A system and method for planting and managing Idesia polycarpa Maxim. forests

Abstract

The present invention discloses an Idesia polycarpa forest planting management system and method, which relates to the technical field of forest planting management. The planting area is divided into several soil clustering regions by the K-means clustering algorithm, and each soil clustering region is further subdivided into several sub-regions by considering the growth indicators of Idesia polycarpa. A multi-factor correlation model is established by combining the characteristic data of Idesia polycarpa, soil and environment. Correction factors are generated for each sub-region through the multi-factor correlation model. Based on the correction factors, the coating thickness of the protective layer for each sub-region is dynamically corrected. After evaluating the coating effect of the protective layer for the sub-region, corresponding management strategies are generated. This management system calculates correction factors through the multi-factor correlation model and dynamically adjusts the coating thickness of the protective layer for each sub-region according to the correction factors, making the protective measures more accurate, effectively reducing resource waste, and improving the protective effect at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of forest tree planting management, and particularly relates to a management system and method for planting and managing Idesia polycarpa forest trees. Background Art

[0002] Idesia polycarpa is a deciduous tree widely distributed in the Yangtze River Basin and southern regions of China. It has strong adaptability and high ecological, economic, and energy values. Idesia polycarpa can not only be used for ecological greening, soil conservation, and water source conservation, but also has a high oil content in its fruits and is regarded as a potential raw material for biodiesel. In recent years, it has received wide attention. With the development of the bioenergy industry, the large-scale planting of Idesia polycarpa has gradually expanded, and the demand for scientific and intelligent planting management has also increased day by day.

[0003] The existing technology has the following deficiencies:

[0004] Under the existing management mode, the coating thickness of the protective layer of Idesia polycarpa (such as the cold-proof layer, anti-disease coating, etc.) is usually a preset fixed value, or is only adjusted according to the experience of the planting personnel, lacking scientific basis. This method may lead to insufficient protective layers for Idesia polycarpa in some areas, failing to achieve the protective effect, while in some areas, there may be waste of resources due to excessive coating.

[0005] Based on this, the present invention proposes a management system and method for planting and managing Idesia polycarpa forest trees. By calculating the correction factor through a multi-factor correlation model and dynamically adjusting the coating thickness of the protective layer for each sub-region according to the correction factor, the protective measures are made more precise, effectively reducing resource waste and improving the protective effect at the same time. Summary of the Invention

[0006] The purpose of the present invention is to provide a management system and method for planting and managing Idesia polycarpa forest trees to solve the deficiencies in the background art.

[0007] To achieve the above purpose, the present invention provides the following technical solution: A method for planting and managing Idesia polycarpa forest trees, the management method comprising the following steps:

[0008] The management system collects the soil data of the location of each Idesia polycarpa in the planting area, divides the planting area into several soil clustering regions through the K-means clustering algorithm, and further divides each soil clustering region into several sub-regions by considering the growth indicators of Idesia polycarpa;

[0009] Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub-region, and establish a multi-factor correlation model in combination with the characteristic data of Idesia polycarpa, soil, and environment;

[0010] Generate a correction factor for each sub-region through a multi-factor correlation model, dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor, and generate corresponding management strategies after evaluating the coating effect of the protective layer for the sub-region.

[0011] In a preferred embodiment, regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub-region. The changes in the growth indicators of Idesia polycarpa include the retention rate of chlorophyll content, the changes in soil indicators include the degree of soil salinization, and the environmental changes include the environmental change index.

[0012] In a preferred embodiment, establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, and generate a correction factor for each sub-region through the multi-factor correlation model, including the following steps:

[0013] The changes in the growth indicators of Idesia polycarpa include the retention rate of chlorophyll content, the changes in soil indicators include the degree of soil salinization, and the environmental changes include the environmental change index;

[0014] Establish a multi-factor correlation model based on the retention rate of chlorophyll content, the degree of soil salinization, and the environmental change index. The multi-factor correlation model calculates the weighted values of the retention rate of chlorophyll content, the degree of soil salinization, and the environmental change index to generate a correction factor for each sub-region.

[0015] In a preferred embodiment, dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor, including the following steps:

[0016] After obtaining the correction factor of the sub-region, compare the correction factor with the correction threshold. If the correction factor of the sub-region is less than the correction threshold, it is analyzed that there is no need to dynamically correct the coating thickness of Idesia polycarpa in this sub-region. If the correction factor of the sub-region is greater than or equal to the correction threshold, it is analyzed that it is necessary to dynamically correct the coating thickness of Idesia polycarpa in this sub-region;

[0017] Dynamically correct the initial coating thickness of the protective layer for the sub-region based on the correction factor to obtain the corrected coating thickness, and the expression is:

[0018] , where is the corrected coating thickness, is the initial coating thickness, is the correction factor, is the learning rate.

[0019] In a preferred embodiment, after evaluating the coating effect of the protective layer for the sub-region, generate corresponding management strategies, including the following steps:

[0020] Adjust the learning rate based on the overall effect score , and the adjustment algorithm is as follows:

[0021] , where is the adjusted learning rate, is the learning rate before adjustment, is the deviation of the protective layer coating cost after normalization processing, is the retention rate of chlorophyll content after normalization processing, is the overall effect score, is the score threshold.

