Tree growth intelligent monitoring and lesion early warning system

Abstract

The invention relates to the technical field of plant monitoring, in particular to a tree growth intelligent monitoring and lesion early warning system which comprises a data acquisition module, a growth state analysis module, a lesion risk assessment module, an environmental adaptability assessment module and a comprehensive early warning analysis module. Wherein the data acquisition module is used for acquiring tree growth data and environment data in real time; the growth state analysis module is used for evaluating the current growth state of the tree; the lesion risk assessment module is used for detecting whether the trees have lesion symptoms or not; the environment adaptability evaluation module is used for judging whether the tree faces an environment adaptability problem or not; and the comprehensive early warning analysis module is used for comprehensively judging whether the trees have health threats or not. According to the invention, through comprehensive real-time collected tree growth data, environment data and lesion image analysis, early warning and intelligent management of tree health are realized, the monitoring efficiency is significantly improved, and potential growth problems and lesion risks are effectively prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of plant monitoring, and particularly to an intelligent monitoring and disease warning system for tree growth. Background Art

[0002] In the fields of modern agriculture, forestry production, and forest ecological protection, the monitoring of tree growth and disease warning are crucial for ensuring the sustainability and health of forest resources; with the impacts of climate change, environmental pollution, and pests and diseases, the growth and health conditions of trees are facing more and more challenges; traditional tree health detection methods mainly rely on manual inspections or regular checks, which have problems such as long monitoring cycles, high labor costs, and low efficiency; in addition, the real-time collection and analysis of various physiological data and environmental data of tree growth are still difficult to achieve accurately and efficiently; although some existing sensors and image recognition technologies can provide data support to a certain extent, there is a lack of a comprehensive and real-time monitoring scheme and an intelligent analysis system that can effectively process these data.

[0003] Therefore, there are obvious technical gaps in the prior art in comprehensively evaluating the growth status, environmental adaptability, and disease risks of trees; traditional monitoring methods cannot effectively predict and warn the growth status, environmental changes, and potential diseases of trees in real time and comprehensively, and often cannot detect the health threats faced by trees in the first time, resulting in damaged tree growth or spread of diseases. Summary of the Invention

[0004] Based on the above purpose, the present invention provides an intelligent monitoring and disease warning system for tree growth.

[0005] An intelligent monitoring and disease warning system for tree growth includes a data collection module, a growth status analysis module, a disease risk assessment module, an environmental adaptability assessment module, and a comprehensive warning analysis module; wherein: Data collection module: Through the deployed sensor network, it collects tree growth data and environmental data in real time, and collects tree appearance images through a high-resolution camera. Growth status analysis module: Based on the tree growth data collected by the data collection module, it calculates the growth rate, health degree, and growth trend of the tree, and evaluates the current growth status of the tree by comparing with the normal growth mode. Disease risk assessment module: It uses image recognition technology to analyze the tree appearance images collected by the data collection module, detects whether there are disease symptoms on the tree, and evaluates the disease risk of the tree. Environmental adaptability assessment module: Combining the environmental data provided by the data collection module and the tree growth status evaluated by the growth status analysis module, it calculates the impact of environmental changes on tree growth, and judges whether the tree faces environmental adaptability problems. Comprehensive Early Warning Analysis Module: It is used to comprehensively analyze the growth status analysis results output by the growth status analysis module, the lesion risk assessment results output by the lesion risk assessment module, and the environmental adaptability assessment results output by the environmental adaptability assessment module, determine whether there is a health threat to the tree, and issue a warning signal when necessary.

[0006] Optionally, the data acquisition module includes a tree growth data acquisition unit, an environmental data acquisition unit, and a tree appearance image acquisition unit; among them: Tree Growth Data Acquisition Unit: It includes a height sensor, a diameter sensor, and a leaf coverage area sensor, and is used to collect tree growth data in real time; among them, the height sensor is used to measure the height of the tree; the diameter sensor is used to measure the diameter of the tree trunk; the leaf coverage area sensor is used to calculate the coverage area of the tree leaves; Environmental Data Acquisition Unit, including a soil humidity sensor, an air temperature and humidity sensor, a light intensity sensor, and a precipitation sensor; among them, the soil humidity sensor is used to detect the soil humidity in the tree growth environment; the air temperature and humidity sensor is used to detect the air temperature and humidity around the tree; the light intensity sensor is used to measure the light intensity of the environment where the tree is located in real time; the precipitation sensor is used to collect precipitation data around the tree in real time; Tree Appearance Image Acquisition Unit: It includes a high-definition camera, and the high-definition camera is configured to have no less than 30 million pixels, and the camera angle is set at a 45-degree angle to the tree trunk, and is used to take high-definition pictures of the tree leaves, bark, and the surface of the tree trunk to obtain the appearance state data of the tree.

[0007] Optionally, the growth status analysis module includes a growth rate calculation unit, a health assessment unit, a growth trend prediction unit, and a growth status comparison unit; among them: Growth Rate Calculation Unit: By processing the tree growth data in the data acquisition module, calculate the growth rate of the tree within a specified time; Health Assessment Unit: It is used to calculate the health index of the tree according to the change of the leaf coverage area in the tree growth data, combined with the environmental data; Growth Trend Prediction Unit: Utilize the historical growth data of the tree, combined with the growth data collected in real time, and predict the future growth trend of the tree based on linear regression analysis; Growth Status Comparison Unit: Compare and analyze the growth trend predicted by the growth trend prediction unit with the normal growth mode, and through the comparison and analysis, evaluate the current growth status of the tree and judge whether it deviates from the normal growth mode.

