Forest pest prediction method, system and readable storage medium

Abstract

The present invention provides a forest pest prediction method, system, and readable storage medium, relating to the technical field of forest pest prediction. The present invention divides a forest into multiple grids and collects data on the main tree species, tree characteristics, soil properties, and meteorological data for each grid, thereby achieving scientific assessment and management of pest risks. The method primarily includes: first, collecting characteristic parameters for the grids and dividing similar grid groups based on soil characteristics; second, constructing a pest prediction model using a random forest algorithm, training it using pest data from sample grids to predict the severity of pests in other grids; finally, analyzing the changes in pest severity levels for each grid at current and historical times, generating an alarm index, and issuing corresponding alarm signals based on preset thresholds. This method combines the environmental suitability index and the tree vulnerability index, employing an expert scoring method to determine pest levels. It can effectively monitor and warn of pest risks, thus providing a scientific basis for forest management.

Description

Technical Field

[0001] The present invention relates to the technical field of forest pest prediction, and in particular to a forest pest prediction method, system and readable storage medium. Background Art

[0002] Forest pest prediction is a crucial task in forest resource management and protection. With the intensification of global climate change and the impact of human activities, forest ecosystems face an increasingly severe threat from insect pests. Insect pests not only lead to a loss of forest biodiversity but also compromise ecological balance and the sustainable development of the forest economy. Therefore, timely and accurate prediction of insect pest risks is crucial for developing effective prevention and control measures.

[0003] Traditional pest prediction methods often rely on a single data source, such as meteorological data or historical pest records, which often fail to fully capture the complexity and diversity of pest occurrences. This results in inaccurate and in-time pest warnings, posing challenges to forest management and resource conservation. Prediction models based on historical data often lack sufficient adaptability to emerging pest species and cannot provide timely and effective warnings. Therefore, a new approach is urgently needed to integrate multiple data sources and effectively model pests and their ecological dynamics to improve the accuracy and reliability of pest predictions.

[0004] The existing technology has the following deficiencies:

[0005] Existing technologies have some significant shortcomings in forest pest prediction, mainly reflected in the limitations of data collection and the accuracy of prediction models. Many traditional methods rely on a limited number of monitoring points or empirical data, resulting in insufficient data coverage and an inability to fully reflect the actual situation of forest ecosystems. This limitation makes pest prediction results often inaccurate, prone to misjudgment, and affects forest management decisions. In addition, existing technologies usually use single factors or simplified models for analysis in pest severity assessments, failing to fully consider the combined impact of various meteorological conditions and forest characteristics on pest occurrence. The lack of a comprehensive assessment of the suitability of different environments makes the prediction model insufficiently flexible and adaptable, making it difficult to cope with the uncertainties brought about by climate change. In this case, traditional methods cannot provide timely warnings of pest risks, resulting in managers being unable to take effective prevention and control measures, increasing the risk of losses caused by pests.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide a forest pest prediction method, system and readable storage medium to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A forest pest prediction method, comprising the following steps:

[0010] Step 1: Divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data;

[0011] Step 2: Divide all grids into multiple similar grid groups based on the soil property data of each grid. Randomly select a number of sample grids from the similar grid groups and obtain forest pest data for the sample grids. The forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density.

[0012] Step 3: Determine the environmental suitability index for each grid based on the main tree species and meteorological data for the sample grids. Analyze the tree characteristic data to obtain the tree vulnerability index for the sample grids. Analyze the tree vulnerability index and tree pest data for the sample grids based on the expert scoring method to determine the pest severity level for each grid.

[0013] Step 4: Based on the random forest algorithm, a pest prediction model is constructed that corresponds to each similar grid group. The main tree species, tree characteristics, and environmental suitability index of the sample grids in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. The trained pest prediction model is then used to obtain the pest severity level of all grids in the same similar grid group except the sample grid.

[0014] Step 5: Analyze the distribution changes of pest severity levels of N grids at the current time and historical time, obtain the change amount of each pest severity level, determine the pest situation in the forest and issue corresponding alarm signals.

[0015] Furthermore, it specifically includes:

[0016] Divide the forest land area into N grids of equal area, collect the species of all trees in each grid, use the tree species with the largest number in each grid as the main tree species of the corresponding grid, collect tree characteristic data of the trees corresponding to the main tree species in each grid, and use the average value of the tree characteristic data of the trees as the tree characteristic data of the corresponding grid; the tree characteristic data includes tree species, tree density, and tree moisture content;

[0017] The center of each grid is set as a sampling point, and soil characteristic data of each grid sampling point is collected, wherein the soil characteristic data includes soil pH value, soil moisture and organic matter content;

[0018] Obtain meteorological data of the forest location. The meteorological data of each grid is the meteorological data of the forest location, and the meteorological data includes temperature, humidity and rainfall.

[0019] Furthermore, obtaining the forest pest data of the sample grid specifically includes:

[0020] Each grid is regarded as a node, and the soil characteristic data corresponding to each node is used as the attribute of the node to construct an undirected graph. If two nodes are adjacent, an edge is added to the undirected graph to form an undirected graph network.

[0021] Each node is placed in an independent similar grid group. For each node in the undirected graph network, it is moved one by one to the similar grid groups where all its neighboring nodes are located. The difference in characteristic changes caused by each move is calculated, including:

[0022]

[0023] in, is the difference in characteristic changes between the i-th node and the j-th node, is the mean pH value of the i-th node and the j-th node, is the pH value of the i-th node, is the mean soil moisture of the i-th node and the j-th node, is the soil moisture of the i-th node, is the mean value of organic matter content between the i-th node and the j-th node, is the organic matter content of the i-th node, i and j are both nodes in the undirected graph, and i and j are neighbor nodes;

[0024] Move each node to the neighboring similar grid group with the smallest difference in characteristic changes. Repeat the node movement until the similar grid group affiliation of all nodes no longer changes. At this point, randomly select several nodes in each similar grid group as sample grids for this similar grid group.