[0022] In a preferred embodiment, the management system collects soil data at the location of each idesia tree in the planting area, and divides the planting area into several soil clustering regions by the K-means clustering algorithm, including the following steps:

[0023] The management system obtains the soil data at the location of each idesia tree in the planting area through sensors, including soil humidity, soil pH value, soil organic matter content, and nitrogen, phosphorus, and potassium element content:

[0024] Assume that there are N sampling points in the planting area, obtain the soil data of each sampling point, and construct a feature vector;

[0025] Randomly select the feature vectors of K sampling points as the initial clustering centers, calculate the distance from each sample point to the K initial clustering centers according to the Euclidean distance algorithm, assign each sampling point to the soil clustering region where the initial clustering center with the minimum distance is located, and calculate the feature vector mean of each soil clustering region as the new centroid;

[0026] Repeat the sampling point assignment and new centroid calculation steps. When the change amount of the new centroid of all soil clustering regions in any one time is less than the change threshold, it is judged that the convergence condition is satisfied, and K soil clustering regions are output.

[0027] In a preferred embodiment, assume that there are N sampling points in the planting area, obtain the soil data of each sampling point, and construct a feature vector: , where represents the soil feature vector of the th sampling point, successively represent different attributes of the soil, and M represents the number of detected soil attributes.

[0028] In a preferred embodiment, randomly select the feature vectors of K sampling points as the initial clustering centers, and calculate the distance from each sample point to the K initial clustering centers according to the Euclidean distance algorithm. The expression is:

[0029] , where is the distance from the j-th sampling point to the i-th initial clustering center, M represents the number of detected soil properties, is the m-th soil property value of the j-th sampling point, represents the m-th soil property value of the i-th initial clustering center;

[0030] Calculate the mean of the feature vectors of each soil clustering region as the new centroid, and the expression is: , where is the new centroid of the i-th soil clustering region, represents the number of sampling points in the i-th soil clustering region, represents the soil feature vector of the j-th sampling point.

[0031] In a preferred embodiment, considering the growth indicators of Idesia polycarpa, each soil clustering region is further divided into several sub-regions, including the following steps:

[0032] Within each soil clustering region, collect the growth indicators of Idesia polycarpa, including tree height, crown width, trunk diameter, number of leaves, leaf color index, and root length;

[0033] Construct the growth indicators into feature vectors: , where represents the growth indicator feature vector of the k-th Idesia polycarpa, successively represent different attributes of Idesia polycarpa, represents the number of detected growth indicators;

[0034] Randomly select the feature vectors of K Idesia polycarpa as the initial clustering centers, calculate the distance from each Idesia polycarpa in the soil clustering region to the K initial clustering centers according to the Euclidean distance algorithm, assign each Idesia polycarpa to the sub-region where the initial clustering center with the smallest distance is located, and calculate the mean of the growth indicator feature vectors of each sub-region as the new centroid;

[0035] Repeat the steps of sampling point assignment and new centroid calculation. When the change amount of the new centroid of all sub-regions in any one time is less than the change threshold, it is judged that the convergence condition is satisfied, and K subdivided sub-regions are output in the soil clustering region.

[0036] An Idesia polycarpa forest planting management system includes a subdivision clustering module, a data acquisition module, a calculation module, and a dynamic correction module;

[0037] Sub - clustering module: Collect soil data of the location of each Idesia polycarpa in the planting area, divide the planting area into several soil clustering regions through the K - means clustering algorithm, and further divide each soil clustering region into several sub - regions by considering the growth indicators of Idesia polycarpa;

[0038] Data acquisition module: Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub - region;

[0039] [[ID=X]]Calculation module: Establish a multi - factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, and generate a correction factor for each sub - region through the multi - factor correlation model;

[0040] Dynamic correction module: Dynamically correct the coating thickness of the protective layer for each sub - region based on the correction factor. After evaluating the coating effect of the protective layer in the sub - region, generate corresponding management strategies.

[0041] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0042] 1. The present invention divides the planting area into several soil clustering regions through the K - means clustering algorithm, further divides each soil clustering region into several sub - regions by considering the growth indicators of Idesia polycarpa, establishes a multi - factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, generates a correction factor for each sub - region through the multi - factor correlation model, dynamically corrects the coating thickness of the protective layer for each sub - region based on the correction factor, and generates corresponding management strategies after evaluating the coating effect of the protective layer in the sub - region. This management system calculates the correction factor through the multi - factor correlation model and dynamically adjusts the coating thickness of the protective layer in each sub - region according to the correction factor, making the protection measures more accurate, effectively reducing resource waste, and improving the protection effect at the same time;

[0043] 2. The present invention divides the Idesia polycarpa with similar growth characteristics in the soil clustering region into sub - regions, so that the plants in the same region have more balanced growth characteristics, which is convenient for precise management. The Euclidean distance algorithm is used for classification to improve the scientific nature of sub - region division, and the new centroid is iteratively optimized to ensure the stability and accuracy of clustering. Finally, this method can improve the refinement degree of planting management, make management measures such as water and fertilizer regulation and protective layer coating more targeted, improve the overall planting efficiency and the growth quality of Idesia polycarpa, reduce the cost of manual intervention at the same time, and realize intelligent management. Brief description of the drawings

[0044] Note: In the original text, there is no "X" in the ID. I added "X" to the ID in the translation of the "Calculation module" part for the sake of consistency in the translation structure. If this is not allowed, please let me know and I will adjust it according to your requirements.To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments described in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0045] Figure 1 This is the method flowchart of the management method of the present invention.

