Intelligent planting management method and system for Huai apples

Abstract

The invention relates to the technical field of agriculture, in particular to an intelligent planting management method and system for Huai apples, and the method comprises the following steps: S1, monitoring soil environment parameters around roots in real time; s2, evaluating the health state of the root system based on the data collected in the S1; s3, adjusting irrigation and fertilization parameters according to the root health score obtained in S2; s4, configuring an unmanned aerial vehicle to execute a regular flight task, and collecting growth state images of the Huai apple trees; s5, comprehensively analyzing the image data collected in the step S4 and the root system health score data in the step S2; and S6, automatically generating a planting management report and an adjustment suggestion based on an analysis result of S5. According to the invention, by integrating environment monitoring, unmanned aerial vehicle imaging and machine learning analysis technologies, real-time and accurate planting management suggestions are provided, so that the growth quality and yield of the Huai apples are significantly improved, resource use is optimized, and the efficiency and sustainability of agricultural production are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to an intelligent planting management method and system for Huaniu apples. Background Art

[0002] In modern agricultural production, Huaniu apples are loved by consumers for their excellent taste and nutritional value. However, traditional Huaniu apple planting and management mostly rely on manual observation and empirical judgment. This method faces significant challenges in accuracy and efficiency, especially in large-scale planting. How to monitor and accurately control the growth environment of each apple tree in real time, such as soil moisture, temperature and nutrient status, becomes the key to improving production efficiency and fruit quality. In addition, traditional methods make it difficult to detect and respond to subtle changes in the growth environment in a timely manner, which may lead to plant diseases and growth problems, thus affecting overall yield and quality.

[0003] In response to these problems, the present invention aims to solve the problems of insufficient accuracy and low efficiency in the existing technology in the planting and management of Huaniu apples. The existing technology lacks a system that can comprehensively monitor the plant surface and root environment and realize data-driven decision-making, which limits the real-time adjustment and optimization of planting conditions.

[0004] Therefore, it is particularly necessary to develop an intelligent planting management system that integrates environmental monitoring, data analysis, and management suggestion output. Summary of the invention

[0005] Based on the above objectives, the present invention provides an intelligent planting management method and system for Huaniu apples.

[0006] An intelligent planting management method for Huaniu apples, comprising the following steps:

[0007] S1: Deploy micro underground sensors in the Huaniu apple tree planting area to monitor the soil environmental parameters around the roots in real time, including soil moisture, temperature, conductivity and nutrient content;

[0008] S2: using a preset root health analysis model to evaluate the root health status based on the data collected in S1 and generate a root health score;

[0009] S3: According to the root health score obtained in S2, adjust the parameters of irrigation and fertilization, including adjusting the amount and frequency of water and nutrient supply;

[0010] S4: Configure drones to perform regular flight missions, using infrared and multispectral imaging technology to collect growth status images of Huaniu apple trees, including leaf color and growth status data;

[0011] S5: Comprehensively analyze the image data collected by S4 and the root health score data of S2, and determine the relationship between the plant surface condition and root health through a preset plant growth analysis model;

[0012] S6: Based on the analysis results of S5, it automatically generates planting management reports and adjustment suggestions.

[0013] Optionally, the S1 specifically includes:

[0014] S11: deploy micro underground sensors around the main root of each Huaniu apple tree in a predetermined pattern, with four sensors deployed on each tree to form a square layout; the sensors include humidity sensors, temperature sensors, conductivity sensors, and nutrient content sensors;

[0015] S12: Monitor the moisture content in the soil through a humidity sensor. The humidity sensor uses a capacitive principle to measure the change in the dielectric constant in the soil and obtain soil moisture data in real time;

[0016] S13: Monitor the temperature change of the soil through a temperature sensor. The temperature sensor adopts the principle of thermistor and uses the characteristic that resistance changes with temperature to obtain soil temperature data in real time.

[0017] S14: The conductivity of the soil is monitored by a conductivity sensor. The conductivity sensor adopts a four-electrode method to obtain soil conductivity data in real time by measuring the conductivity of current in the soil.

[0018] S15: Monitor the nutrient concentration in the soil through the nutrient sensor. The nutrient sensor uses the principle of ion selective electrode to measure the ion concentration in the soil solution and obtain the data of nitrogen, phosphorus and potassium nutrients in the soil in real time.

[0019] Optionally, the S2 specifically includes:

[0020] S21: collects soil environmental parameter data collected by the sensors in S1, including soil moisture, temperature, conductivity and nutrient concentration, and transmits the data to the central processing unit;

[0021] S22: constructing a root health analysis model in the central processing unit, wherein the root health analysis model is trained based on a support vector machine algorithm, wherein an input parameter of the root health analysis model is soil environment data, and an output is a root health score;

[0022] S23: pre-process the real-time data collected by S21, including data cleaning, normalization and outlier detection, to ensure that the data quality meets the input requirements of the root health analysis model;

[0023] S24: input the preprocessed data into the root health analysis model constructed in S22, comprehensively evaluate the health status of the root system according to the input soil moisture, temperature, electrical conductivity and nutrient concentration, and generate a root health score;

[0024] S25: Generate a root health score based on the calculation result of S24, the score range is from 0 to 100, and the higher the score, the better the root health status.