[0025] The formula for calculating the proportion of trees infested by insects is:

[0026]

[0027] Where Q is the proportion of insect-infested trees in the sample grid, is the number of infested trees in the sample grid, is the total number of trees in the sample grid;

[0028] Randomly select several trees in the sample grid as sample trees and obtain the insect infestation area ratio of the sample trees. The calculation formula is:

[0029]

[0030] in, is the proportion of the pest area of ​​the xth sample tree in the sample grid, is the pest area of ​​the x-th sample tree in the sample grid, is the total area of ​​the x-th sample tree in the sample grid, x is the index of the sample tree, and the mean of the pest area ratios of all sample trees is taken as the pest area ratio of the sample grid;

[0031] The formula for calculating the pest area spread rate is:

[0032]

[0033] Among them, Pv(t) is the pest area spread speed of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the previous moment, Indicates the time interval between the current moment and the previous moment;

[0034] Multiple sampling areas are randomly selected within the infested area of ​​the trees in the sample grid. Image data of the sampling areas are collected. The number of pests in each sampling area is obtained using image processing software. The pest density formula is calculated as follows:

[0035]

[0036] in, is the pest density in the sampling area, Pn is the number of pests in the sampling area image, and a is the area of ​​the sampling area;

[0037] Calculate the pest density of all sampling areas and calculate the average value as the pest density of the corresponding sample grid. The formula for calculating the pest density growth rate is:

[0038]

[0039] in, is the pest density growth rate of the sample grid at the current moment, is the pest density of the sample grid at the current moment, is the pest density of the sample grid at the previous moment.

[0040] Furthermore, calculating the environmental suitability index of each grid specifically includes:

[0041] The calculation formula of environmental suitability index is:

[0042]

[0043] in, is the environmental suitability index, are the suitability functions of temperature, humidity and rainfall, respectively. are the weight coefficients of their respective corresponding items, ,and ;

[0044] The calculation formula of temperature suitability function is:

[0045]

[0046] in, Indicates temperature in °C. is a positive value used to control the opening size of the function. represents the most suitable value of temperature, The optimal pest prevention temperature for trees belonging to the main forest species corresponding to the grid;

[0047] The calculation formula of humidity adaptability function is:

[0048]

[0049] in, Indicates humidity, is a positive value used to control the opening size of the function. Represents the optimal humidity value, The optimal moisture content for preventing insect pests for the trees belonging to the main forest species corresponding to the grid;

[0050] The calculation formula of rainfall adaptability function is:

[0051]

[0052] Among them, R represents rainfall in mm. is a positive value used to control the opening size of the function. represents the best suitable value of rainfall, The optimal rainfall for pest prevention of trees belonging to the main forest species corresponding to the grid.

[0053] Furthermore, calculating the forest vulnerability index of each grid specifically includes:

[0054] The calculation formula of the forest vulnerability index of the sample grid is:

[0055]

[0056] in, is the tree vulnerability index of the sample grid, is the tree density of the main tree species corresponding to the sample grid, is the tree moisture content of the main tree species corresponding to the sample grid;

[0057] The environmental suitability index and forest vulnerability index of each grid are analyzed based on the expert scoring method to determine the pest severity level of each grid, which includes high pest level, medium pest level and low pest level.

[0058] Furthermore, constructing the pest prediction model specifically includes:

[0059] The main tree species, tree characteristic data, environmental suitability index and pest severity level of several sample grids in the similar grid group were integrated into a sample set, and the sample set was divided into a training set and a test set with a division ratio of 7:3. The main tree species, tree characteristic data and environmental suitability index in the training set were used as input, and the corresponding pest severity index was used as a label. The random forest model was trained to obtain a pest prediction model. The mean square error was set as the loss function, and the value of the loss function was monitored. When the value of the loss function dropped to 0.001 within 10 iterations, the model was considered to have been trained. The test set was then used to evaluate the model. The evaluation indicators were accuracy, precision and recall. If the accuracy, precision and recall were above 70%, the model performance was considered good. If the value of the evaluation indicator was lower than 70%, the model parameters were adjusted.

[0060] Then, the main tree species, tree characteristic data and environmental suitability index of other grids in the same similar grid group except the sample grid are input into the trained pest prediction model to obtain the pest severity level output by the model.

[0061] Furthermore, the specific conditions of forest pests include:

[0062] Get the proportion of grids with high pest severity level at the current moment. The calculation formula is:

[0063]

[0064] in, is the proportion of grids with high pest severity at the current moment, is the indicator function, when When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the current moment, which is high, medium, or low. n is the index of the grid, and N is the total number of grids. ;

[0065] Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ;

[0066] Get the proportion of grids with high pest severity level at the previous moment. The calculation formula is:

[0067]

[0068] in, is the proportion of grids with high pest severity level at the previous moment. When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the previous moment, which is high, medium, or low;

[0069] Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ;

[0070] Calculate the change in severity of different insect pests in the forest at the current moment. The formula for calculating the change in severity of high insect pests is:

[0071]

[0072] in, is the change in the high pest level at the current moment;

[0073] Similarly, obtain the change in the pest level and the change in the low pest level at the current moment, expressed as ;

[0074] According to the change in severity of different insect pests in the forest, an alarm index is generated. The calculation formula is:

[0075]

[0076] Among them, AI(t) is the alarm index of the forest at the current moment, are the weight coefficients of the corresponding items, ;

[0077] Compare the forest alarm index at the current moment with the preset threshold. , if it is judged that there are many insect pests in the forest at the current moment, a high insect pest alarm will be issued. , judge that the insect pest in the forest is normal at the moment, then issue an insect pest alarm, if , if it is judged that there are few insect pests in the forest at the current moment, no alarm will be issued, where High risk threshold and low risk threshold.