[0046] Figure 2 This is the timing diagram of the management method of the present invention.

[0047] Figure 3 This is the system architecture diagram of the management system of the present invention. Detailed implementation manners

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0049] Embodiment 1: Please refer to Figure 1 - Figure 2 As shown, the management method for the cultivation of Idesia polycarpa Maxim. forest trees in this embodiment includes the following steps:

[0050] The management system collects the soil data of the location of each Idesia polycarpa Maxim. in the planting area, divides the planting area into several soil clustering areas through the K-means clustering algorithm, further divides each soil clustering area into several sub-areas considering the growth indicators of Idesia polycarpa Maxim., regularly collects the changes in the growth indicators, soil indicators, and environmental changes of Idesia polycarpa Maxim. in each sub-area, establishes a multi-factor correlation model by combining the characteristic data of Idesia polycarpa Maxim., soil, and environment, generates a correction factor for each sub-area through the multi-factor correlation model, dynamically corrects the coating thickness of the protective layer for each sub-area, and generates corresponding management strategies after evaluating the coating effect of the protective layer for the sub-area.

[0051] Using Geographic Information System (GIS) and soil detection technology, comprehensively collect soil data of each Idesia polycarpa in the planting area, covering indicators such as soil pH, fertility, texture, etc. Divide the planting area into several soil clustering regions through the K-means clustering algorithm. The soil conditions within each region are similar, and each soil clustering region contains several Idesia polycarpa. Within each soil clustering region, consider the growth indicators of Idesia polycarpa, such as tree height, diameter at breast height, crown width, health status, etc. Then, further divide each soil clustering region into several sub-regions through the K-means clustering algorithm to ensure a high degree of consistency in the growth basis of Idesia polycarpa within each sub-region.

[0052] The existing Idesia polycarpa planting management methods usually simply divide the planting area based on experience or a small amount of soil detection data. For example, divide by plot or only classify according to soil types (such as sandy soil, loam, clay). This division method cannot accurately reflect the subtle differences in soil composition in different regions, resulting in management strategies being difficult to accurately match the actual needs of each region. This solution uses the K-means clustering algorithm to automatically classify regions with similar soil characteristics based on the soil data at each location in the planting area, forming multiple soil clustering regions, and further subdividing the regions in combination with the growth indicators of Idesia polycarpa, making the management more refined and improving soil utilization efficiency.

[0053] Regularly (such as monthly) measure and record the growth indicators of Idesia polycarpa in each sub-region, including the growth of tree height and diameter at breast height, changes in leaf color, morphology, and quantity, as well as the development status of fruits, etc. The combination of unmanned aerial vehicle remote sensing technology and ground monitoring equipment can be used to improve the accuracy and efficiency of monitoring. Collect soil samples in the sub-region and analyze the changes in indicators such as soil pH, fertility, and moisture content. Use soil sensors to continuously monitor data such as soil temperature, humidity, and nutrient content to provide timely and accurate information for subsequent analysis. Based on the meteorological station, continuously monitor the meteorological elements in the sub-region, such as environmental changes in temperature, light intensity, precipitation, wind speed, etc. At the same time, pay attention to the changes in the surrounding ecological environment, such as the occurrence of pests and diseases and changes in vegetation coverage.

[0054] Establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, and generate a correction factor for each sub-region through the multi-factor correlation model. The calculation method of the correction factor can be determined according to the multi-factor correlation model. Comprehensively consider the influence of the growth status of Idesia polycarpa, changes in soil conditions, and environmental changes on the coating thickness of quicklime powder mixture. Dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor. After evaluating the coating effect of the protective layer in the sub-region, generate corresponding management strategies.

[0055] The existing management methods fail to effectively integrate the complex relationships among the growth of Idesia polycarpa, soil characteristics, and environmental factors. For example, when abnormal growth occurs in plants, it is usually judged based on experience whether it is caused by soil problems, climate change, or other factors, lacking precise quantitative analysis. This solution combines the long-term accumulated growth data, soil data, and environmental data of Idesia polycarpa to construct a multi-factor correlation model, analyze the impact of each factor on the growth of Idesia polycarpa as a whole, and extract key influencing factors to improve the scientificity and reliability of decision-making.

[0056] After implementing protective measures, the existing planting management methods usually lack systematic evaluation means, mainly relying on the observation and experience of planting personnel to judge whether the protective measures are effective, making it difficult to quantify the advantages and disadvantages of different management strategies, resulting in greater optimization difficulty. After dynamically correcting the coating thickness of the protective layer in this solution, the protective effect will also be evaluated. By analyzing the growth changes of Idesia polycarpa and the improvement of the soil environment, etc., a closed-loop feedback mechanism is formed to ensure the continuous optimization of management strategies and improve the overall planting efficiency.

[0057] In this application, the planting area is divided into several soil clustering regions through the K-means clustering algorithm. Considering the growth indicators of Idesia polycarpa, each soil clustering region is further divided into several sub-regions. A multi-factor correlation model is established by combining the characteristic data of Idesia polycarpa, soil, and environment. A correction factor is generated for each sub-region through the multi-factor correlation model. Based on the correction factor, the coating thickness of the protective layer for each sub-region is dynamically corrected. After evaluating the coating effect of the protective layer for the sub-region, corresponding management strategies are generated. This management system calculates the correction factor through the multi-factor correlation model and dynamically adjusts the coating thickness of the protective layer for each sub-region according to the correction factor, making the protective measures more accurate, effectively reducing resource waste, and improving the protective effect at the same time.