[0008] Optionally, the growth trend prediction unit includes: Data collection and preprocessing: Collect historical growth data of trees, including tree height, diameter, and leaf coverage area, and preprocess the historical growth data to eliminate outliers and noise; Establish a linear regression model: Based on the preprocessed historical growth data, use a linear regression model to predict the future growth trend of trees. The expression of the linear regression model is: , where is the predicted future growth parameter of the tree, is the height of the tree at the current moment, is the diameter of the tree at the current moment, is the leaf coverage area of the tree at the current moment, are the coefficients of the regression model, is the error term; Model training and coefficient optimization: Optimize the coefficients in the regression model through the least squares method. The expression of the least squares method is: , where is the actual tree growth parameter of the th sample, are the tree height, diameter, and leaf coverage area of the th sample respectively, is the number of training samples; Prediction of future growth trend: Apply the optimized regression model to the real-time collected tree growth data to predict the future growth trend of the tree.

[0009] Optionally, the growth state comparison unit includes: Obtain normal growth pattern data: Collect normal growth pattern data of trees and establish a mathematical model of the normal growth pattern. The expression is: , where is the predicted growth parameter of the tree under normal growth conditions, are the initial tree height, trunk diameter, and leaf coverage area under normal growth conditions, are the regression coefficients, is the error term; Calculate the deviation between the predicted value and the normal growth pattern: Compare the predicted tree growth trend with the normal growth pattern and calculate the deviation between the two . The formula is: , where is the deviation value between the predicted growth trend and the normal growth pattern; Judge whether it deviates from the normal growth pattern: Judge whether the tree deviates from the normal growth pattern according to the deviation value . The specific judgment condition is: where is a preset threshold value used to determine whether the deviation is significant. If the condition is met, it is determined that the tree deviates from the normal growth pattern.

[0010] Optionally, the lesion risk assessment module includes an image preprocessing unit, a lesion feature extraction unit, a lesion risk assessment unit, and a lesion risk judgment unit; where: Image preprocessing unit: used to preprocess the tree appearance image provided by the data acquisition module, including noise removal and contrast enhancement, to enhance the image quality and details; Lesion feature extraction unit: based on a convolutional neural network, extracts features from the preprocessed image, and identifies the area, shape, and color of the lesion area in the image; let the area of the lesion area be , the shape feature of the lesion area is , the color feature of the lesion area is ; Lesion risk assessment unit: according to the extracted lesion features, assesses the lesion risk of the tree. The calculation formula for the lesion risk is: , where is the lesion risk value of the tree, is the corresponding weighting coefficient; Lesion risk judgment unit: used to compare the lesion risk value calculated in the lesion risk assessment unit with the preset lesion risk threshold to determine whether the tree has a lesion risk. If , it is determined that the tree has a lesion risk; otherwise, the tree is in a normal health state.

[0011] Optionally, the environmental adaptability assessment module includes an environmental data analysis unit and a tree growth impact calculation unit; where: Environmental data analysis unit: by processing the environmental data provided by the data acquisition module, including soil humidity, air temperature and humidity, light intensity, and precipitation, analyzes the changing trend of the current environmental conditions, and calculates the change rate of the environmental parameters to evaluate the potential impact of environmental fluctuations on tree growth; Tree growth impact calculation unit: used to evaluate the specific impact of environmental changes on tree growth according to the tree growth state evaluated by the growth state analysis module, and combine the environmental change trend calculated by the environmental data analysis unit, and determine whether environmental fluctuations will cause the tree growth rate to slow down or the health level to decline.

[0012] Optionally, the environmental data analysis unit includes: Environmental data standardization processing: obtains the environmental data of soil humidity, air temperature and humidity, light intensity, and precipitation from the data acquisition module, and performs standardization processing on the environmental data to ensure the comparability of data with different units and magnitudes; Calculate the change rate of environmental parameters: By calculating the change rate of standardized environmental data, evaluate the fluctuation range of environmental conditions over a period of time. The change rate of environmental parameters is calculated by the difference method, and the formula is: , where is the environmental data at the current moment, is the environmental data at the previous moment, is the change rate of environmental parameters; Evaluate the potential impact of environmental fluctuations on tree growth: By comparing the change rate of the current environmental parameters with a preset threshold, judge whether the amplitude of environmental changes will have a potential impact on tree growth; if the change rate of a certain environmental parameter exceeds the set threshold, it is considered that this environmental change will affect tree growth.