[0078] The present invention further provides a forest pest prediction system, which is used to implement the above-mentioned forest pest prediction method, and includes:

[0079] A characteristic parameter collection module is used to divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data;

[0080] A sample selection module is used to divide all grids into multiple similar grid groups based on the soil property data of each grid, randomly select a number of sample grids from the similar grid groups, and obtain forest pest data for the sample grids, wherein the forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density;

[0081] The pest severity level determination module is used to determine the environmental suitability index of each grid by combining the main tree species and meteorological data of the sample grid, analyze the tree characteristic data to obtain the tree vulnerability index of the sample grid, and analyze the tree vulnerability index and forest pest data of the sample grid based on the expert scoring method to determine the pest severity level of each grid;

[0082] The pest prediction model construction module is used to construct a pest prediction model corresponding to each similar grid group based on the random forest algorithm. The main tree species, tree characteristic data and environmental suitability index of the sample grid in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. The pest prediction model is then used to obtain the pest severity level of other grids in the same similar grid group except the sample grid.

[0083] The pest monitoring and alarm module is used to analyze the distribution changes of pest severity levels of N grids at current and historical times, obtain the change in severity level of each pest, determine the pest situation in the forest and issue corresponding alarm signals.

[0084] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned forest pest prediction method.

[0085] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0086] The forest pest prediction method of the present invention effectively solves the problem that traditional pest monitoring methods are unable to achieve accurate and timely early warning. By dividing the forest into grids and combining comprehensive analysis of multiple environmental characteristic parameters, pest risks can be more accurately identified and assessed. This data-driven method uses the random forest algorithm to construct a pest prediction model, which significantly improves the prediction accuracy of pest levels, thereby providing a scientific basis for the formulation of prevention and control measures, helping managers to take timely countermeasures and reduce economic losses caused by pests. In addition, this solution makes pest risk assessment more comprehensive by combining the environmental suitability index and the forest vulnerability index, and can comprehensively consider multiple factors such as meteorological and soil characteristics. This multi-dimensional analysis method not only improves the flexibility of monitoring, but also enhances the responsiveness of the early warning system, ensuring that alarms can be issued at the early stages of pest occurrence, thereby effectively protecting the health and sustainable development of forest ecosystems. This innovative method provides a new approach to forest pest management and significantly improves the efficiency of ecological protection and resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0088] Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0089] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0090] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0091] Example:

[0092] See also Figure 1 , the present invention provides a technical solution:

[0093] A forest pest prediction method, comprising the following steps:

[0094] Step 1: Divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data;

[0095] In this embodiment, it specifically includes:

[0096] Divide the forest land area into N grids of equal area, collect the species of all trees in each grid, use the tree species with the largest number in each grid as the main tree species of the corresponding grid, collect tree characteristic data of the trees corresponding to the main tree species in each grid, and use the average value of the tree characteristic data of the trees as the tree characteristic data of the corresponding grid; the tree characteristic data includes tree species, tree density, and tree moisture content;

[0097] The center of each grid is set as a sampling point, and soil characteristic data of each grid sampling point is collected, wherein the soil characteristic data includes soil pH value, soil moisture and organic matter content;

[0098] Obtain meteorological data of the forest location. The meteorological data of each grid is the meteorological data of the forest location, and the meteorological data includes temperature, humidity and rainfall.

[0099] The moisture content of trees can be monitored through forest moisture meters, and meteorological data can be obtained through the meteorological station where the forest is located. The tree species in each grid area can be determined based on local forest survey data, and the tree density can be determined by querying relevant literature and data based on the tree species. pH sensors and humidity sensors are arranged at the sampling points of each grid to collect soil pH and soil moisture. The soil at the grid location can also be sampled and the soil pH, soil moisture and organic matter content data can be obtained through laboratory analysis.

[0100] Selecting the most abundant tree species in each grid as the primary forest species and calculating the average of its forest characteristic data better reflects the ecological characteristics of the grid and improves the representativeness of the data. Collected soil property data (such as pH, moisture, and organic matter content) and meteorological data (such as temperature, humidity, and rainfall) provide essential conditions for subsequent assessments of environmental suitability. Daily rainfall data is collected here. This data helps analyze the impact of different environmental factors on forest pests and provides a scientific basis for potential pest risk.

[0101] Step 2: Divide all grids into multiple similar grid groups based on the soil property data of each grid. Randomly select a number of sample grids from the similar grid groups and obtain forest pest data for the sample grids. The forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density.

[0102] In this embodiment, obtaining the forest pest data of the sample grid specifically includes:

[0103] Each grid is regarded as a node, and the soil characteristic data corresponding to each node is used as the attribute of the node to construct an undirected graph. If two nodes are adjacent, an edge is added to the undirected graph to form an undirected graph network.

[0104] Each node is placed in an independent similar grid group. For each node in the undirected graph network, it is moved one by one to the similar grid groups where all its neighboring nodes are located. The difference in characteristic changes caused by each move is calculated, including:

[0105]

[0106] in, is the difference in characteristic changes between the i-th node and the j-th node, is the mean pH value of the i-th node and the j-th node, is the pH value of the i-th node, is the mean soil moisture of the i-th node and the j-th node, is the soil moisture of the i-th node, is the mean value of organic matter content between the i-th node and the j-th node, is the organic matter content of the i-th node, i and j are both nodes in the undirected graph, and i and j are neighbor nodes;

[0107] Each node is moved to the neighboring similar grid group with the smallest difference in characteristic changes. The nodes are moved repeatedly until the similar grid group affiliation of all nodes no longer changes. At this time, several nodes are randomly selected in each similar grid group as the sample grids of the similar grid group.

[0108] By dividing grids into similar groups based on soil properties, areas with similar environmental conditions can be effectively identified, providing a more accurate and detailed foundation for pest prediction. Calculating the difference in property changes helps understand environmental variations between adjacent grids, enabling the algorithm to select the most appropriate similar grid groups for pest data collection, ensuring representative samples. The gradual movement of nodes allows the grid to adapt, ultimately resulting in a division into similar grid groups that better reflects actual conditions and improves prediction accuracy.