[0025] Optionally, the S22 includes:

[0026] S221: Collect a large amount of historical data, including soil moisture, temperature, conductivity and nutrient concentration in different planting areas, as well as corresponding root health records, as input data for model training;

[0027] S222: preprocessing the collected historical data, including data cleaning, normalization and outlier detection;

[0028] S223: Divide the preprocessed data set into a training set and a test set, specifically using an 80:20 ratio of data division, where 80% is used for training and 20% is used for testing;

[0029] S224: Use the support vector machine algorithm to train the model, define the input feature vector as x = x1, x2, x3, x4], where x1, x2, x3, x4 represent soil moisture, temperature, conductivity and nutrient concentration respectively, and the output is the root health score y; the optimization goal of the support vector machine is to find an optimal hyperplane to maximize the interval from the feature vector to the hyperplane. The optimization problem is expressed as: Among them, w is the normal vector of the hyperplane, b is the bias term; the constraints are: Among them, y i is the root health score of the training sample, x i is the corresponding input feature vector, ξ i is the slack variable;

[0030] S225: Use radial basis kernel function for nonlinear mapping. The radial basis kernel function is defined as: K(x i ,x j )=exp(-γ||x i -x j || 2 ), where γ is the parameter of the kernel function, x i and x j are the input feature vectors of different samples respectively;

[0031] S226: Using the training set data, the model parameters w and b are iteratively optimized by the gradient descent method until the loss function converges. The loss function is defined as: Among them, L is the loss function, C is the regularization parameter, n is the number of training samples, ξ i is the slack variable;

[0032] S227: The root health analysis model expression after construction is:

[0033] Where f(x) is the root health score prediction value of the input feature vector x, α i is the Lagrange multiplier, y i is the actual root health score of the training sample, K(x i ,x) is the radial basis kernel function, x i is the support vector and b is the bias term.

[0034] Optionally, the S3 specifically includes:

[0035] S31: According to the root health score, the score is divided into three intervals, namely 0-40 for low health status, 41-70 for medium health status, and 71-100 for high health status;

[0036] S32: Adjust irrigation and fertilization parameters according to the interval to which the root health score belongs;

[0037] S33: Adjust irrigation parameters and calculate the water requirement of each Huaniu apple tree. Assuming the water requirement is W, the formula is: Among them, W base is the basic water requirement, y is the root health score; according to the water requirement W, adjust the irrigation frequency F, and the irrigation frequency formula is: Among them, F base The basic irrigation frequency;

[0038] S34: Adjust the fertilization parameters and calculate the fertilizer requirement of each Huaniu apple tree. Assuming the fertilizer requirement is N, the formula is: Among them, N base is the basic fertilizer requirement, y is the root health score; according to the fertilizer requirement N, adjust the fertilization frequency G, and the fertilization frequency formula is: Among them, G base The frequency of basal fertilization;

[0039] S35: Input the adjusted irrigation and fertilization parameters into the automatic control system, and automatically perform irrigation and fertilization operations according to the parameters.

[0040] Optionally, the S4 specifically includes:

[0041] S41: Select and configure drones suitable for agricultural monitoring, and ensure that the drones are equipped with infrared imaging equipment and multispectral imaging equipment. The infrared imaging equipment is used to detect temperature distribution, and the multispectral imaging equipment is used to detect the spectral reflectance characteristics of plants.

[0042] S42: Set the flight route and altitude of the drone to ensure coverage of the entire Huaniu apple planting area. The flight route planning needs to take terrain and obstacles into consideration, and the flight altitude needs to be kept stable to ensure the consistency and accuracy of the image data.

[0043] S43: Set up a regular flight plan for the drone, determine the frequency and time of the flight, usually conduct flight monitoring once a week to obtain regular growth data;

[0044] S44: In each flight mission, the drone flies according to the preset route and altitude, and simultaneously activates the infrared imaging device and the multi-spectral imaging device to collect data. The infrared imaging device captures the temperature distribution of the Huaniu apple tree and records the temperature changes;

[0045] S45: The multispectral imaging device collects multispectral image data of Huaniu apple trees and monitors the leaf color and spectral reflectance characteristics of the plants, including the reflectance of blue, green, red and near-infrared light;

[0046] S46: The collected infrared image and multispectral image data are transmitted to the central processing unit in real time through the wireless communication module; in the central processing unit, the infrared image data is processed, the temperature distribution is analyzed, potential abnormal areas are identified, and it is determined whether the plant has temperature abnormalities;

[0047] S47: Process the multispectral image data, calculate the vegetation index by analyzing the reflectance of each band, and evaluate the growth health and leaf color changes of Huaniu apple trees;

[0048] S48: Compare the processed image data with previous historical data to generate a growth status report, which includes information on leaf color changes, temperature distribution, and vegetation index.

[0049] Optionally, the S5 specifically includes:

[0050] S51: receiving the infrared image data and the multispectral image data transmitted to the central processing unit in S4, and the root health score data generated in S2;

[0051] S52: preprocessing the infrared image data and the multispectral image data, including denoising, correction and normalization;

[0052] S53: Based on the random forest algorithm, a plant growth analysis model was constructed to comprehensively analyze the plant surface condition and root health data;

[0053] S54: Extract infrared image features, including temperature distribution pattern and temperature anomaly ratio, and extract multispectral image features, including reflectance of each band and normalized vegetation index;

[0054] S55: fusing the extracted image features with the root health score data as input to the plant growth analysis model;

[0055] S56: Using the trained plant growth analysis model, analyze the data fused in S55 to determine whether the surface condition of the plant is consistent with the health status of the root;

[0056] S57: Generate a comprehensive analysis report, including the comparison results of plant surface condition and root health score, the correlation between leaf color change and root nutrition status, and the correspondence between abnormal temperature areas and root health problems.

[0057] Optionally, the S53 includes:

[0058] S531: Collect data sets for model training, including the root health score data obtained from S2 and the infrared image features and multispectral image features extracted from S4;

[0059] S532: Perform data preprocessing, including missing value processing, data normalization, and feature selection to optimize the training data set;

[0060] S533: Initialize the random forest algorithm, set the number of trees, specifically 100 to 500 trees, and set the depth of the decision tree, including the number of samples of the minimum split node and the maximum number of features, to control the complexity of the model and prevent overfitting;

[0061] S534: Use the random forest algorithm to train a plant growth analysis model. Random forest improves prediction accuracy by constructing multiple decision trees and averaging or majority voting their predictions, where each tree is trained on a different random subsample of the dataset and the segmentation features are also selected from a random subset of features.