[0013] Optionally, the tree growth impact calculation unit includes: Obtain tree growth status data: Obtain the tree growth status data from the growth status analysis module, and evaluate the health of the tree by calculating the deviation between the growth index of the tree and the normal growth mode. The formula is: , where is the actual growth index of the tree, is the ideal growth index under the normal growth mode, is the health of the tree; Calculate the tree growth rate under environmental changes: Assume that the impact of environmental changes on the growth rate is adjusted by a multiplication factor, and the calculation formula is: , where is the adjusted tree growth rate, is the baseline growth rate, is the sensitivity coefficient of environmental changes to the growth rate, is the amount of environmental change; Judge the impact of environmental fluctuations on tree growth: According to the calculated changes in growth rate and health, judge whether environmental fluctuations will cause the tree growth rate to slow down or the health to decline; the specific judgment conditions include: Judgment condition 1: If the change in growth rate caused by environmental fluctuations slows down by more than 5%, it is considered that the tree growth rate is affected by the environment; Judgment condition 2: If the health of the tree drops by more than 20%, it is considered that the tree growth is adversely affected by the environment, resulting in a decline in the tree health status.

[0014] Optionally, the comprehensive warning analysis module includes a growth status comprehensive evaluation unit, a lesion risk result receiving unit, a comprehensive health threat assessment unit, a comprehensive health threat assessment unit, and a warning signal output unit; among them: Growth Status Comprehensive Evaluation Unit: It is used to receive the tree growth status data output by the growth status analysis module, including growth rate, health, and growth trend, and comprehensively evaluate the growth status by the weighted average method. The formula is: , where is the comprehensive evaluation value of tree growth, and are the weight values of growth rate, health, and growth trend respectively, is the weight of each factor; Lesion Risk Result Receiving Unit: It is used to receive the tree lesion risk assessment result output by the lesion risk assessment module ; Environmental Adaptability Comprehensive Evaluation Unit: It is used to receive the tree adaptability data output by the environmental adaptability assessment module, combine the environmental change trend calculated by the environmental data analysis unit, evaluate the impact of environmental change on tree growth, and calculate the comprehensive evaluation value of environmental adaptability risk; The formula is: , where is the actual impact of environmental change on tree growth, is the maximum value of environmental impact, is the environmental adaptability risk assessment value; Comprehensive Health Threat Evaluation Unit: It is used to weight and integrate the evaluation results output by the growth status comprehensive evaluation unit, the lesion risk comprehensive evaluation unit, and the environmental adaptability comprehensive evaluation unit, and comprehensively calculate the health threat evaluation value of the tree. The formula is: , where is the health threat evaluation value of the tree, is the comprehensive evaluation value of growth status, is the lesion risk value of the tree, is the environmental adaptability risk assessment value, , and are the corresponding weights respectively; Early Warning Signal Output Unit: It is used to set a threshold according to the health threat evaluation value output by the comprehensive health threat evaluation unit. When the health threat evaluation value of the tree exceeds the preset threshold, an early warning signal is automatically triggered to indicate that the tree is facing a health threat.

[0015] Advantages of the present invention: The present invention can monitor the health status and growth trend of trees in real time and accurately by comprehensively integrating tree growth data, environmental data, and analysis of lesion risk images. Compared with the prior art, it can automatically obtain multi-dimensional data and deeply mine and comprehensively evaluate these data through an intelligent analysis system, achieving comprehensive monitoring of tree health. This system can not only obtain growth status indicators such as the growth rate and health of trees in real time but also analyze the impact of the environment on tree growth according to the trend of environmental changes, thereby discovering potential growth problems earlier.

[0016] The present invention can accurately detect the lesion risk of trees, evaluate its health threat, and issue early warning signals in a timely manner under environmental fluctuations or abnormal growth by combining advanced image recognition technology. This system has an intelligent early warning function and can conduct comprehensive analysis based on the evaluation results of tree growth status and environmental adaptability to predict in advance the risks that may lead to growth slowdown or lesion occurrence, thus providing strong support for the maintenance and management of trees. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only those of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 Schematic diagram of the intelligent monitoring and lesion early warning system according to an embodiment of the present invention; Figure 2 Schematic diagram of the growth status analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0020] It should be pointed out that in the specification, references to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment includes such specific features, structures, or characteristics. Additionally, when combining embodiments to describe specific features, structures, or characteristics, implementing such features, structures, or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0021] Generally, terms can be understood at least in part from their 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 property in a singular sense, or can be used to describe a combination of features, structures, or properties in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather can alternatively, at least in part depending on the context, allow for the existence of other factors that are not necessarily explicitly described.

[0022] As Figure 1 - Figure 2 shown, a smart monitoring and disease warning system for tree growth includes a data acquisition module, a growth status analysis module, a disease risk assessment module, an environmental adaptability assessment module, and a comprehensive warning analysis module; wherein: Data acquisition module: Through the deployed sensor network, it collects tree growth data and environmental data in real time, and collects tree appearance images through a high-resolution camera. The tree growth data includes the height of the tree, the trunk diameter, and the leaf coverage area; the environmental data includes soil humidity, air temperature and humidity, light intensity, and precipitation; Growth status analysis module: Based on the tree growth data collected by the data acquisition module, it calculates the growth rate, health, and growth trend of the tree, and evaluates the current growth status of the tree by comparing with the normal growth mode; Disease risk assessment module: It uses image recognition technology to analyze the tree appearance images collected by the data acquisition module, detects whether there are disease symptoms (such as withering, spots, cracks, etc.) on the tree, and evaluates the disease risk of the tree; Environmental adaptability assessment module: Combining the environmental data provided by the data acquisition module and the tree growth status evaluated by the growth status analysis module, it calculates the impact of environmental changes on tree growth and determines whether the tree faces environmental adaptability problems; Comprehensive warning analysis module: It is used to comprehensively analyze the growth status analysis results output by the growth status analysis module, the disease risk assessment results output by the disease risk assessment module, and the environmental adaptability assessment results output by the environmental adaptability assessment module, determine whether there are health threats to the tree, and issue a warning signal when necessary.