[0058] In this application, the steps of applying the protective layer are as follows:

[0059] After planting, mix quicklime powder with edible salt (ratio 100:2), add water to make a paste, and apply it from the root up to the trunk. For young trees, it is above 50 cm, and for big trees, it is above 1.2 m. Apply it once a year later to keep warm, moisturize, sterilize, and prevent pests.

[0060] Example 2: As Figure 3 shown: The Idesia polycarpa forest planting management system described in this example includes a subdivision clustering module, a data collection module, a calculation module, and a dynamic correction module;

[0061] Sub - clustering module: Collect soil data of the location of each Idesia polycarpa in the planting area, divide the planting area into several soil clustering regions through the K - means clustering algorithm, and further divide each soil clustering region into several sub - regions considering the growth indicators of Idesia polycarpa. Send the sub - region subdivision information to the data acquisition module and the dynamic correction module;

[0062] Data acquisition module: Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub - region, and send the collected data to the calculation module;

[0063] Calculation module: Establish a multi - factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, generate a correction factor for each sub - region through the multi - factor correlation model, and send the correction factor to the dynamic correction module;

[0064] Dynamic correction module: Dynamically correct the coating thickness of the protective layer for each sub - region based on the correction factor. After evaluating the coating effect of the protective layer for the sub - region, generate corresponding management strategies.

[0065] Example 3: The management system collects the soil data of the location of each Idesia polycarpa in the planting area, and divides the planting area into several soil clustering regions through the K - means clustering algorithm, including the following steps:

[0066] In the actual process of planting Idesia polycarpa, the larger the planting area, the more complex the soil conditions in the area. In order to improve the growth quality of Idesia polycarpa, the management system collects soil data of the planting area and uses the K - means clustering algorithm for area division to achieve precise management.

[0067] The management system obtains the soil data of the location of each Idesia polycarpa in the planting area through sensors (usually one sensor can obtain the soil data within a certain circular range, and there are at least 3 - 4 Idesia polycarpa trees within this circular range), including soil humidity, soil pH value, soil organic matter content, and the content of nutrient elements such as nitrogen, phosphorus, and potassium:

[0068] Soil humidity: The moisture content in different regions.

[0069] Soil pH value: The acidity - alkalinity information that affects plant nutrient absorption.

[0070] [[ID=Z7]]Soil organic matter content: An important indicator reflecting soil fertility.

[0071] Content of nutrient elements such as nitrogen, phosphorus, and potassium: Determines the nutrient level required for the growth of Idesia polycarpa.

[0072] All data forms a multi - dimensional data set containing spatial coordinates and soil physical and chemical properties.

[0073] Preprocess all the obtained soil data, including outlier handling and missing value filling:

[0074] Outlier handling: Remove extremely abnormal measurement values, such as abnormal points where the pH value at some points is lower than 4 or higher than 9.

[0075] Missing value filling: For individual missing data points, fill them with the mean value of the data at adjacent sampling points.

[0076] Suppose there are N sampling points in the planting area, obtain the soil data of each sampling point, and construct a feature vector: , where represents the soil feature vector of the th sampling point, successively represent different attributes of the soil, and M represents the number of detected soil attributes (such as humidity, pH value, organic matter content, nitrogen, phosphorus, and potassium content, particle composition, etc., where M is equal to 5 here).

[0077] Calculate the sum of squared errors within clusters SSE (Sum-of-Squared-Errors) at different K values through the general elbow method: , where represents the i-th cluster, represents the center of the i-th cluster, is the squared Euclidean distance from the sample point to the cluster center , is the number of clusters, and take the K value at the inflection point of the SSE curve. For example, when K = 5, the SSE decrease slows down, then select K = 5.

[0078] Randomly select the feature vectors of K sampling points as the initial cluster centers, and calculate the distance from each sample point to the K initial cluster centers according to the Euclidean distance algorithm. The expression is:

[0079] , where is the distance from the j-th sampling point to the i-th initial cluster center, M represents the number of detected soil attributes, is the m-th soil attribute value of the j-th sampling point, represents the m-th soil attribute value of the i-th initial cluster center. Assign each sampling point to the soil cluster area where the initial cluster center with the minimum distance is located , and calculate the mean value of the feature vectors of each soil cluster area as the new centroid. The expression is: , where is the new centroid of the i-th soil cluster area, represents the number of sampling points in the \(i\)-th soil clustering region, represents the soil feature vector of the \(j\)-th sampling point.

[0080] Repeat the steps of sampling point allocation and new centroid calculation. When the change amount of the new centroid of all soil clustering regions in any iteration is less than the change threshold (the change amount of the new centroid is obtained by subtracting the new centroid obtained in the previous iteration from the new centroid obtained in the current iteration), it is judged that the convergence condition is satisfied, and \(K\) soil clustering regions are output.