[0109] It reflects the degree of change in soil properties (pH value, soil moisture, organic matter content) between node i and its adjacent node j. Specifically, the smaller this value is, the more similar the properties of the two nodes are. The calculation of its value can reveal the differences between environmental characteristics and help identify which adjacent areas are closer in soil properties, thereby providing a basis for pest monitoring decisions. Independent variables include pH value, soil moisture and organic matter content. These soil properties directly affect the growth of plants, and the health of plants is closely related to the occurrence of pests, affecting the availability of nutrients, thereby affecting the growth of trees, and then affecting the occurrence of pests; directly affecting the growth and health of plants, too high or too low humidity may lead to a decrease in plant resistance and increase the probability of pests; affecting soil fertility, and then affecting plant growth, healthy plants are more resistant to pests. If the soil properties of the two nodes are similar, that is, A small value indicates that the environmental conditions of these nodes have similar effects on pests, which may lead to similar risks of pests. If the soil properties of node i and node j are quite different, it indicates that the environmental conditions may lead to significantly different risks of pests. Grouping more similar nodes into a similar grid group and randomly selecting samples from it can better describe the characteristics of all grid-related data in this similar grid group.

[0110] The formula for calculating the proportion of trees infested by insects is:

[0111]

[0112] Where Q is the proportion of insect-infested trees in the sample grid, is the number of infested trees in the sample grid, is the total number of trees in the sample grid;

[0113] A limiting condition can be given here. When the proportion of the pest area of ​​a tree exceeds a certain threshold, for example, 30%, the tree is considered an infested tree. Alternatively, when the pest density in the sampling area of ​​the sample grid reaches a certain threshold, for example, 10 pests per square meter, the trees in the sampling area are considered infested trees.

[0114] Q is the proportion of infested trees in the sample grid. This ratio reflects the proportion of infested trees relative to the total number of trees in the sample grid and can directly reflect the severity of the infestation. The greater the number of infested trees in the sample grid, the higher the corresponding proportion of infested trees.

[0115] Randomly select several trees in the sample grid as sample trees and obtain the insect infestation area ratio of the sample trees. The calculation formula is:

[0116]

[0117] in, is the proportion of the pest area of ​​the xth sample tree in the sample grid, is the pest area of ​​the x-th sample tree in the sample grid, is the total area of ​​the x-th sample tree in the sample grid, x is the index of the sample tree, and the mean of the pest area ratios of all sample trees is taken as the pest area ratio of the sample grid;

[0118] The insect infestation area ratio is the insect infestation area ratio of a certain tree in the sample grid. This indicator reflects the ratio of the area affected by insect infestation on a specific tree to its total area, indicating the degree of impact of insect infestation on a specific tree.

[0119] The formula for calculating the pest area spread rate is:

[0120]

[0121] Among them, Pv(t) is the pest area spread speed of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the previous moment, Indicates the time interval between the current moment and the previous moment;

[0122] The pest area spread speed indicates the rate of change of the pest area ratio per unit time, reflecting the speed of pest spread. In the same time interval, the higher the pest area ratio at the current moment and the greater the change in the pest area ratio, the faster the pest area spreads.

[0123] Multiple sampling areas are randomly selected within the infested area of ​​the trees in the sample grid. Image data of the sampling areas are collected. The number of pests in each sampling area is obtained using image processing software. The pest density formula is calculated as follows:

[0124]

[0125] in, is the pest density of the sampling area. This index represents the number of pests per unit area, indicating the intensity of the pest. Pn is the number of pests in the sampling area image, and a is the area of ​​the sampling area.

[0126] Calculate the pest density of all sampling areas and calculate the average value as the pest density of the corresponding sample grid. The formula for calculating the pest density growth rate is:

[0127]

[0128] in, is the pest density growth rate of the sample grid at the current moment, is the pest density of the sample grid at the current moment, is the pest density of the sample grid at the previous moment.

[0129] The growth rate of pest density reflects the rate of change of pest density per unit time and the growth trend of pests. If the pest density at the current moment increases, the greater the difference with the pest density at the previous moment, the faster the growth rate of pest density, which reflects that the pest is getting worse.

[0130] Step 3: Determine the environmental suitability index for each grid based on the main tree species and meteorological data for the sample grids. Analyze the tree characteristic data to obtain the tree vulnerability index for the sample grids. Analyze the tree vulnerability index and tree pest data for the sample grids based on the expert scoring method to determine the pest severity level for each grid.

[0131] In this embodiment, calculating the environmental suitability index of each grid specifically includes:

[0132] The calculation formula of environmental suitability index is:

[0133]

[0134] in, is the environmental suitability index, are the suitability functions of temperature, humidity and rainfall, respectively. are the weight coefficients of their respective corresponding items, ,and ;

[0135] Temperature, humidity, and rainfall are all normalized by maximum-minimum normalization, and the optimal suitable values ​​of temperature, humidity, and rainfall are also normalized by maximum-minimum normalization. The temperature suitability function calculation formula is:

[0136]

[0137] in, Indicates temperature in °C. ∈[0,1], used to control the opening size of the function, set to 0.2, Represents the best suitable value of temperature, set c value to 1, 1 represents the best, 0 represents the worst, The optimal pest prevention temperature for trees belonging to the main forest species corresponding to the grid;

[0138] Temperature is a significant factor influencing insect growth, reproduction, and activity. Generally, many forest pests exhibit optimal activity and reproduction within a temperature range of 15°C to 30°C. Below 15°C, many insects experience a slowdown in metabolic rate and reduced activity, while temperatures above 30°C can cause heat stress in many species, leading to mortality or reproductive inhibition. Therefore, this temperature range accurately reflects the biological needs of insect pests. The optimal pest-control temperature here can be set at 25°C, but specific values ​​can be determined by consulting relevant literature and reports for specific tree species.

[0139] The calculation formula of humidity adaptability function is:

[0140]

[0141] in, Indicates humidity, A positive value used to control the opening size of the function, set to 0.1, Represents the best suitable value of humidity, set d to 1, The optimal moisture content for preventing insect pests for the trees belonging to the main forest species corresponding to the grid;

[0142] Humidity significantly impacts the growth environment of plants and insects. Low humidity (below 40%) can cause drought in plants, impacting their growth and health, and thus reducing their resistance to pests. High humidity (above 70%) can foster the growth of mold and other pathogens, and also hinder insect activity. Therefore, the optimal humidity for pest control can be set at 55%. However, the specific value should be determined by consulting relevant literature and reports for the optimal humidity for pest control, depending on the species of trees.