[0023] The data acquisition module includes a tree growth data acquisition unit, an environmental data acquisition unit, and a tree appearance image acquisition unit; wherein: Tree Growth Data Acquisition Unit: It includes a height sensor, a diameter sensor, and a leaf coverage area sensor, which are used to collect tree growth data in real time. Among them, the height sensor is used to measure the height of the tree and provide real-time feedback on the growth changes of the tree. The diameter sensor is used to measure the diameter of the tree trunk, which is an important indicator of tree growth. The leaf coverage area sensor is used to calculate the coverage area of the tree leaves and evaluate the health status and growth ability of the tree. Environmental Data Acquisition Unit, including a soil moisture sensor, an air temperature and humidity sensor, a light intensity sensor, and a precipitation sensor. Among them, the soil moisture sensor is used to detect the soil moisture in the tree growth environment and provide real-time feedback on the impact of soil moisture on tree growth. The air temperature and humidity sensor is used to detect the air temperature and humidity around the tree and evaluate their impact on tree growth. The light intensity sensor is used to measure the light intensity in the tree environment in real time and analyze its impact on tree photosynthesis. The precipitation sensor is used to collect precipitation data around the tree in real time to determine whether the water is sufficient. Tree Appearance Image Acquisition Unit: It includes a high-definition camera with a pixel count of no less than 30 million. The camera angle is set at a 45-degree angle to the tree trunk and is used to take high-definition photos of the tree leaves, bark, and trunk surface to obtain the appearance state data of the tree. Through the combination of the above units, the data acquisition module can accurately collect tree growth data and environmental data, and collect the appearance images of the tree through a high-resolution camera, providing comprehensive and real-time basic data for subsequent growth state analysis, disease risk assessment, and environmental adaptability assessment.

[0024] The growth state analysis module includes a growth rate calculation unit, a health assessment unit, a growth trend prediction unit, and a growth state comparison unit. Among them: Growth Rate Calculation Unit: By processing the tree growth data in the data acquisition module, calculate the growth rate of the tree within a specified time. The growth rate is based on the tree height change rate and the tree trunk diameter change rate. The calculation formula is: ; ; where is the tree height change speed, is the current tree height, is the initial tree height, is the time period; is the tree diameter change speed, is the current tree trunk diameter, is the initial tree trunk diameter, is the time period. By calculating the growth rate of the tree, the annual average growth rate of the tree can be obtained. Health Assessment Unit: It is used to calculate the health index of trees according to the change of leaf coverage area in tree growth data and in combination with environmental data. The health index comprehensively considers factors such as the leaf coverage area, soil humidity, and light intensity of the tree. The formula for calculating the health index is: , where is the health index of the tree, is the current leaf coverage area, is the initial leaf coverage area, is the health coefficient weighted and corrected according to the soil humidity and the light intensity ; Growth Trend Prediction Unit: It uses the historical growth data of trees and combines the growth data collected in real time to predict the future growth trend of trees based on linear regression analysis; Growth Status Comparison Unit: It compares and analyzes the growth trend predicted by the Growth Trend Prediction Unit with the normal growth pattern. The normal growth pattern is generated based on a large amount of historical data and serves as the standard for the normal growth of trees. Through the comparative analysis, it evaluates the current growth status of the trees and determines whether they deviate from the normal growth pattern; Through each unit of the above growth status analysis module, it can calculate and evaluate the growth rate, health, and growth trend of trees in real time, and then accurately determine whether the trees are within the normal growth range. When the growth of the trees deviates from the normal pattern, it can send out a warning signal in a timely manner, thus helping the management personnel to take corresponding measures to ensure the healthy growth of the trees.

[0025] The Growth Trend Prediction Unit includes: Data Collection and Preprocessing: Collect the historical growth data of trees, including the height, diameter, and leaf coverage area of the trees, and preprocess the historical growth data to eliminate outliers and noise to ensure the stationarity and consistency of the data. The data preprocessing process includes standardization processing, and the formula is as follows: , where is the original data, is the data mean, is the data standard deviation, is the standardized data; Establish a Linear Regression Model: Based on the preprocessed historical growth data, use a linear regression model to predict the future growth trend of trees. The expression of the linear regression model is: , where is the predicted future growth parameter of the tree (such as height, diameter, etc.), is the height of the tree at the current moment, is the diameter of the tree at the current moment, is the leaf coverage area of the tree at the current moment, is the coefficient of the regression model, is the error term, representing the residuals in model fitting; Model training and coefficient optimization: Optimize the coefficients in the regression model through the least squares method. The expression of the least squares method is: , where is the actual tree growth parameter of the -th sample, are respectively the tree height, diameter and leaf coverage area of the -th sample, is the number of training samples. This method obtains the optimal regression coefficients by minimizing the sum of squared errors, thereby improving prediction accuracy; Future growth trend prediction: Apply the optimized regression model to the real-time collected tree growth data to predict the future growth trend of the tree; Through the above steps, the growth trend prediction unit can accurately predict the future growth trend of the tree and provide a basis for subsequent health warning and growth status analysis.