[0081] Considering the growth indicators of Idesia polycarpa, each soil clustering region is further divided into several sub-regions, including the following steps:

[0082] Since the division of soil clustering regions is achieved by setting multiple sampling points to collect soil data, and the sampling points obtain soil data within a certain circular range through sensors, and there are at least 3 - 4 Idesia polycarpa trees within this circular range. That is, the soil data of 3 - 4 Idesia polycarpa trees growing in the soil clustering region is roughly similar, but the growth conditions of 3 - 4 Idesia polycarpa trees may vary. In order to improve the accuracy of subsequent analysis, we also need to further divide each soil clustering region considering the growth indicators of Idesia polycarpa. The solution is as follows:

[0083] Within each soil clustering region, for all Idesia polycarpa plants, collect the growth indicators of Idesia polycarpa, including tree height, crown width, trunk diameter, number of leaves, leaf color index (e.g., obtained through spectral analysis), and root length. These data can be collected through remote sensing monitoring, manual measurement, or intelligent sensors.

[0084] Construct a feature vector from the growth indicators: , where represents the growth indicator feature vector of the \(m\)-th Idesia polycarpa, successively represent different attributes of Idesia polycarpa, represents the number of growth indicators detected (such as tree height, crown width, trunk diameter, number of leaves, leaf color index, and root length. Here \(P\) is equal to 6).

[0085] Randomly select the feature vectors of \(K\) Idesia polycarpa as the initial clustering centers. Calculate the distance from each Idesia polycarpa in the soil clustering region to the \(K\) initial clustering centers according to the Euclidean distance algorithm, and assign each Idesia polycarpa to the sub-region where the initial clustering center with the minimum distance is located. Calculate the mean value of the growth indicator feature vectors of each sub-region as the new centroid.

[0086] Repeat the steps of sampling point allocation and new centroid calculation. When the change amount of the new centroid of all sub-regions in any iteration is less than the change threshold (the change amount of the new centroid is obtained by subtracting the new centroid obtained in the previous iteration from the new centroid obtained in the current iteration), it is determined that the convergence condition is met, and K subdivided sub-regions are output in the soil clustering region.

[0087] In this application, the idesia trees with similar growth characteristics in the soil clustering region are divided into sub-regions, so that the plants in the same region have more balanced growth characteristics, which is convenient for precise management. The Euclidean distance algorithm is used for classification to improve the scientificity of sub-region division, and the new centroid is optimized iteratively to ensure the stability and accuracy of clustering. Finally, this method can improve the refinement degree of planting management, make management measures such as water and fertilizer regulation and protective layer coating more targeted, improve the overall planting efficiency and the growth quality of idesia trees, reduce the cost of manual intervention at the same time, and achieve intelligent management.

[0088] Regularly collect the changes in the growth indicators, soil indicators and environmental conditions of idesia trees in each sub-region, including the following steps:

[0089] The changes in the growth indicators of idesia trees include the chlorophyll content retention rate, the changes in the soil indicators include the degree of soil salinization, and the environmental changes include the environmental change index.

[0090] The chlorophyll content can reflect the health status of plants. Usually, the chlorophyll content of the leaves per unit area is obtained by a chlorophyll meter. The chlorophyll content retention rate can represent the change degree of chlorophyll over time. The calculation logic of the chlorophyll content retention rate is: obtain the chlorophyll content of idesia trees at the current time t and the chlorophyll content at the reference time (such as the initial planting period), divide the chlorophyll content at the current time t by the chlorophyll content at the reference time to obtain the chlorophyll content retention rate. When the chlorophyll content retention rate is low, it indicates that the growth status is poor and the plants may be under environmental stress, and the coating thickness should be increased to enhance the protection effect. When the chlorophyll content retention rate is high, it indicates that the plants are healthy, and the coating thickness can be appropriately reduced to reduce resource waste.

[0091] The calculation logic of the degree of soil salinization is: detect the soil conductivity through a conductivity meter, monitor the soil pH value through a PK detector, after normalizing the soil conductivity and the soil pH value, map the value ranges of the soil conductivity and the soil pH value to between [0,1], and sum the normalized soil conductivity and the soil pH value to obtain the degree of soil salinization. When the degree of soil salinization is large, it indicates that the soil salt content is high and it is easy to cause salinization, and the coating thickness needs to be increased.

[0092] The calculation logic of the environmental change index is as follows: obtain the temperature increase value by subtracting the temperature value at time t0 from the temperature value at time t, obtain the monitoring duration by subtracting t0 from t, divide the temperature increase value by the monitoring duration to obtain the temperature change rate at time t, obtain the humidity increase value by subtracting the humidity value at time t0 from the humidity value at time t, obtain the monitoring duration by subtracting t0 from t, divide the humidity increase value by the monitoring duration to obtain the humidity change rate at time t. When the environmental temperature is relatively high, it is necessary to increase the coating thickness to reduce the impact of heat stress. When the temperature change rate of the environment is relatively small, appropriately reduce the coating thickness to avoid affecting the trunk respiration. When the humidity change rate of the environment is relatively small, increase the coating thickness to reduce water transpiration. When the humidity change rate of the environment is relatively large, appropriately reduce the thickness to avoid the coating being too thick and affecting gas exchange.

[0093] In summary, in an accumulation period, calculate the environmental change index based on the temperature change rate and the environmental humidity change rate. The expression is as follows: , where is the environmental change index, is the temperature change rate at time t, is the humidity change rate at time t, is the accumulation period. The larger the environmental change index, the faster the temperature increases and the more the humidity decreases, and the more necessary it is to increase the coating thickness.

[0094] Establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment. Generate a correction factor for each sub-region through the multi-factor correlation model, including the following steps:

[0095] Obtain the change situation of the growth indicators of Idesia polycarpa, including the retention rate of chlorophyll content, the change situation of soil indicators, including the degree of soil salinization, and the environmental change situation, including the environmental change index.