[0143] The calculation formula of rainfall adaptability function is:

[0144]

[0145] Among them, R represents rainfall in mm. is a positive value used to control the opening size of the function, set to 0.15, Represents the best suitable value of rainfall, set g to 1, The optimal rainfall for pest prevention of trees belonging to the main forest species corresponding to the grid.

[0146] Rainfall directly affects soil moisture and plant health, which in turn influences the occurrence of insect pests. Within this range, rainfall ensures soil moisture and promotes healthy plant growth. However, too little rainfall (less than 50 mm) can cause drought in plants, reducing their resistance to insect pests. Excessive rainfall (over 100 mm) can cause waterlogging, leading to an increase in plant diseases and indirectly affecting insect pests. Therefore, the optimal rainfall for pest prevention can be set at 75. However, the specific value can be determined by consulting relevant literature and reports based on the main forest species to determine the optimal rainfall for pest prevention.

[0147] E is a comprehensive indicator reflecting the suitability of environmental conditions (temperature, humidity, and rainfall) within a specific grid for the occurrence of forest pests. Temperature is a key factor influencing insect growth, reproduction, and activity. Many forest pests exhibit optimal growth and reproduction within a specific temperature range. Humidity has a significant impact on plant health and the occurrence of pests. Suitable humidity promotes plant growth and improves plant resistance; however, excessively low or high humidity can restrict plant growth, thereby affecting its resistance to pests. Furthermore, some insects thrive and thrive in high-humidity environments. Precipitation influences soil moisture and plant growth. Adequate rainfall helps plants absorb water, thereby enhancing their growth and health and improving their resistance to pests. However, excessive rainfall can lead to root hypoxia or disease, compromising plant health and, consequently, the occurrence of pests.

[0148] Within the suitable range, as the three independent variables of temperature, humidity, and rainfall approach the optimal temperature, optimal humidity, and optimal rainfall for pest control, their respective adaptability function values ​​will increase, and the environmental suitability index will also increase, indicating that the current environmental conditions are closer to the optimal pest control conditions. As the three independent variables deviate more from the optimal pest control values, the corresponding adaptability function values ​​will decrease, and the corresponding environmental suitability index will decrease, indicating that the current environmental conditions are not conducive to pest control.

[0149] Step 4: Based on the random forest algorithm, a pest prediction model is constructed that corresponds to each similar grid group. The main tree species, tree characteristics, and environmental suitability index of the sample grids in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. The trained pest prediction model is then used to obtain the pest severity level of all grids in the same similar grid group except the sample grid.

[0150] In this embodiment, calculating the tree vulnerability index of each grid specifically includes:

[0151] The calculation formula of the forest vulnerability index of the sample grid is:

[0152]

[0153] in, is the tree vulnerability index of the sample grid, is the tree density of the main tree species corresponding to the sample grid, is the tree moisture content of the main tree species corresponding to the sample grid;

[0154] By calculating the Tree Vulnerability Index, we can quantitatively assess the vulnerability of trees to insect pests under specific environmental conditions. Tree density and moisture content are key factors influencing tree biophysical properties. Trees with low density or high moisture content may be more susceptible to insect pests.

[0155] The tree vulnerability index and tree pest data of each grid are analyzed based on the expert scoring method to determine the pest severity level of each grid, which includes high pest level, medium pest level and low pest level.

[0156] Different weights can be assigned to the tree pest data and the tree vulnerability index. The specific weights can be set by experts, who will score the tree pest data and tree vulnerability index for each grid separately, and then use the weights to calculate a composite score. The greater the number of tree pest data, the higher the expert score can be; conversely, the smaller the number of tree pest data, the lower the expert score should be. The greater the tree vulnerability index, the higher the expert score can be; conversely, the smaller the tree vulnerability index, the lower the expert score should be. However, please note that the scores assigned to the tree pest data and tree vulnerability index are positively correlated with the severity of the pest: that is, the greater the number of tree pest data and tree vulnerability index, the higher the severity of the pest.

[0157] In this embodiment, constructing the pest prediction model specifically includes:

[0158] The main tree species, tree characteristic data, environmental suitability index, and pest severity level of several sample grids in the similar grid group are integrated into a sample set, and the sample set is divided into a training set and a test set with a division ratio of 7:3. The main tree species, tree characteristic data, and environmental suitability index in the training set are used as input, and the corresponding pest severity index is used as a label. The random forest model is trained to obtain a pest prediction model. The mean square error is set as the loss function, and the value of the loss function is monitored. When the value of the loss function drops to 0.001 within 10 iterations, the model is considered to have been trained. The model is then evaluated using the test set. The evaluation indicators are accuracy, precision, and recall. If the accuracy, precision, and recall are above 70%, the model performance is considered good. If the value of the evaluation indicator is below 70%, the model parameters are adjusted. Adjustment parameters include the number of trees in the random forest. You can consider increasing or decreasing the number of trees, adjusting the maximum depth of the tree, or adjusting the minimum sample split number and the minimum sample leaf number.

[0159] Then, the main tree species, tree characteristic data and environmental suitability index of other grids in the same similar grid group except the sample grid are input into the trained pest prediction model to obtain the pest severity level output by the model.

[0160] Different tree species possess distinct physiological, chemical, and structural characteristics, which directly impact their resistance to pests. For example, some tree species may be naturally resistant to specific pests, while others may be more vulnerable. Therefore, incorporating major tree species as input data helps the model capture these diverse characteristics, enabling more accurate predictions of pest severity. Tree characteristics, such as tree density and moisture content, are important factors influencing tree vulnerability. Generally speaking, denser trees are more resistant to pests, while moisture content can affect tree decay and pest infestation. Incorporating these characteristics into the model provides more nuanced input, helping the model understand correlations with pest occurrence, thereby improving prediction accuracy. The Environmental Suitability Index is calculated by integrating environmental factors such as temperature, humidity, and rainfall. These factors influence the occurrence and progression of pests. For example, certain pests may reproduce more rapidly under certain temperature and humidity conditions, while rainfall can indirectly influence pest occurrence by affecting soil moisture and plant growth. Therefore, using the Environmental Suitability Index as input data can help the model identify the potential risk of insect pests under specific environmental conditions. The Pest Severity Index quantifies the impact of insect pests and reflects the threat they pose to forest ecosystems. Because the input data already considers tree species, characteristics, and environmental factors, the output Pest Severity Index is necessarily closely related to these input variables. When input conditions change (such as different tree species or environmental conditions), the Pest Severity Index will also change accordingly. The model is trained to capture these complex relationships between input and output, enabling effective prediction of pest severity levels.