[0062] S535: During the training process, each decision tree selects the features and split points for splitting based on optimizing information gain, thereby splitting the data set at each node until a preset tree depth is reached or the amount of data in the node is lower than a threshold;

[0063] S536: When all decision trees are built, the random forest model will make a final prediction by integrating the prediction results of all trees; specifically for regression problems, the result is the average of all tree predictions; for classification problems, the result is the category with the most votes;

[0064] S537: After model training is completed, model validation is performed, using cross-validation or retaining a portion of the data as a test set to evaluate the model's predictive performance and generalization ability;

[0065] S538: The expression of the plant growth analysis model after construction is: Among them, f(x) represents the output of the model, x represents the input feature vector, N is the number of decision trees, and f i (x) represents the prediction result of the i-th tree.

[0066] Optionally, the S6 specifically includes:

[0067] S61: receiving the comprehensive analysis report generated in S5, and based on the comprehensive analysis report, comparing the current data with the historical data, identifying abnormal situations or trend changes, and extracting influencing factors;

[0068] S62: Generate a planting management report, including a historical trend chart of root health scores, analysis results of infrared images and multispectral images, annotated abnormal area charts, and a comprehensive plant health score;

[0069] S63: Based on the comprehensive analysis report, generate adjustment suggestions, including irrigation suggestions, fertilization suggestions, pest and disease control suggestions, and environmental adjustment suggestions;

[0070] S65: The planting management report and adjustment suggestions are presented to the grower through a user interface, which includes charts, text descriptions and specific operation suggestions.

[0071] An intelligent planting management system for Huaniu apples, used to implement the above-mentioned intelligent planting management method for Huaniu apples, includes the following modules:

[0072] Environmental monitoring module: used to monitor soil environmental parameters in the Huaniu apple planting area in real time, including soil moisture, temperature, conductivity and nutrient content;

[0073] Data processing module: connected to the environmental monitoring module, receiving data from the environmental monitoring module, and analyzing the data using the root health analysis model to generate a root health score;

[0074] UAV monitoring module: used to perform regular flight missions to collect images of the growth status of Huaniu apple trees, including infrared and multispectral images;

[0075] Comprehensive analysis module: connected with the data processing module and the drone monitoring module, receiving the root health score from the data processing module and the image data from the drone monitoring module, using the plant growth analysis model to comprehensively analyze the relationship between the plant surface condition and root health, and generate a comprehensive analysis report;

[0076] Management suggestion generation module: connected with the comprehensive analysis module, it generates specific planting management reports and adjustment suggestions based on the comprehensive analysis report, including irrigation, fertilization, pest control and environmental adjustment suggestions;

[0077] User interface module: connected to the management suggestion generation module, providing a graphical interface for growers to view planting management reports and implement adjustment suggestions.

[0078] Beneficial effects of the present invention:

[0079] The present invention realizes efficient management of Huaniu apple planting by comprehensively utilizing environmental monitoring technology, drone imaging and advanced data analysis technology. By deploying various types of sensors directly in the planting area of ​​Huaniu apples, the method can monitor key indicators such as soil moisture, temperature, conductivity and nutrients in real time. In addition, by utilizing infrared and multi-spectral imaging equipment carried by drones, the method can accurately capture the growth status and health status of the plants and monitor the overall growth of the plants from the air.

[0080] The present invention, by inputting the collected data into a data processing system based on a machine learning model, can comprehensively analyze soil conditions and plant growth data, and accurately determine the relationship between root health and plant surface conditions. This comprehensive analysis enables the planting management method to not only improve the efficiency of monitoring the health of plants, but also greatly improve the accuracy of processing data. Based on these analysis results, the method can provide specific planting management suggestions in a timely manner, such as adjusting irrigation and fertilization plans, and effectively preventing diseases and insect pests, thereby significantly improving the growth quality and yield of Huaniu apples, optimizing the use of resources, and promoting the sustainable development of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0082] Figure 1 A schematic diagram of an intelligent planting management method according to an embodiment of the present invention;

[0083] Figure 2Schematic diagram of an intelligent planting management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0084] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0085] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0086] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0087] like Figure 1 As shown, an intelligent planting management method for Huaniu apples includes the following steps:

[0088] S1: Deploy micro underground sensors in the Huaniu apple tree planting area to monitor the soil environmental parameters around the roots in real time, including soil moisture, temperature, conductivity and nutrient content;

[0089] S2: using a preset root health analysis model to evaluate the root health status based on the data collected in S1 and generate a root health score;

[0090] S3: According to the root health score obtained in S2, adjust the parameters of irrigation and fertilization to optimize the root growth environment, including adjusting the amount and frequency of water and nutrient supply;

[0091] S4: Configure drones to perform regular flight missions, using infrared and multispectral imaging technology to collect growth status images of Huaniu apple trees, including leaf color and growth status data;

[0092] S5: Comprehensively analyze the image data collected by S4 and the root health score data of S2, and determine the relationship between the plant surface condition and root health through a preset plant growth analysis model;

[0093] S6: Based on the analysis results of S5, it automatically generates planting management reports and adjustment suggestions to optimize the planting conditions of Huaniu apples and improve the overall health and production efficiency of the plants.

[0094] S1 specifically includes:

[0095] S11: Deploy micro underground sensors around the taproot of each Huaniu apple tree in a predetermined pattern, with four sensors deployed per tree to form a square layout to ensure all-round monitoring of soil conditions; the sensors include humidity sensors, temperature sensors, conductivity sensors, and nutrient content sensors;

[0096] S12: Monitor the moisture content in the soil through a humidity sensor. The humidity sensor uses a capacitive principle to measure the change in the dielectric constant in the soil and obtain soil moisture data in real time;

[0097] S13: Monitor the temperature change of the soil through a temperature sensor. The temperature sensor adopts the principle of thermistor and uses the characteristic that resistance changes with temperature to obtain soil temperature data in real time.

[0098] S14: The conductivity of the soil is monitored by a conductivity sensor. The conductivity sensor adopts a four-electrode method to obtain soil conductivity data in real time by measuring the conductivity of current in the soil.