[0096] Establish a multi-factor correlation model based on the retention rate of chlorophyll content, the degree of soil salinization, and the environmental change index. In this application, after matching a similar planting environment of Idesia polycarpa based on the database, generate a coating thickness range. In order to reduce costs and avoid reducing the survival rate of Idesia polycarpa due to too thick a coating thickness in the early stage, select the minimum value in the coating thickness range as the initial coating thickness.

[0097] Therefore, in practical applications, it is mainly through the correction factor generated by the multi-factor correlation model to determine whether it is necessary to increase the coating thickness. Based on this, the multi-factor correlation model determines the positive and negative proportional relationships between the chlorophyll content retention rate, the degree of soil salinization, and the environmental change index and the correction factor. Among them, the chlorophyll content retention rate is inversely proportional to the correction factor, and the degree of soil salinization and the environmental change index are directly proportional to the correction factor. According to the above logic, the multi-factor correlation model weights the chlorophyll content retention rate, the degree of soil salinization, and the environmental change index to calculate the correction factor for each sub-region. The expression of the multi-factor correlation model is:

[0098] , where is the correction factor, is the degree of soil salinization, is the environmental change index, is the chlorophyll content retention rate, , , are the weight coefficients, and the sum of the weight coefficients , , is 1.

[0099] Based on the correction factor, the coating thickness of the protective layer for each sub-region is dynamically corrected, including the following steps:

[0100] The larger the correction factor of the sub-region, the more it indicates that it is necessary to increase the coating thickness of the protective layer of Idesia polycarpa in this sub-region. After obtaining the correction factor of the sub-region, compare the correction factor with the correction threshold. If the correction factor of the sub-region is less than the correction threshold, it is analyzed that there is no need to dynamically correct the coating thickness of the protective layer of Idesia polycarpa in this sub-region. If the correction factor of the sub-region is greater than or equal to the correction threshold, it is analyzed that it is necessary to dynamically correct the coating thickness of the protective layer of Idesia polycarpa in this sub-region, then the initial coating thickness of the protective layer of the sub-region is dynamically corrected based on the correction factor to obtain the corrected coating thickness, and the expression is:

[0101] , where is the corrected coating thickness, is the initial coating thickness of the protective layer, is the correction factor, is the learning rate, and , which is used to adjust the influence of the correction factor on the coating thickness of the protective layer.

[0102] After evaluating the coating effect of the protective layer of the sub-region, the corresponding management strategy is generated, including the following steps:

[0103] After the application of the protective layer in all sub-regions and after a period of time, obtain the deviation of the protective layer application cost in the planting area and the retention rate of chlorophyll content. Normalize the retention rate of chlorophyll content and the deviation of the protective layer application cost so that the value ranges of the retention rate of chlorophyll content and the deviation of the protective layer application cost are mapped between [0, 1]. Subtract the deviation of the protective layer application cost from the normalized retention rate of chlorophyll content to obtain the overall effect score.

[0104] Adjust the learning rate based on the overall effect score , and the adjustment algorithm is:

[0105] , where, is the adjusted learning rate, is the learning rate before adjustment, is the deviation of the protective layer application cost after normalization, is the retention rate of chlorophyll content after normalization, is the overall effect score, is the score threshold.

[0106] The acquisition logic of the deviation of the protective layer application cost is: subtract the expected cost from the actual cost of the protective layer application in the sub-region to obtain the deviation of the protective layer application cost. The larger the deviation of the protective layer application cost, the higher the actual cost is above the expected cost, and the learning rate needs to be reduced to reduce the influence of the correction factor on the coating thickness.

[0107] In this application, after dynamically correcting the initial coating thickness to obtain the corrected coating thickness, remotely send the corrected coating thickness control instruction to the Idesia polycarpa trunk coating device. The Idesia polycarpa trunk coating device applies the protective layer to the Idesia polycarpa trunk based on the corrected coating thickness, including the following steps:

[0108] After the management system generates the corrected coating thickness, send the coating thickness control instruction to the Idesia polycarpa trunk coating device through wireless communication (such as LoRa, NB-IoT, 5G, etc.). After receiving the instruction, the trunk coating device adjusts the coating layer thickness to ensure that the thickness of the protective layer is consistent with the dynamically corrected thickness of the protective layer. The device uses technologies such as precise control spraying and intelligent pressure adjustment to ensure that the coating evenly covers the trunk. After the device completes the coating, use the sensor to detect whether the actual coating thickness meets the target value, and send the feedback data back to the management system. If the coating deviation exceeds the set threshold, automatically adjust the spraying parameters for secondary correction.

[0109] Example 4: The planting areas in this application can be classified and managed for different site conditions in the whole province (such as Guizhou Province).

[0110] Within the entire territory of Guizhou Province, the planting areas of Idesia polycarpa cover diverse and complex site conditions (such as mountains, hills, plains, karst landforms, etc.). In this embodiment, the original K-means clustering algorithm is extended, and multi-source data of the Geographic Information System (GIS) (including altitude, slope, aspect, soil type, average annual precipitation, light intensity, etc.) are combined to divide the whole province into several site condition clustering regions. The specific steps are as follows:

[0111] Collect site data across the province through remote sensing satellites, drones, and ground sensors, construct multi-dimensional feature vectors including geography, climate, and soil, divide the whole province into K site clustering regions, and for each site clustering region, combine the Idesia polycarpa growth model to generate differentiated coating thickness for protection layer, irrigation plans, and pest control strategies. For example, in the karst region, due to poor soil, the coating thickness for the protection layer is increased by 20%, and water-retaining agents are used for auxiliary irrigation.