[0161] Expert scoring is used to evaluate pest severity. A higher environmental suitability index (EI) and lower tree vulnerability indicate a lower pest severity. Conversely, a lower EI and higher tree vulnerability indicate a higher pest severity. The random forest model, which integrates multiple decision trees for prediction, can effectively improve prediction accuracy. The presence of specific tree species may be closely correlated with the incidence of certain pests. For example, certain insects may prefer specific trees or be more susceptible to specific tree species. Therefore, identifying the dominant tree species in a sample grid as input can help the model understand the underlying drivers of pest severity. Tree density is generally proportional to its strength and pest resistance. Denser trees are generally less susceptible to pest infestation and are more resilient than lower-density trees. Therefore, tree density, as an input feature, has a direct impact on the pest severity index. The EI is calculated from factors such as temperature, humidity, and rainfall, all of which influence the occurrence and progression of pests. For example, excessively high or low temperatures may lead to reduced pest activity, while suitable humidity may promote pest reproduction and thus be considered as a factor in determining the severity of pests. Because random forests leverage the principles of diversity and ensemble learning, they have greater generalization capabilities than single decision trees and are better able to adapt to complex data. In pest prediction, input variables may have high-dimensional features. Random forests can effectively handle high-dimensional data and identify important features that influence pests through feature selection techniques, thereby improving the efficiency and interpretability of the model. When evaluating a model, multiple metrics such as accuracy, precision, and recall can be used to comprehensively reflect the model's performance. These metrics each focus on different aspects and can better evaluate the model's actual effectiveness in pest prediction. The combination of precision and recall is particularly effective when dealing with imbalanced datasets.

[0162] Step 5: Analyze the distribution changes of pest severity levels of N grids at the current time and historical time, obtain the change amount of each pest severity level, determine the pest situation in the forest and issue corresponding alarm signals.

[0163] In this embodiment, determining the insect pest situation in the forest specifically includes:

[0164] Get the proportion of grids with high pest severity level at the current moment. The calculation formula is:

[0165]

[0166] in, is the proportion of grids with high pest severity at the current moment, is the indicator function, when When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the current moment, which is high, medium, or low. n is the index of the grid, and N is the total number of grids. ;

[0167] Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ;

[0168] Get the proportion of grids with high pest severity level at the previous moment. The calculation formula is:

[0169]

[0170] in, is the proportion of grids with high pest severity level at the previous moment. When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the previous moment, which is high, medium, or low;

[0171] Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ;

[0172] By comparing the severity of pests at the current moment with that at the previous moment, we can track changes in pest conditions in real time. This dynamic monitoring helps to promptly detect pest spread trends and ensure managers can take appropriate measures quickly. In this paper, the use of indicator functions transforms the classification problem of pest severity into a straightforward numerical problem. By counting the number of high-severity pests within a grid, the current severity of the pest is accurately reflected. By comparing the current pest severity level with the previous one, changing trends in pest activity can be effectively identified. This method, based on the principles of time series analysis, is highly logical and practical.

[0173] Calculate the change in severity of different insect pests in the forest at the current moment. The formula for calculating the change in severity of high insect pests is:

[0174]

[0175] in, is the change in the high pest level at the current moment;

[0176] Similarly, obtain the change in the pest level and the change in the low pest level at the current moment, expressed as ;

[0177] According to the changes in the severity of different insect pests in the forest, an alarm index is generated. The calculation formula is:

[0178]

[0179] Among them, AI(t) is the alarm index of the forest at the current moment, are the weight coefficients of the corresponding items, ;

[0180] Compare the forest alarm index at the current moment with the preset threshold. , if it is judged that there are many insect pests in the forest at the current moment, a high insect pest alarm will be issued. , judge that the insect pest in the forest is normal at the moment, then issue an insect pest alarm, if , if it is judged that there are few insect pests in the forest at the current moment, no alarm will be issued, where High risk threshold and low risk threshold.

[0181] AI(t) represents the comprehensive assessment value of the pest risk in the forest at the current moment. It comprehensively considers the changes in high, medium and low pest levels, and reflects the severity of the overall pest situation by weighting the changes in different levels. This index can help forest managers quickly judge the severity of the current pests. Based on the comparison between the alarm index and the preset threshold, high, medium and low risk alarms can be issued in a timely manner to ensure a rapid response to pest problems. The independent variable directly affects the dependent variable. Specifically, the change in the pest level reflects the extent of the spread of the pest. For example, if the high pest level If the increase in is large, AI(t) will increase significantly, indicating a high risk of pests. When the value of the independent variable (i.e., the change in the different pest levels) increases, the dependent variable AI(t) will usually increase as well. For example, if An increase means that the proportion of grids with high pest levels increases, which directly leads to an increase in AI(t), reflecting the increase in pest risk. Similarly, if the change in the medium pest level or the change in low pest level Although the impact is small, it will also improve AI(t) to a certain extent. On the contrary, if the change in pest level is negative, that is, A decrease in AI(t) will result in a decrease in AI(t), reflecting a reduction in pest risk.