[0099] S15: Monitor the nutrient concentration in the soil through nutrient sensors. The nutrient sensors use the principle of ion-selective electrodes to measure the ion concentration in the soil solution and obtain real-time data on nitrogen, phosphorus and potassium nutrients in the soil for use in subsequent steps. Through the above steps, real-time monitoring of soil environmental parameters around the roots is achieved in the planting area of ​​Huaniu apple trees. Different micro-underground sensors are used in combination with capacitive, thermistor, four-electrode method and ion-selective electrode technologies to accurately obtain soil moisture, temperature, conductivity and nutrient data, which provides a scientific basis for the precise management of the root health of Huaniu apple trees and improves the scientificity and effectiveness of planting management.

[0100] The root health analysis model in S2 specifically includes:

[0101] S21: collects soil environmental parameter data collected by the sensors in S1, including soil moisture, temperature, conductivity and nutrient concentration, and transmits the data to the central processing unit;

[0102] S22: constructing a root health analysis model in the central processing unit, wherein the root health analysis model is trained based on a support vector machine (SVM) algorithm, wherein an input parameter of the root health analysis model is soil environment data, and an output is a root health score; the root health analysis model uses the support vector machine algorithm to learn a large amount of historical data to determine the relationship between soil parameters and root health status;

[0103] S23: pre-process the real-time data collected by S21, including data cleaning, normalization and outlier detection, to ensure that the data quality meets the input requirements of the root health analysis model;

[0104] S24: input the preprocessed data into the root health analysis model constructed in S22, comprehensively evaluate the health status of the root system according to the input soil moisture, temperature, electrical conductivity and nutrient concentration, and generate a root health score;

[0105] S25: Based on the calculation results of S24, a root health score is generated, ranging from 0 to 100, and the higher the score, the better the root health. Through the above steps, the root health analysis model constructed using the support vector machine algorithm realizes real-time root health assessment based on soil environmental parameters. The model can accurately analyze and predict the health of the root system, providing growers with a scientific and intuitive root health management tool. In addition, the root health score of the model's output results provides data support for growers to formulate irrigation and fertilization strategies, which helps to optimize the root growth environment and thereby improve the overall growth health and yield of Huaniu apples.

[0106] The steps of constructing a root health analysis model using the support vector machine algorithm in S22 include:

[0107] S221: Collect a large amount of historical data, including soil moisture, temperature, conductivity and nutrient concentration in different planting areas, as well as corresponding root health records, as input data for model training;

[0108] S222: preprocessing the collected historical data, including data cleaning, normalization processing and outlier detection. The normalization processing adopts the minimum-maximum scaling method to scale all data to the [0,1] interval;

[0109] S223: Divide the preprocessed data set into a training set and a test set, specifically using an 80:20 ratio of data division, where 80% is used for training and 20% is used for testing;

[0110] S224: Use the support vector machine (SVM) algorithm to train the model. Define the input feature vector as x = [x1, x2, x3, x4], where x1, x2, x3, x4 represent soil moisture, temperature, conductivity and nutrient concentration respectively, and the output is the root health score y; the optimization goal of the support vector machine is to find an optimal hyperplane to maximize the interval from the feature vector to the hyperplane. The optimization problem is expressed as: Among them, w is the normal vector of the hyperplane, b is the bias term; the constraints are: Among them, y i is the root health score of the training sample, x i is the corresponding input feature vector, ξ i is a slack variable used to handle nonlinear separable situations;

[0111] S225: Use radial basis kernel function (RBF) for nonlinear mapping to improve the classification ability of the model. The radial basis kernel function is defined as: K(x i ,x j )=exp(-γ||x i -x j || 2 ), where γ is the parameter of the kernel function, which is used to control the width of the Gaussian distribution, and x i and x j are the input feature vectors of different samples respectively;

[0112] S226: Using the training set data, the model parameters w and b are iteratively optimized by the gradient descent method until the loss function converges. The loss function is defined as: Among them, L is the loss function, C is the regularization parameter used to balance the relationship between maximizing the interval and minimizing the error, n is the number of training samples, ξ i is the slack variable;

[0113] S227: The root health analysis model expression after construction is:

[0114] Where f(x) is the root health score prediction value of the input feature vector x, α i is the Lagrange multiplier, y i is the actual root health score of the training sample, K(x i ,x) is the radial basis kernel function, x i is the support vector, b is the bias term;

[0115] Through the above steps, an accurate root health analysis model was constructed using the support vector machine algorithm. Through training with a large amount of historical data, the model can effectively analyze and predict the health of the root system and provide a quantitative root health score. The radial basis kernel function is used for nonlinear mapping to improve the classification ability of the model. The accuracy and generalization ability of the model have been verified, and it can provide growers with a scientific root health management tool, which helps to optimize the root growth environment and improve the overall growth health and yield of Huaniu apples.

[0116] S3 specifically includes:

[0117] S31: According to the root health score, the score is divided into three intervals, namely 0-40 for low health status, 41-70 for medium health status, and 71-100 for high health status;

[0118] S32: Adjust irrigation and fertilization parameters according to the interval to which the root health score belongs;

[0119] If the score is between 0-40, it means that the root system is in a low health state and needs to increase the supply of water and nutrients, as well as the frequency of supply;

[0120] If the score is between 41-70, it means that the root system is in a moderately healthy state. Maintain the current supply of water and nutrients and adjust the supply frequency appropriately;

[0121] If the score is between 71-100, it means that the root system is in a high health state, and the amount of water and nutrients supplied can be appropriately reduced, and the supply frequency can be reduced;

[0122] S33: Adjust irrigation parameters and calculate the water requirement of each Huaniu apple tree. Assuming the water requirement is W, the formula is: Among them, W base is the basic water requirement, y is the root health score; according to the water requirement W, adjust the irrigation frequency F, and the irrigation frequency formula is: Among them, F base The basic irrigation frequency;

[0123] S34: Adjust the fertilization parameters and calculate the fertilizer requirement of each Huaniu apple tree. Assuming the fertilizer requirement is N, the formula is: Among them, N base is the basic fertilizer requirement, y is the root health score; according to the fertilizer requirement N, adjust the fertilization frequency G, and the fertilization frequency formula is: Among them, G base The frequency of basal fertilization;

[0124] S35: Input the adjusted irrigation and fertilization parameters into the automatic control system, and automatically perform irrigation and fertilization operations according to the parameters to ensure that the root environment is optimized. Through the above steps, the irrigation and fertilization parameters are dynamically adjusted according to the root health score, and a clear calculation formula is used to determine the supply amount and frequency of water and nutrients, so that each Huaniu apple tree can obtain a suitable growth environment. By precisely controlling the irrigation and fertilization operations, the water and fertilizer utilization efficiency is improved, the root growth environment is optimized, and the overall health and yield of Huaniu apples are improved.