[0026] The growth status comparison unit includes: Obtain data of normal growth mode: Collect data of the normal growth mode of the tree and establish a mathematical model of the normal growth mode, where the expression is: , where is the predicted growth parameter (such as height, diameter, etc.) of the tree under normal growth conditions, are the initial tree height, trunk diameter and leaf coverage area under normal growth conditions, is the regression coefficient, is the error term; Calculate the deviation between the predicted value and the normal growth mode: Compare the predicted tree growth trend with the normal growth mode and calculate the deviation between the two , and the formula is: , where is the deviation value between the predicted growth trend and the normal growth mode; Judge whether it deviates from the normal growth mode: Judge whether the tree deviates from the normal growth mode according to the deviation value , and the specific judgment condition is: where is a preset threshold for determining whether the deviation is significant. If the condition is met, it is determined that the tree deviates from the normal growth mode; Through the above steps, the growth status comparison unit can effectively detect whether the tree deviates from the normal growth mode and provide data support for subsequent warning analysis.

[0027] The lesion risk assessment module includes an image preprocessing unit, a lesion feature extraction unit, a lesion risk assessment unit, and a lesion risk judgment unit; among them: Image preprocessing unit: It is used to preprocess the tree appearance images provided by the data acquisition module, including noise removal and contrast enhancement, to enhance the image quality and details; The image preprocessing process includes the following steps: Noise removal: Gaussian filtering is used to smooth the image, and the formula is as follows: , where is the original image, is the Gaussian filter kernel, is the filtered image; Contrast enhancement: The contrast of the image is improved through histogram equalization, and the formula is as follows: , where is the inverse transform of histogram equalization, is the enhanced image.

[0028] Lesion feature extraction unit: Based on a convolutional neural network, it extracts features from the preprocessed images, and identifies the area, shape and color of the lesion areas in the images; Let the area of the lesion area be , the shape feature of the lesion area be , and the color feature of the lesion area be ; Lesion risk assessment unit: According to the extracted lesion features, it assesses the lesion risk of the trees. The calculation formula for the lesion risk is: , where is the lesion risk value of the tree, is the corresponding weighting coefficient, reflecting the influence of different features on the lesion risk; Lesion risk judgment unit: It is used to compare the lesion risk value calculated in the lesion risk assessment unit with the preset lesion risk threshold to judge whether the tree has a lesion risk. If , it is judged that the tree has a lesion risk; otherwise, the tree is in a normal health state; The above units accurately analyze the tree appearance images through image recognition technology, effectively evaluate the lesion risk of the trees, and provide a reliable basis for lesion early warning.

[0029] The environmental adaptability assessment module includes an environmental data analysis unit and a tree growth impact calculation unit; Among them: Environmental data analysis unit: By processing the environmental data provided by the data acquisition module, including soil humidity, air temperature and humidity, light intensity and precipitation, it analyzes the change trend of the current environmental conditions, and calculates the change rate of the environmental parameters to evaluate the potential impact of environmental fluctuations on tree growth; Tree growth impact calculation unit: Used to evaluate the specific impact of environmental changes on tree growth based on the tree growth status evaluated by the growth status analysis module and the environmental change trend calculated by the environmental data analysis unit, and to determine whether environmental fluctuations will lead to a slowdown in tree growth rate or a decline in health; Through the above units, the environmental adaptability evaluation module can accurately calculate the impact of environmental changes on tree growth and effectively determine whether the tree faces environmental adaptability problems, thus providing important decision-making support for the health maintenance of the tree.

[0030] The environmental data analysis unit includes: Environmental data standardization processing: Obtain environmental data such as soil humidity, air temperature and humidity, light intensity, and precipitation from the data acquisition module, and perform standardization processing on the environmental data to ensure the comparability of data with different units and magnitudes; Calculate the change rate of environmental parameters: By calculating the change rate of standardized environmental data, evaluate the fluctuation range of environmental conditions over a period of time. The change rate of environmental parameters is calculated by the difference method, and the formula is: , where, is the environmental data at the current moment, is the environmental data at the previous moment, is the change rate of environmental parameters; Evaluate the potential impact of environmental fluctuations on tree growth: By comparing the change rate of the current environmental parameters with the preset threshold, determine whether the amplitude of environmental changes will have a potential impact on tree growth; If the change rate of a certain environmental parameter exceeds the set threshold, it is considered that this environmental change will affect tree growth; According to different change amplitudes, set the following judgment conditions to evaluate whether the tree is affected: Judgment condition 1: If the change rate of soil humidity exceeds 10% and lasts for more than 3 hours, it may lead to insufficient water supply to the tree roots, thereby affecting the tree growth rate and possibly resulting in a slowdown in growth; Judgment condition 2: If the change rate of air temperature and humidity exceeds 5°C and lasts for more than 6 hours, it may cause the tree to be unable to adapt to temperature changes in the short term, affecting the tree's photosynthesis, and there may be a risk of leaf withering or growth stagnation; Judgment condition 3: If the change rate of light intensity exceeds 15% and lasts for more than 12 hours, it may lead to a decrease in the photosynthesis efficiency of the tree, thereby affecting the health of the tree, and there may be yellowing of leaves or abnormal growth; Judgment condition 4: If the change rate of precipitation exceeds 20% and lasts for more than 24 hours, it may cause the soil to be too wet or too dry, affecting the water absorption capacity of the tree roots, and there may be root rot or drought phenomena, resulting in abnormal tree growth.