[0112] Thus, precise zoning management of Idesia polycarpa planting across the province can be achieved, adapting to complex terrain and climate conditions. Through multi-dimensional data fusion, resource waste caused by differences in site conditions can be reduced, providing a scientific basis for the government to formulate regional ecological restoration and energy forest planning.

[0113] Example 5: On the basis of the sub-regions generated by secondary clustering, overlay the classification parameters of public welfare forests and commercial forests (such as planting density, mixed planting ratio), and dynamically adjust management measures:

[0114] Classification rules setting:

[0115] Commercial forest: The planting density is 27 - 33 plants per mu, adopting a pure forest mode, regularly fertilizing (nitrogen, phosphorus, and potassium compound fertilizer), pruning and shaping (twice a year), and increasing the coating thickness for the protection layer by 10%.

[0116] Public welfare forest: The planting density is 111 plants per mu, mixed with other native tree species (such as Masson pine), simplifying the fertilization measures (once every two years), reducing the pruning frequency to once a year, and reducing the coating thickness for the protection layer by 20%.

[0117] Through a multi-factor correlation model, combined with correction factors and forest type classification, optimize the fertilization amount and pruning intensity. For example, if the correction factor is high in the sub-region of the commercial forest, additional foliar fertilizer is added; in the sub-region of the public welfare forest, eco-friendly coating materials are preferentially used.

[0118] The commercial forest has significant economic benefits through refined management. The mixed planting mode of the public welfare forest enhances the stability of the ecosystem and improves the carbon sequestration capacity. Classification management reduces labor costs and achieves a balance between ecological and economic benefits.

[0119] Example 6: In this application, the dynamic correction logic of the correction factor and the coating thickness of the protective layer can also be extended to forest tending measures such as fertilization and pruning, and public welfare forests and commercial forests are distinguished:

[0120] Correction factor Is associated with the fertilization amount, and the expression is:

[0121] , where, Is the corrected fertilization amount, Is the fertilization amount before correction, Is the fertilization adjustment coefficient (the adjustment coefficient Is 0.5 in commercial forests, and the adjustment coefficient Is 0.2 in public welfare forests), and when the degree of soil salinization exceeds the degree threshold, commercial forests need to add organic fertilizer to improve the soil.

[0122] Commercial forests dynamically adjust the pruning frequency according to the crown width growth rate. If the correction factor is greater than the correction threshold, the pruning frequency increases to 3 times a year, while public welfare forests only prune diseased branches, and the pruning cost is incorporated into the evaluation model of the protective layer coating effect.

[0123] Through precise fertilization in commercial forests, the light transmittance of the crown width is optimized after pruning, and the photosynthetic efficiency is improved. Public welfare forests reduce human intervention, and the natural growth form is more adaptable to the needs of ecological restoration. The multi-measure linkage model improves resource utilization rate and effectively improves the comprehensive growth index of Idesia polycarpa.

[0124] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0125] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Among them, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the front and back associated objects, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0126] It should be understood that in various embodiments of this application, the magnitude of the serial numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0127] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0128] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for planting and managing Idesia polycarpa Maxim. forest trees, characterized in that: The management method includes the following steps: The management system collects soil data at the location of each Idesia polycarpa in the planting area, divides the planting area into several soil clustering regions through the K-means clustering algorithm, and further divides each soil clustering region into several sub-regions by considering the growth indicators of Idesia polycarpa; Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub-region, and establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment. The expression of the multi-factor correlation model is: , where is the correction factor, is the degree of soil salinization, is the environmental change index, is the chlorophyll content retention rate, , , are the weight coefficients, and the sum of the weight coefficients , , is 1; Generate a correction factor for each sub-region through a multi-factor correlation model, and dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor. The expression is: , where is the corrected coating thickness of the protective layer, is the initial coating thickness of the protective layer, is the correction factor, is the learning rate. After evaluating the coating effect of the protective layer for the sub-region, generate the corresponding management strategy.

2. The method for planting and managing Idesia polycarpa Maxim. forest trees according to claim 1, characterized in that: Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub-region. The changes in the growth indicators of Idesia polycarpa include the retention rate of chlorophyll content, the changes in soil indicators include the degree of soil salinization, and the environmental changes include the environmental change index.

3. The management method for planting and cultivating Idesia polycarpa Maxim. trees according to claim 2, wherein: Establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and environment, and generate a correction factor for each sub-region through the multi-factor correlation model, including the following steps: Establish a multi-factor correlation model based on the retention rate of chlorophyll content, the degree of soil salinization, and the environmental change index. The multi-factor correlation model calculates the weighted values of the retention rate of chlorophyll content, the degree of soil salinization, and the environmental change index to generate a correction factor for each sub-region.