[0125] S4 specifically includes:

[0126] S41: Select and configure drones suitable for agricultural monitoring, and ensure that the drones are equipped with infrared imaging equipment and multispectral imaging equipment. The infrared imaging equipment is used to detect temperature distribution, and the multispectral imaging equipment is used to detect the spectral reflectance characteristics of plants.

[0127] S42: Set the flight route and altitude of the drone to ensure coverage of the entire Huaniu apple planting area. The flight route planning needs to take terrain and obstacles into consideration, and the flight altitude needs to be kept stable to ensure the consistency and accuracy of the image data.

[0128] S43: Set up a regular flight plan for the drone, determine the frequency and time of the flight, usually conduct flight monitoring once a week to obtain regular growth data;

[0129] S44: In each flight mission, the drone flies according to the preset route and altitude, and simultaneously activates the infrared imaging device and the multi-spectral imaging device to collect data. The infrared imaging device captures the temperature distribution of the Huaniu apple tree and records the temperature changes;

[0130] S45: The multispectral imaging device collects multispectral image data of Huaniu apple trees and monitors the leaf color and spectral reflectance characteristics of the plants, including the reflectance of blue, green, red and near-infrared light;

[0131] S46: The collected infrared image and multispectral image data are transmitted to the central processing unit in real time through the wireless communication module; in the central processing unit, the infrared image data is processed, the temperature distribution is analyzed, potential abnormal areas are identified, and it is determined whether the plant has temperature abnormalities;

[0132] The specific steps include:

[0133] S461: Setting the temperature threshold range T min and T max , based on historical data and experimental results, determine the temperature range of Huaniu apple trees under normal growth conditions;

[0134] S462: Compare the temperature of each pixel in the infrared image data with the temperature threshold range and calculate the temperature anomaly index T anomaly , the formula is:

[0135] Where T is the temperature of a pixel in the infrared image, T anomaly is the temperature anomaly index, 1 indicates abnormal temperature, and 0 indicates normal temperature;

[0136] S463: Summarize the temperature anomaly index of all pixels and calculate the overall temperature anomaly ratio P anomaly , the formula is: Where N is the total number of pixels in the infrared image, ΣT anomaly is the sum of all temperature anomaly indices;

[0137] S464: If the overall temperature abnormality ratio P anomaly Exceeding the preset warning value P threshold , it is judged that the temperature of the Huaniu apple tree is abnormal and further investigation and treatment are needed.

[0138] S47: Process the multispectral image data, calculate the vegetation index (such as NDVI) by analyzing the reflectance of each band, and evaluate the growth health and leaf color changes of Huaniu apple trees;

[0139] The specific steps include:

[0140] S471: Collect multispectral image data transmitted by drones and pre-process the images, including denoising and correction, to ensure data accuracy;

[0141] S472: Analyze the reflectance of each band in the multispectral image, including blue light R blue , Green Light R green , Red light R red and near infrared light R nir Reflectivity;

[0142] S473: Calculate the Normalized Difference Vegetation Index (NDVI), the formula is: Among them, R nir is the near-infrared light reflectivity, R red The NDVI is the red light reflectance, and its value range is between -1 and 1. The larger the value, the better the vegetation health.

[0143] S474: Set a NDVI health threshold range NDVI min and NDVI max , based on historical data and experimental results, the NDVI range of Huaniu apple trees under normal growth conditions was determined;

[0144] S475: Compare the calculated NDVI value with the health threshold range. If the NDVI value is within the NDVI min and NDVI max If the NDVI value is lower than NDVI, the growth and health of the Huaniu apple tree is good. min or above NDVI max , further investigation and adjustment are needed;

[0145] S476: Analyze the changes in reflectance of each band, evaluate the changes in leaf color, and calculate the content of plant pigments, such as chlorophyll and carotenoids, by comparing the reflectance of blue, green and red light to determine the health of the leaves.

[0146] S48: Compare the processed image data with previous historical data to generate a growth status report, which includes information on leaf color changes, temperature distribution and vegetation index, providing a basis for subsequent management decisions. Through the above steps, drones equipped with infrared imaging equipment and multispectral imaging equipment are used to regularly perform flight missions to collect growth status image data of Huaniu apple trees. By analyzing infrared images and multispectral images, the leaf color and temperature distribution of plants can be accurately monitored, and the growth health status can be evaluated. This method provides comprehensive and real-time growth data, which helps to detect abnormalities in a timely manner, optimize planting management, and improve the overall growth health and yield of Huaniu apples.

[0147] S5 specifically includes:

[0148] S51: receiving the infrared image data and the multispectral image data transmitted to the central processing unit in S4, and the root health score data generated in S2;

[0149] S52: Preprocessing of infrared image data and multispectral image data, including denoising, correction and normalization, to ensure data quality and consistency;

[0150] S53: Based on the random forest algorithm, a plant growth analysis model is constructed to comprehensively analyze the plant surface condition and root health data. The input of the plant growth analysis model includes infrared image features, multispectral image features and root health score;

[0151] S54: Extract infrared image features, including temperature distribution pattern and temperature anomaly ratio, and extract multispectral image features, including reflectance of each band and normalized difference vegetation index (NDVI);

[0152] S55: The extracted image features are integrated with the root health score data as input to the plant growth analysis model. The model can identify the relationship between the plant surface condition and the root health through learning and training;

[0153] S56: Using the trained plant growth analysis model, analyze the data fused in S55 to determine whether the plant surface conditions (such as leaf color changes and temperature distribution) are consistent with the root health status (such as root health score);

[0154] S57: Generate a comprehensive analysis report, including the comparison results of plant surface condition and root health score, the correlation between leaf color change and root nutritional status, and the correspondence between abnormal temperature areas and root health problems; through the above steps, the infrared and multispectral image data are comprehensively analyzed with the root health score data, and the plant growth analysis model constructed by the random forest algorithm is used to accurately judge the relationship between the plant surface condition and root health. This method provides more accurate health assessment and management decision support through comprehensive image feature extraction and data fusion, helping growers to promptly identify potential problems and take effective measures to improve the overall growth health and yield of Huaniu apples.