[0031] The tree growth impact calculation unit includes: Obtain tree growth status data: Obtain the tree growth status data from the growth status analysis module, and evaluate the tree health by calculating the deviation of the tree growth indicators (such as trunk diameter, tree height, etc.) from the normal growth pattern. The formula is: , where is the actual tree growth indicator (such as trunk diameter, tree height, etc.), is the ideal growth indicator under the normal growth pattern, is the tree health; Calculate the tree growth rate under environmental changes: Combine the environmental change trend provided by the environmental data analysis unit to calculate the impact of environmental changes on the tree growth rate. Environmental changes may have positive or negative impacts on tree growth. Assume that the impact of environmental changes on the growth rate is adjusted by a multiplication factor. The calculation formula is: , where is the adjusted tree growth rate, is the baseline growth rate (the growth rate under ideal environmental conditions), is the sensitivity coefficient of environmental changes to the growth rate, is the amount of environmental change (such as soil humidity, light intensity change, etc.); Judge the impact of environmental fluctuations on tree growth: According to the calculated changes in growth rate and health, judge whether environmental fluctuations will cause the tree growth rate to slow down or the tree health to decline. The specific judgment conditions include: Judgment condition 1: If the slowdown in the growth rate change caused by environmental fluctuations exceeds 5%, it is considered that the tree growth rate is affected by the environment; Judgment condition 2: If the tree health decline exceeds 20%, it is considered that the tree growth is adversely affected by the environment, resulting in a decline in the tree health status.

[0032] The comprehensive warning analysis module includes a growth status comprehensive evaluation unit, a lesion risk result receiving unit, a comprehensive health threat assessment unit, a comprehensive health threat assessment unit, and a warning signal output unit; among them: Growth status comprehensive evaluation unit: Used to receive the tree growth status data output by the growth status analysis module, including growth rate, health, and growth trend, and comprehensively evaluate the growth status by the weighted average method. The formula is: , where is the comprehensive evaluation value of tree growth, and are the weight values of growth rate, health, and growth trend respectively, are the weights of each factor, and ; Lesion risk result receiving unit: used to receive the tree lesion risk assessment result output by the lesion risk assessment module ; Comprehensive environmental adaptability assessment unit: used to receive the tree adaptability data output by the environmental adaptability assessment module, combine with the environmental change trend calculated by the environmental data analysis unit, evaluate the impact of environmental changes on tree growth, and calculate the comprehensive assessment value of environmental adaptability risk; the formula is: , where is the actual impact of environmental changes on tree growth, is the maximum value of environmental impact, is the environmental adaptability risk assessment value; Comprehensive health threat assessment unit: used to perform weighted integration on the assessment results output by the comprehensive growth status assessment unit, the comprehensive lesion risk assessment unit, and the comprehensive environmental adaptability assessment unit, and comprehensively calculate the health threat assessment value of the tree. The formula is: , where is the health threat assessment value of the tree, is the comprehensive growth status assessment value, is the tree lesion risk value, is the environmental adaptability risk assessment value, , and are the corresponding weights respectively, and is the weighting coefficient; Warning signal output unit: used to set a threshold according to the health threat assessment value output by the comprehensive health threat assessment unit. When the health threat assessment value of the tree exceeds the preset threshold, an early warning signal is automatically triggered to indicate that the tree is facing a health threat; the above units can accurately evaluate whether the tree is facing a health threat by comprehensively analyzing the growth status, lesion risk, and environmental adaptability assessment results, and give early warnings about possible growth problems, lesions, or environmental adaptability problems, thereby improving the efficiency and accuracy of tree management, reducing tree losses caused by ignoring environmental changes or lesion signs, and ensuring the healthy and continuous growth of trees.

[0033] The present invention covers any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of the present invention. For the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without these detailed descriptions. In addition, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0034] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A tree growth intelligent monitoring and disease early warning system, characterized in that: It includes data acquisition module, growth status analysis module, pathological risk assessment module, environmental adaptability assessment module and comprehensive early warning analysis module; among which: Data collection module: collects tree growth data and environmental data in real time through the deployed sensor network, and collects tree appearance images through high-resolution cameras; Growth status analysis module: Based on the tree growth data collected by the data acquisition module, the growth rate, health and growth trend of the trees are calculated, and the current growth status of the trees is evaluated by comparing with the normal growth pattern; Disease risk assessment module: Use image recognition technology to analyze tree appearance images collected by the data acquisition module, detect whether the trees have disease symptoms, and assess the disease risk of the trees; Environmental adaptability assessment module: Combines the environmental data provided by the data acquisition module and the tree growth status assessed by the growth status analysis module to calculate the impact of environmental changes on tree growth and determine whether the trees are facing environmental adaptability issues; Comprehensive early warning analysis module: used to conduct a comprehensive analysis of the growth status analysis results output by the growth status analysis module, the lesion risk assessment results output by the lesion risk assessment module, and the environmental adaptability assessment results output by the environmental adaptability assessment module, to determine whether there is a health threat to the trees and issue an early warning signal when necessary.