4. A method for planting and managing Idesia polycarpa Maxim. forest trees according to claim 3, characterized in that: Dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor, including the following steps: After obtaining the correction factor of the sub-region, compare the correction factor with the correction threshold. If the correction factor of the sub-region is less than the correction threshold, it is analyzed that there is no need to dynamically correct the coating thickness of the protective layer of Idesia polycarpa in this sub-region. If the correction factor of the sub-region is greater than or equal to the correction threshold, it is analyzed that it is necessary to dynamically correct the coating thickness of the protective layer of Idesia polycarpa in this sub-region; Dynamically correct the initial coating thickness of the protective layer of the sub-region based on the correction factor to obtain the corrected coating thickness of the protective layer.

5. A method for planting and managing Idesia polycarpa Maxim. forest trees according to claim 4, characterized in that: After evaluating the coating effect of the protective layer of the sub-region, generate corresponding management strategies, including the following steps: Adjust the learning rate based on the overall effect score , and the adjustment algorithm is as follows: , where is the adjusted learning rate, is the learning rate before adjustment, is the cost deviation of the protective layer coating after normalization processing, is the retention rate of chlorophyll content after normalization processing, is the overall effect score, is the score threshold.

6. The Idesia polycarpa forest planting and management method according to claim 5, characterized in that: The management system collects soil data at the location of each Idesia polycarpa in the planting area, and divides the planting area into several soil clustering regions through the K-means clustering algorithm, including the following steps: The management system obtains the soil data at the location of each Idesia polycarpa in the planting area through sensors, including soil humidity, soil pH value, soil organic matter content, and nitrogen, phosphorus, and potassium element content: Suppose there are N sampling points in the planting area, obtain the soil data of each sampling point, and construct a feature vector; Randomly select the feature vectors of K sampling points as the initial clustering centers, calculate the distances from each sample point to the K initial clustering centers according to the Euclidean distance algorithm, assign each sampling point to the soil clustering region where the initial clustering center with the minimum distance is located, and calculate the mean value of the feature vectors of each soil clustering region as the new centroid; Repeat the steps of sampling point allocation and new centroid calculation. When the change amount of the new centroid of all soil clustering regions is less than the change threshold in any one time, it is judged that the convergence condition is met, and K soil clustering regions are output.

7. A method for planting and managing Idesia polycarpa Maxim. trees according to claim 6, characterized in that: Suppose there are N sampling points in the planting area, soil data of each sampling point is obtained, and a feature vector is constructed: , where represents the soil feature vector of the -th sampling point, successively represent different properties of the soil, and M represents the number of detected soil properties.

8. A method for planting and managing Idesia polycarpa Maxim. forest trees according to claim 7, characterized in that: Randomly select the feature vectors of K sampling points as the initial clustering centers, and calculate the distance from each sample point to the K initial clustering centers according to the Euclidean distance algorithm. The expression is: , where is the distance from the j-th sampling point to the i-th initial clustering center, M represents the number of detected soil properties, is the m-th soil property value of the j-th sampling point, represents the m-th soil property value of the i-th initial clustering center; Calculate the mean of the feature vectors for each soil clustering region as the new centroid, with the expression: , where in the formula, is the new centroid of the i-th soil clustering region, represents the number of sampling points in the i-th soil clustering region, represents the soil feature vector of the j-th sampling point.

9. The method for planting and managing Idesia polycarpa Maxim. forest trees according to claim 8, wherein: Further divide each soil clustering region into several sub-regions by considering the growth indicators of Idesia polycarpa, including the following steps: Within each soil clustering region, collect the growth indicators of Idesia polycarpa, including tree height, crown width, trunk diameter, number of leaves, leaf color index, and root length; Construct a feature vector for the growth index: , where represents the growth index feature vector of the th Idesia polycarpa, successively represent different attributes of Idesia polycarpa, represents the number of detected growth indices; Randomly select the feature vectors of K Idesia polycarpa as the initial clustering centers. Calculate the distances from each Idesia polycarpa in the soil clustering region to the K initial clustering centers according to the Euclidean distance algorithm, and assign each Idesia polycarpa to the sub-region where the initial clustering center with the minimum distance is located. Calculate the mean of the growth indicator feature vectors of each sub-region as the new centroid; Repeat the steps of sampling point assignment and new centroid calculation. When the change amount of the new centroid in all sub-regions is less than the change threshold in any iteration, it is judged that the convergence condition is met, and K subdivided sub-regions are output in the soil clustering region.

10. A management system for planting and managing Idesia polycarpa forests, which is used to implement the management method described in any one of claims 1-9, and is characterized in that: It includes a subdivision clustering module, a data acquisition module, a calculation module, and a dynamic correction module; Subdivision clustering module: Collect the soil data at the location of each Idesia polycarpa in the planting area, divide the planting area into several soil clustering regions through the K-means clustering algorithm, and further divide each soil clustering region into several sub-regions considering the growth indicators of Idesia polycarpa; Data acquisition module: Regularly collect the changes in the growth indicators of Idesia polycarpa, the changes in soil indicators, and the environmental changes in each sub-region; Calculation module: Establish a multi-factor correlation model by combining the characteristic data of Idesia polycarpa, soil, and the environment. The expression of the multi-factor correlation model is: , where is the correction factor, is the degree of soil salinization, is the environmental change index, is the chlorophyll content retention rate, , , are the weight coefficients, and the sum of the weight coefficients , , is 1. Generate a correction factor for each sub-region through the multi-factor correlation model; Dynamic correction module: Dynamically correct the coating thickness of the protective layer for each sub-region based on the correction factor. After evaluating the coating effect of the protective layer for the sub-region, generate corresponding management strategies.

Images