[0155] The specific steps of constructing the plant growth analysis model in S53 include:

[0156] S531: Collect data sets for model training, including the root health score data obtained from S2 and the infrared image features and multispectral image features extracted from S4;

[0157] S532: Perform data preprocessing, including missing value processing, data normalization, and feature selection to optimize the training data set; normalization uses the minimum-maximum scaling method to convert feature values ​​to a range of 0 to 1 to ensure that data of different magnitudes can contribute fairly to the training of the model;

[0158] S533: Initialize the random forest algorithm, set the number of trees, specifically 100 to 500 trees, and set the depth of the decision tree, including the number of samples of the minimum split node and the maximum number of features, to control the complexity of the model and prevent overfitting;

[0159] S534: Use the random forest algorithm to train a plant growth analysis model. Random forest improves prediction accuracy by constructing multiple decision trees and averaging or majority voting their predictions, where each tree is trained on a different random subsample of the dataset and the segmentation features are also selected from a random subset of features.

[0160] S535: During the training process, each decision tree selects the features and split points for splitting based on optimizing information gain (entropy reduction or reduction of Gini impurity), thereby splitting the data set at each node until a preset tree depth is reached or the amount of data in the node is below a threshold;

[0161] S536: When all decision trees are built, the random forest model will make a final prediction by integrating the prediction results of all trees; specifically for regression problems, the result is the average of all tree predictions; for classification problems, the result is the category with the most votes;

[0162] S537: After model training is completed, model validation is performed, using cross-validation or retaining a portion of the data as a test set to evaluate the model's predictive performance and generalization ability;

[0163] S538: The expression of the plant growth analysis model after construction is: Where f(x) represents the output of the model, x represents the input feature vector (including infrared image features, multispectral image features and root health score), N is the number of decision trees, and f i (x) represents the prediction result of the i-th tree;

[0164] Through the above steps, a plant growth analysis model was constructed based on the random forest algorithm, and comprehensive analysis was performed using multi-source data to improve the accuracy and reliability of the prediction. The model can accurately judge the relationship between the surface condition of the plant and the health of its roots, providing a scientific basis for the precise management of Huaniu apple trees, helping to optimize planting strategies and improve the health level and yield of fruit trees.

[0165] S6 specifically includes:

[0166] S61: receiving the comprehensive analysis report generated in S5, and based on the comprehensive analysis report, comparing the current data with the historical data, identifying abnormal situations or trend changes, and extracting influencing factors;

[0167] S62: Generate a planting management report, including a historical trend chart of root health score, which is used to show the change of root health score over time, an analysis result chart of infrared images and multispectral images, which is used to show the time series chart of leaf color change, temperature distribution and vegetation index (NDVI), an abnormal area marking chart, which is used to mark the detected temperature abnormality area and its possible cause; and a comprehensive plant health score, which is calculated based on the analysis results and is used to evaluate the overall health status of the plant;

[0168] S63: Based on the comprehensive analysis report, generate adjustment suggestions, including irrigation suggestions, fertilization suggestions, pest and disease control suggestions, and environmental adjustment suggestions; irrigation suggestions are used to adjust the irrigation frequency and water volume according to the root health score and temperature distribution. Specific suggestions include increasing or decreasing the irrigation volume and optimizing the irrigation time; fertilization suggestions are used to adjust the fertilization frequency and fertilizer types according to leaf color changes and vegetation index (NDVI). Specific suggestions include increasing the supply of nutrients such as nitrogen, phosphorus, and potassium; pest and disease control suggestions are used to identify possible pest and disease problems based on abnormal temperature areas and leaf color changes, and propose corresponding prevention and control measures, including spraying pesticides or biological control methods; environmental adjustment suggestions are used to propose environmental adjustment measures that may be needed based on the comprehensive analysis results, such as improving soil drainage and increasing soil organic matter content;

[0169] S65: The planting management report and adjustment suggestions are presented to the growers through a user interface. The interface includes charts, text descriptions and specific operation suggestions, which are easy for growers to understand and implement. Through the above steps, a detailed planting management report and adjustment suggestions are generated based on the comprehensive analysis results. The planting management report provides a comprehensive plant health assessment and historical data comparison to help growers understand the health status and trend changes of the plants. The adjustment suggestions provide specific irrigation, fertilization, pest and disease control and environmental adjustment measures, which help to optimize the planting management strategy and improve the overall growth health and yield of Huaniu apples.

[0170] like Figure 2 As shown, an intelligent planting management system for Huaniu apples is used to implement the above-mentioned intelligent planting management method for Huaniu apples, including the following modules:

[0171] Environmental monitoring module: used to monitor soil environmental parameters in the Huaniu apple planting area in real time, including soil moisture, temperature, conductivity and nutrient content; the environmental monitoring module includes multiple underground sensors, each of which can automatically transmit the collected data to the central processing unit;

[0172] Data processing module: connected to the environmental monitoring module, receiving data from the environmental monitoring module, and analyzing the data using the root health analysis model to generate a root health score;

[0173] UAV monitoring module: used to perform regular flight missions to collect growth status images of Huaniu apple trees, including infrared and multispectral images; the UAV monitoring module includes at least one UAV equipped with infrared and multispectral imaging equipment for monitoring plant growth from the air;

[0174] Comprehensive analysis module: connected with the data processing module and the drone monitoring module, receiving the root health score from the data processing module and the image data from the drone monitoring module, using the plant growth analysis model to comprehensively analyze the relationship between the plant surface condition and root health, and generate a comprehensive analysis report;

[0175] Management suggestion generation module: connected with the comprehensive analysis module, it generates specific planting management reports and adjustment suggestions based on the comprehensive analysis report, including irrigation, fertilization, pest control and environmental adjustment suggestions;

[0176] User Interface Module: Connected to the Management Recommendation Generation Module, it provides a graphical interface for growers to view planting management reports and implement adjustment recommendations; this module provides an interactive interface that enables growers to directly view and operate system recommendations for real-time planting management.