2. The tree growth intelligent monitoring and disease early warning system according to claim 1 is characterized in that: The data acquisition module includes a tree growth data acquisition unit, an environmental data acquisition unit and a tree appearance image acquisition unit; wherein: Tree growth data collection unit: including a height sensor, a diameter sensor and a leaf coverage area sensor, which are used to collect tree growth data in real time; wherein, the height sensor is used to measure the height of the tree; the diameter sensor is used to measure the diameter of the trunk; and the leaf coverage area sensor is used to calculate the coverage area of ​​the tree leaves; The environmental data acquisition unit includes a soil moisture sensor, an air temperature and humidity sensor, a light intensity sensor, and a precipitation sensor; wherein the soil moisture sensor is used to detect the soil moisture in the tree growth environment; the air temperature and humidity sensor is used to detect the air temperature and humidity around the tree; the light intensity sensor is used to measure the light intensity of the tree environment in real time; and the precipitation sensor is used to collect precipitation data around the tree in real time; Tree appearance image acquisition unit: includes a high-definition camera with a configuration of no less than 30 million pixels. The camera angle is set to 45 degrees to the tree trunk, which is used to take high-definition photos of tree leaves, bark and trunk surfaces to obtain tree appearance status data.

3. The tree growth intelligent monitoring and disease early warning system according to claim 1 is characterized in that: The growth status analysis module includes a growth rate calculation unit, a health assessment unit, a growth trend prediction unit and a growth status comparison unit; wherein: Growth rate calculation unit: calculates the growth rate of trees within a specified time by processing the tree growth data in the data acquisition module; Health evaluation unit: used to calculate the health index of trees based on the changes in leaf coverage area in tree growth data and environmental data; Growth trend prediction unit: using historical tree growth data combined with real-time growth data to predict future tree growth trends based on linear regression analysis; Growth status comparison unit: compare and analyze the growth trend predicted in the growth trend prediction unit with the normal growth pattern. Through comparative analysis, evaluate the current growth status of the tree and determine whether it deviates from the normal growth pattern.

4. The tree growth intelligent monitoring and disease early warning system according to claim 3 is characterized in that: The growth trend prediction unit comprises: Data collection and preprocessing: Collect historical growth data of trees, including tree height, diameter, and leaf coverage area, and preprocess the historical growth data to eliminate outliers and noise; Establishing a linear regression model: Based on the preprocessed historical growth data, a linear regression model is used to predict the future growth trend of trees. The expression of the linear regression model is: ,in, is the predicted future growth parameter of trees, is the height of the tree at the current moment, is the diameter of the tree at the current moment, is the leaf coverage area of ​​the tree at the current moment, are the coefficients of the regression model, is the error term; Model training and coefficient optimization: The coefficients in the regression model are optimized by the least squares method, and the expression of the least squares method is: ,in, For the The actual tree growth parameters of samples, Respectively Tree height, diameter and leaf cover of samples, is the number of training samples; Prediction of future growth trends: Apply the optimized regression model to the tree growth data collected in real time to predict the future growth trends of trees.

5. The tree growth intelligent monitoring and disease early warning system according to claim 4 is characterized in that: The growth status comparison unit comprises: Obtain normal growth pattern data: Collect the normal growth pattern data of trees and establish a mathematical model of the normal growth pattern, where the expression is: ,in, are the predicted growth parameters of trees under normal growth conditions, are the initial tree height, trunk diameter and leaf coverage under normal growth conditions, is the regression coefficient, is the error term; Calculate the deviation from the predicted value and normal growth pattern: Compare the predicted tree growth trend with the normal growth pattern and calculate the deviation between the two , the formula is: ,in, The deviation between the predicted growth trend and the normal growth pattern; Determine whether it deviates from the normal growth pattern: according to the deviation value Determine whether the tree deviates from the normal growth pattern. The specific judgment conditions are: in, It is a preset threshold used to determine whether the deviation is significant. If the condition is met, it is judged that the tree deviates from the normal growth pattern.

6. The tree growth intelligent monitoring and disease early warning system according to claim 1 is characterized in that: The lesion risk assessment module includes an image preprocessing unit, a lesion feature extraction unit, a lesion risk assessment unit and a lesion risk judgment unit; wherein: Image preprocessing unit: used to preprocess the tree appearance image provided by the data acquisition module, including noise removal and contrast enhancement, to enhance image quality and details; Lesion feature extraction unit: Based on the convolutional neural network, the preprocessed image is subjected to feature extraction to identify the area, shape and color of the lesion area in the image. Suppose the area of ​​the lesion area is The shape characteristics of the lesion area are , the color characteristics of the lesion area are ; Disease risk assessment unit: Based on the extracted disease features, the disease risk of the tree is assessed. The calculation formula for the disease risk is: ,in, is the tree disease risk value, is the corresponding weighting coefficient; Lesion risk judgment unit: used to convert the lesion risk value calculated in the lesion risk assessment unit into , and the preset lesion risk threshold Compare and judge whether the tree has the risk of disease. , then the tree is judged to be at risk of disease; otherwise, the tree is in normal health.