[0182] In the formula for generating the alarm index AI(t), the weight coefficient and The setting reflects the degree of influence of different pest severity levels on the overall risk assessment. Specifically, the relationship between the size of the weight This reflects the difference in importance of high pest level, medium pest level and low pest level in pest early warning. Refers to the change in the proportion of areas with the highest pest severity at the current point in time. This change directly affects the health of the entire forest, because a high pest level usually means that the damage to trees caused by pests is more serious, which may lead to large-scale tree death and imbalance of the ecosystem. Therefore, high pest levels are not assigned weights, but are used as a 100% proportion parameter in the calculation of the alarm index, which can also be regarded as a weight of 1. This ensures that potential major risks are more sensitively reflected in the early warning. Medium-level pests Although the impact on forests is lower than that of high-level pests, it can still cause potential ecological problems and should be given a certain weight. Its weight is set higher than that of low-level pests. This setting ensures that in pest warning, we can respond appropriately to changes in medium-level pests. Impacts on forests are relatively minor and therefore given the lowest weight This not only reflects its limited contribution to the overall ecological risk, but also avoids the impact of fluctuations in low-level pests on the accuracy of the alarm index in high-risk situations.

[0183] The alarm index is calculated by weighting the changes in different pest levels, taking into account the changes in high, medium and low pest levels. This comprehensive evaluation provides a more comprehensive pest risk assessment than a single indicator. By setting high-risk thresholds and low-risk thresholds, pest risks can be divided into different levels (high, medium and low). This hierarchical management allows forest managers to take corresponding response measures according to different risk levels and improve management efficiency. The high-risk threshold and low-risk threshold can be calculated by analyzing pest data from the past few years to calculate the average alarm index when pest risks occurred in the past few years. The average is set as the high-risk threshold, and 0.7 is set as the low-risk threshold. The mean value was set as the low risk threshold.

[0184] See also Figure 2 The present invention further provides a forest pest prediction system, which is used to implement the above-mentioned forest pest prediction method, including:

[0185] A characteristic parameter collection module is used to divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data;

[0186] A sample selection module is used to divide all grids into multiple similar grid groups based on the soil property data of each grid, randomly select a number of sample grids from the similar grid groups, and obtain forest pest data for the sample grids, wherein the forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density;

[0187] The pest severity level determination module is used to determine the environmental suitability index of each grid by combining the main tree species and meteorological data of the sample grid, analyze the tree characteristic data to obtain the tree vulnerability index of the sample grid, and analyze the tree vulnerability index and forest pest data of the sample grid based on the expert scoring method to determine the pest severity level of each grid;

[0188] The pest prediction model construction module is used to construct a pest prediction model corresponding to each similar grid group based on the random forest algorithm. The main tree species, tree characteristic data and environmental suitability index of the sample grid in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. The pest prediction model is then used to obtain the pest severity level of other grids in the same similar grid group except the sample grid.

[0189] The pest monitoring and alarm module is used to analyze the distribution changes of pest severity levels of N grids at current and historical times, obtain the change in severity level of each pest, determine the pest situation in the forest and issue corresponding alarm signals.

[0190] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned forest pest prediction method.

[0191] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0192] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0193] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple grid units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0194] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A forest pest prediction method, characterized in that: The specific steps include: Step 1: Divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data; Step 2: Divide all grids into multiple similar grid groups based on the soil property data of each grid. Randomly select a number of sample grids from the similar grid groups and obtain forest pest data for the sample grids. The forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density. Step 3: Determine the environmental suitability index for each grid based on the main tree species and meteorological data for the sample grids. Analyze the tree characteristic data to obtain the tree vulnerability index for the sample grids. Analyze the tree vulnerability index and tree pest data for the sample grids based on the expert scoring method to determine the pest severity level for each grid. Step 4: Based on the random forest algorithm, a pest prediction model is constructed that corresponds to each similar grid group. The main tree species, tree characteristics, and environmental suitability index of the sample grids in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. The trained pest prediction model is then used to obtain the pest severity level of all grids in the same similar grid group except the sample grid. Step 5: Analyze the distribution changes of pest severity levels of N grids at the current time and in the past, and obtain the change in severity level of each pest to determine the pest situation in the forest and issue corresponding alarm signals; Divide the forest land area into N grids of equal area, collect the species of all trees in each grid, use the tree species with the largest number in each grid as the main tree species of the corresponding grid, collect tree characteristic data of the trees corresponding to the main tree species in each grid, and use the average value of the tree characteristic data of the trees as the tree characteristic data of the corresponding grid, wherein the tree characteristic data includes tree density and tree moisture content; The center of each grid is set as a sampling point, and soil characteristic data of each grid sampling point is collected, wherein the soil characteristic data includes soil pH value, soil moisture and organic matter content; Obtaining meteorological data for the forest location. The meteorological data for each grid is the meteorological data for the forest location, and the meteorological data includes temperature, humidity, and rainfall. The calculation formula for the environmental suitability index is: in, is the environmental suitability index, are the suitability functions of temperature, humidity and rainfall, respectively. are the weight coefficients of their respective corresponding items, ,and ; The calculation formula of temperature suitability function is: in, Indicates temperature in °C. is a positive value used to control the opening size of the function. represents the most suitable value of temperature, The optimal pest prevention temperature for trees belonging to the main forest species corresponding to the grid; The calculation formula of humidity adaptability function is: in, Indicates humidity, is a positive value used to control the opening size of the function. Represents the optimal humidity value, The optimal moisture content for preventing insect pests for the trees belonging to the main forest species corresponding to the grid; The calculation formula of rainfall adaptability function is: Among them, R represents rainfall in mm. is a positive value used to control the opening size of the function. represents the best suitable value of rainfall, The optimal rainfall for pest prevention of trees belonging to the main forest species corresponding to the grid; The calculation formula of the forest vulnerability index of the sample grid is: in, is the tree vulnerability index of the sample grid, is the tree density of the main tree species corresponding to the sample grid, is the tree moisture content of the main tree species corresponding to the sample grid; The environmental suitability index and forest vulnerability index of each grid are analyzed based on the expert scoring method to determine the pest severity level of each grid, which includes high pest level, medium pest level and low pest level.