[0177] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0178] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent planting management method for Huaniu apples, characterized in that: The following steps are involved: S1: Deploy micro underground sensors in the Huaniu apple tree planting area to monitor the soil environmental parameters around the roots in real time, including soil moisture, temperature, conductivity and nutrient content; S2: using a preset root health analysis model to evaluate the root health status based on the data collected in S1 and generate a root health score; S3: According to the root health score obtained in S2, adjust the parameters of irrigation and fertilization, including adjusting the amount and frequency of water and nutrient supply; S4: Configure drones to perform regular flight missions, using infrared and multispectral imaging technology to collect growth status images of Huaniu apple trees, including leaf color and growth status data; S5: Comprehensively analyze the image data collected by S4 and the root health score data of S2, and determine the relationship between the plant surface condition and root health through a preset plant growth analysis model; S6: Based on the analysis results of S5, it automatically generates planting management reports and adjustment suggestions.

2. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S1 specifically includes: S11: deploy micro underground sensors around the main root of each Huaniu apple tree in a predetermined pattern, with four sensors deployed on each tree to form a square layout; the sensors include humidity sensors, temperature sensors, conductivity sensors, and nutrient content sensors; S12: Monitor the moisture content in the soil through a humidity sensor. The humidity sensor uses a capacitive principle to measure the change in the dielectric constant in the soil and obtain soil moisture data in real time; S13: Monitor the temperature change of the soil through a temperature sensor. The temperature sensor adopts the principle of thermistor and uses the characteristic that resistance changes with temperature to obtain soil temperature data in real time. S14: The conductivity of the soil is monitored by a conductivity sensor. The conductivity sensor adopts a four-electrode method to obtain soil conductivity data in real time by measuring the conductivity of current in the soil. S15: Monitor the nutrient concentration in the soil through the nutrient sensor. The nutrient sensor uses the principle of ion selective electrode to measure the ion concentration in the soil solution and obtain the data of nitrogen, phosphorus and potassium nutrients in the soil in real time.

3. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S2 specifically includes: S21: collects soil environmental parameter data collected by the sensors in S1, including soil moisture, temperature, conductivity and nutrient concentration, and transmits the data to the central processing unit; S22: constructing a root health analysis model in the central processing unit, wherein the root health analysis model is trained based on a support vector machine algorithm, wherein an input parameter of the root health analysis model is soil environment data, and an output is a root health score; S23: pre-process the real-time data collected by S21, including data cleaning, normalization and outlier detection, to ensure that the data quality meets the input requirements of the root health analysis model; S24: input the preprocessed data into the root health analysis model constructed in S22, comprehensively evaluate the health status of the root system according to the input soil moisture, temperature, electrical conductivity and nutrient concentration, and generate a root health score; S25: Generate a root health score based on the calculation result of S24, the score range is from 0 to 100, and the higher the score, the better the root health status.

4. The intelligent planting management method for Huaniu apple according to claim 3 is characterized in that: The S22 includes: S221: Collect a large amount of historical data, including soil moisture, temperature, conductivity and nutrient concentration in different planting areas, as well as corresponding root health records, as input data for model training; S222: preprocessing the collected historical data, including data cleaning, normalization and outlier detection; S223: Divide the preprocessed data set into a training set and a test set, specifically using an 80:20 ratio of data division, where 80% is used for training and 20% is used for testing; S224: Use the support vector machine algorithm to train the model, define the input feature vector as x = x1, x2, x3, x4], where x1, x2, x3, x4 represent soil moisture, temperature, conductivity and nutrient concentration respectively, and the output is the root health score y; the optimization goal of the support vector machine is to find an optimal hyperplane to maximize the interval from the feature vector to the hyperplane. The optimization problem is expressed as: Among them, w is the normal vector of the hyperplane, b is the bias term; the constraints are: Among them, y i is the root health score of the training sample, x i is the corresponding input feature vector, ξ i is the slack variable; S225: Use radial basis kernel function for nonlinear mapping. The radial basis kernel function is defined as: K(x i ,x j )=exp(-γ||x i -x j || 2 ), where γ is the parameter of the kernel function, x i and x j are the input feature vectors of different samples respectively; S226: Using the training set data, the model parameters w and b are iteratively optimized by the gradient descent method until the loss function converges. The loss function is defined as: Among them, L is the loss function, C is the regularization parameter, n is the number of training samples, ξ i is the slack variable; S227: The root health analysis model expression after construction is: Where f(x) is the root health score prediction value of the input feature vector x, α i is the Lagrange multiplier, y i is the actual root health score of the training sample, K(x i ,x) is the radial basis kernel function, x i is the support vector and b is the bias term.

5. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S3 specifically includes: S31: According to the root health score, the score is divided into three intervals, namely 0-40 for low health status, 41-70 for medium health status, and 71-100 for high health status; S32: Adjust irrigation and fertilization parameters according to the interval to which the root health score belongs; S33: Adjust irrigation parameters and calculate the water requirement of each Huaniu apple tree. Assuming the water requirement is W, the formula is: Among them, W base is the basic water requirement, y is the root health score; according to the water requirement W, adjust the irrigation frequency F, and the irrigation frequency formula is: Among them, F base The basic irrigation frequency; S34: Adjust the fertilization parameters and calculate the fertilizer requirement of each Huaniu apple tree. Assuming the fertilizer requirement is N, the formula is: Among them, N base is the basic fertilizer requirement, y is the root health score; according to the fertilizer requirement N, adjust the fertilization frequency G, and the fertilization frequency formula is: Among them, G base The frequency of basal fertilization; S35: Input the adjusted irrigation and fertilization parameters into the automatic control system, and automatically perform irrigation and fertilization operations according to the parameters.

6. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S4 specifically includes: S41: Select and configure drones suitable for agricultural monitoring, and ensure that the drones are equipped with infrared imaging equipment and multispectral imaging equipment. The infrared imaging equipment is used to detect temperature distribution, and the multispectral imaging equipment is used to detect the spectral reflectance characteristics of plants. S42: Set the flight route and altitude of the drone to ensure coverage of the entire Huaniu apple planting area. The flight route planning needs to take terrain and obstacles into consideration, and the flight altitude needs to be kept stable to ensure the consistency and accuracy of the image data. S43: Set up a regular flight plan for the drone, determine the frequency and time of the flight, usually conduct flight monitoring once a week to obtain regular growth data; S44: In each flight mission, the drone flies according to the preset route and altitude, and simultaneously activates the infrared imaging device and the multi-spectral imaging device to collect data. The infrared imaging device captures the temperature distribution of the Huaniu apple tree and records the temperature changes; S45: The multispectral imaging device collects multispectral image data of Huaniu apple trees and monitors the leaf color and spectral reflectance characteristics of the plants, including the reflectance of blue, green, red and near-infrared light; S46: The collected infrared image and multispectral image data are transmitted to the central processing unit in real time through the wireless communication module; in the central processing unit, the infrared image data is processed, the temperature distribution is analyzed, potential abnormal areas are identified, and it is determined whether the plant has temperature abnormalities; S47: Process the multispectral image data, calculate the vegetation index by analyzing the reflectance of each band, and evaluate the growth health and leaf color changes of Huaniu apple trees; S48: Compare the processed image data with previous historical data to generate a growth status report, which includes information on leaf color changes, temperature distribution, and vegetation index.

7. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S5 specifically includes: S51: receiving the infrared image data and the multispectral image data transmitted to the central processing unit in S4, and the root health score data generated in S2; S52: preprocessing the infrared image data and the multispectral image data, including denoising, correction and normalization; S53: Based on the random forest algorithm, a plant growth analysis model was constructed to comprehensively analyze the plant surface condition and root health data; S54: Extract infrared image features, including temperature distribution pattern and temperature anomaly ratio, and extract multispectral image features, including reflectance of each band and normalized vegetation index; S55: fusing the extracted image features with the root health score data as input to the plant growth analysis model; S56: Using the trained plant growth analysis model, analyze the data fused in S55 to determine whether the surface condition of the plant is consistent with the health status of the root; S57: Generate a comprehensive analysis report, including the comparison results of plant surface condition and root health score, the correlation between leaf color change and root nutrition status, and the correspondence between abnormal temperature areas and root health problems.

8. The intelligent planting and management method for Huaniu apple according to claim 7, characterized in that: The S53 includes: S531: Collect data sets for model training, including the root health score data obtained from S2 and the infrared image features and multispectral image features extracted from S4; S532: Perform data preprocessing, including missing value processing, data normalization, and feature selection to optimize the training data set; S533: Initialize the random forest algorithm, set the number of trees, specifically 100 to 500 trees, and set the depth of the decision tree, including the number of samples of the minimum split node and the maximum number of features, to control the complexity of the model and prevent overfitting; S534: Use the random forest algorithm to train a plant growth analysis model. Random forest improves prediction accuracy by constructing multiple decision trees and averaging or majority voting their predictions, where each tree is trained on a different random subsample of the dataset and the segmentation features are also selected from a random subset of features. S535: During the training process, each decision tree selects the features and split points for splitting based on optimizing information gain, thereby splitting the data set at each node until a preset tree depth is reached or the amount of data in the node is lower than a threshold; S536: When all decision trees are built, the random forest model will make a final prediction by integrating the prediction results of all trees; specifically for regression problems, the result is the average of all tree predictions; for classification problems, the result is the category with the most votes; S537: After model training is completed, model validation is performed, using cross-validation or retaining a portion of the data as a test set to evaluate the model's predictive performance and generalization ability; S538: The expression of the plant growth analysis model after construction is: Among them, f(x) represents the output of the model, x represents the input feature vector, N is the number of decision trees, and f i (x) represents the prediction result of the i-th tree.

9. The intelligent planting management method for Huaniu apple according to claim 1, characterized in that: The S6 specifically includes: S61: receiving the comprehensive analysis report generated in S5, and based on the comprehensive analysis report, comparing the current data with the historical data, identifying abnormal situations or trend changes, and extracting influencing factors; S62: Generate a planting management report, including a historical trend chart of root health scores, analysis results of infrared images and multispectral images, annotated abnormal area charts, and a comprehensive plant health score; S63: Based on the comprehensive analysis report, generate adjustment suggestions, including irrigation suggestions, fertilization suggestions, pest and disease control suggestions, and environmental adjustment suggestions; S65: The planting management report and adjustment suggestions are presented to the grower through a user interface, which includes charts, text descriptions and specific operation suggestions.

10. An intelligent planting management system for Huaniu apples, used to implement an intelligent planting management method for Huaniu apples as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Environmental monitoring module: used to monitor soil environmental parameters in the Huaniu apple planting area in real time, including soil moisture, temperature, conductivity and nutrient content; Data processing module: connected to the environmental monitoring module, receiving data from the environmental monitoring module, and analyzing the data using the root health analysis model to generate a root health score; UAV monitoring module: used to perform regular flight missions to collect images of the growth status of Huaniu apple trees, including infrared and multispectral images; Comprehensive analysis module: connected with the data processing module and the drone monitoring module, receiving the root health score from the data processing module and the image data from the drone monitoring module, using the plant growth analysis model to comprehensively analyze the relationship between the plant surface condition and root health, and generate a comprehensive analysis report; Management suggestion generation module: connected with the comprehensive analysis module, it generates specific planting management reports and adjustment suggestions based on the comprehensive analysis report, including irrigation, fertilization, pest control and environmental adjustment suggestions; User interface module: connected to the management suggestion generation module, providing a graphical interface for growers to view planting management reports and implement adjustment suggestions.

Images