7. The tree growth intelligent monitoring and disease early warning system according to claim 1 is characterized in that: The environmental adaptability assessment module includes an environmental data analysis unit and a tree growth impact calculation unit; wherein: Environmental data analysis unit: By processing the environmental data provided by the data acquisition module, including soil moisture, air temperature and humidity, light intensity and precipitation, it analyzes the changing trend of the current environmental conditions and calculates the rate of change of environmental parameters to evaluate the potential impact of environmental fluctuations on tree growth; Tree growth impact calculation unit: It is used to evaluate the specific impact of environmental changes on tree growth based on the tree growth status evaluated by the growth status analysis module and the environmental change trend calculated by the environmental data analysis unit, and to determine whether environmental fluctuations will cause the tree growth rate to slow down or the health to decline.

8. The tree growth intelligent monitoring and disease early warning system according to claim 7 is characterized in that: The environmental data analysis unit comprises: Standardization of environmental data: Obtain environmental data such as soil moisture, air temperature and humidity, light intensity and precipitation from the data acquisition module, and standardize the environmental data to ensure the comparability of data of different units and magnitudes; Calculate the rate of change of environmental parameters: By calculating the rate of change of standardized environmental data, the fluctuation range of environmental conditions over a period of time is evaluated. The rate of change of environmental parameters is calculated by the difference method, and the formula is: ,in, is the current environmental data, is the environmental data of the previous moment, is the rate of change of environmental parameters; Assess the potential impact of environmental fluctuations on tree growth: By comparing the rate of change of the current environmental parameters with the preset threshold, determine whether the magnitude of environmental changes will have a potential impact on tree growth; if the rate of change of an environmental parameter exceeds the set threshold, it is considered that the environmental change will affect tree growth.

9. The tree growth intelligent monitoring and disease early warning system according to claim 8, characterized in that: The tree growth impact calculation unit comprises: Obtain tree growth status data: Obtain tree growth status data from the growth status analysis module, and evaluate the health of the tree by calculating the deviation of the tree's growth index from the normal growth pattern. The formula is: ,in, is the actual growth index of trees. It is an ideal growth indicator under normal growth mode. For the health of the trees; Calculate the growth rate of trees under environmental changes: Assume that the effect of environmental changes on growth rate is adjusted by a multiplication factor, and the calculation formula is: ,in, is the adjusted tree growth rate, is the baseline growth rate, is the sensitivity coefficient of environmental change to growth rate, is the amount of environmental change; Determine the impact of environmental fluctuations on tree growth: Based on the calculated changes in growth rate and health, determine whether environmental fluctuations will cause the growth rate of trees to slow down or their health to decline; specific judgment conditions include: Judgment condition 1: if the change in growth rate caused by environmental fluctuations slows down by more than 5%, it is considered that the growth rate of the tree is affected by the environment; Judgment condition 2: if the health of the tree decreases by more than 20%, it is considered that the growth of the tree has been adversely affected by the environment, resulting in a decline in the health of the tree.

10. The tree growth intelligent monitoring and disease early warning system according to claim 9, characterized in that: The comprehensive early warning analysis module includes a growth status comprehensive evaluation unit, a pathological risk result receiving unit, a comprehensive health threat evaluation unit, a comprehensive health threat evaluation unit and an early warning signal output unit; wherein: Growth status comprehensive evaluation unit: used to receive the tree growth status data output by the growth status analysis module, including growth rate, health and growth trend, and conduct a comprehensive evaluation of the growth status through the weighted average method. The formula is: ,in, is the comprehensive assessment value of tree growth. and are the weights of growth rate, health and growth trend respectively. is the weight of each factor; Disease risk result receiving unit: used to receive the tree disease risk assessment results output by the disease risk assessment module ; Environmental adaptability comprehensive assessment unit: used to receive the tree adaptability data output by the environmental adaptability assessment module, combine the environmental change trend calculated by the environmental data analysis unit, assess the impact of environmental changes on tree growth, and calculate the comprehensive assessment value of environmental adaptability risk; the formula is: ,in, To understand the actual impact of environmental changes on tree growth, is the maximum value of environmental impact, is the environmental adaptability risk assessment value; Comprehensive health threat assessment unit: used to weight and integrate the assessment results output by the growth status comprehensive assessment unit, the disease risk comprehensive assessment unit and the environmental adaptability comprehensive assessment unit, and comprehensively calculate the health threat assessment value of the tree. The formula is: ,in, Assess the threat value to tree health, is the comprehensive evaluation value of growth status, is the tree disease risk value, is the environmental adaptability risk assessment value, , and are the corresponding weights respectively; Early warning signal output unit: used to output the health threat assessment value according to the comprehensive health threat assessment unit , set a threshold. When the health threat assessment value of a tree exceeds the preset threshold, an early warning signal is automatically triggered to indicate that the tree is facing a health threat.

Images