model is sent to the cloud platform to perform agricultural product planting environment detection.

Images