2. A forest pest prediction method according to claim 1, characterized in that: Obtaining the forest pest data of the sample grid specifically includes: Each grid is regarded as a node, and the soil characteristic data corresponding to each node is used as the attribute of the node to construct an undirected graph. If two nodes are adjacent, an edge is added to the undirected graph to form an undirected graph network. Each node is placed in an independent similar grid group. For each node in the undirected graph network, it is moved one by one to the similar grid groups where all its neighboring nodes are located. The difference in characteristic changes caused by each move is calculated, including: in, is the difference in characteristic changes between the i-th node and the j-th node, is the mean pH value of the i-th node and the j-th node, is the pH value of the i-th node, is the mean soil moisture of the i-th node and the j-th node, is the soil moisture of the i-th node, is the mean value of organic matter content between the i-th node and the j-th node, is the organic matter content of the i-th node, i and j are both nodes in the undirected graph, and i and j are neighbor nodes; Move each node to the neighboring similar grid group with the smallest difference in characteristic changes. Repeat the node movement until the similar grid group affiliation of all nodes no longer changes. At this point, randomly select several nodes in each similar grid group as sample grids for this similar grid group. The formula for calculating the proportion of trees infested by insects is: Where Q is the proportion of insect-infested trees in the sample grid, is the number of insect-infested trees in the sample grid, is the total number of trees in the sample grid; Randomly select several trees in the sample grid as sample trees and obtain the insect infestation area ratio of the sample trees. The calculation formula is: in, is the proportion of the pest area of ​​the xth sample tree in the sample grid, is the pest area of ​​the x-th sample tree in the sample grid, is the total area of ​​the x-th sample tree in the sample grid, x is the index of the sample tree, and the mean of the pest area ratios of all sample trees is taken as the pest area ratio of the sample grid; The formula for calculating the pest area spread rate is: Among them, Pv(t) is the pest area spread speed of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the current moment, is the insect pest area ratio of the sample grid at the previous moment, Indicates the time interval between the current moment and the previous moment; Multiple sampling areas are randomly selected within the infested area of ​​the trees in the sample grid. Image data of the sampling areas are collected. The number of pests in each sampling area is obtained using image processing software. The pest density formula is calculated as follows: in, is the pest density in the sampling area, Pn is the number of pests in the sampling area image, and a is the area of ​​the sampling area; Calculate the pest density of all sampling areas and calculate the average value as the pest density of the corresponding sample grid. The formula for calculating the pest density growth rate is: in, is the pest density growth rate of the sample grid at the current moment, is the pest density of the sample grid at the current moment, is the pest density of the sample grid at the previous moment.

3. A forest pest prediction method according to claim 1, characterized in that: Constructing the pest prediction model specifically includes: The main tree species, tree characteristic data, environmental suitability index and pest severity level of several sample grids in the similar grid group were integrated into a sample set, and the sample set was divided into a training set and a test set with a division ratio of 7:

3. The main tree species, tree characteristic data and environmental suitability index in the training set were used as input, and the corresponding pest severity index was used as a label. The random forest model was trained to obtain a pest prediction model. The mean square error was set as the loss function, and the value of the loss function was monitored. When the value of the loss function dropped to 0.001 within 10 iterations, the model was considered to have been trained. The test set was then used to evaluate the model. The evaluation indicators were accuracy, precision and recall. If the accuracy, precision and recall were above 70%, the model performance was considered good. If the value of the evaluation indicator was lower than 70%, the model parameters were adjusted. Then, the main tree species, tree characteristic data and environmental suitability index of other grids in the same similar grid group except the sample grid are input into the trained pest prediction model to obtain the pest severity level output by the model.

4. A forest pest prediction method according to claim 1, characterized in that: Determining the pest situation in the forest includes: Get the proportion of grids with high pest severity level at the current moment. The calculation formula is: in, is the proportion of grids with high pest severity at the current moment, is the indicator function, when When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the current moment, which is high, medium, or low. n is the index of the grid, and N is the total number of grids. ; Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ; Get the proportion of grids with high pest severity level at the previous moment. The calculation formula is: in, is the proportion of grids with high pest severity level at the previous moment. When it is high, the value is 1, otherwise it is 0. is the classification value of the pest severity level corresponding to the nth grid at the previous moment, which is high, medium, or low; Similarly, the proportion of grids with medium pest severity level and low pest severity level at the current moment is obtained, which is expressed as ; Calculate the change in severity of different insect pests in the forest at the current moment. The formula for calculating the change in severity of high insect pests is: in, is the change in the high pest level at the current moment; Similarly, obtain the change in the pest level and the change in the low pest level at the current moment, expressed as ; According to the change in severity of different insect pests in the forest, an alarm index is generated. The calculation formula is: Among them, AI(t) is the alarm index of the forest at the current moment, are the weight coefficients of the corresponding items, ; Compare the forest alarm index at the current moment with the preset threshold. , if it is judged that there are many insect pests in the forest at the current moment, a high insect pest alarm will be issued. , judge that the insect pest in the forest is normal at the moment, then issue an insect pest alarm, if , if it is judged that there are few insect pests in the forest at the current moment, no alarm will be issued, where High risk threshold and low risk threshold.

5. A forest pest prediction system, characterized in that: The forest pest prediction system is used to implement the forest pest prediction method according to any one of claims 1 to 4, comprising: A characteristic parameter collection module is used to divide the forest area into N grids and collect characteristic parameters of each grid, including main tree species, tree characteristic data, soil property data and meteorological data; A sample selection module is used to divide all grids into multiple similar grid groups based on the soil property data of each grid, randomly select a number of sample grids from the similar grid groups, and obtain forest pest data for the sample grids, wherein the forest pest data includes the proportion of infested trees, the speed of spread of the infested area, and the growth rate of the infestation density; The pest severity level determination module is used to determine the environmental suitability index of each grid by combining the main tree species and meteorological data of the sample grid, analyze the tree characteristic data to obtain the tree vulnerability index of the sample grid, and analyze the tree vulnerability index and forest pest data of the sample grid based on the expert scoring method to determine the pest severity level of each grid; The pest prediction model construction module is used to construct a pest prediction model corresponding to each similar grid group based on the random forest algorithm. The main tree species, tree characteristic data and environmental suitability index of the sample grid in the same similar grid group are used as input, and the corresponding pest severity level is used as output to train the pest prediction model. After the pest prediction model is trained, the pest severity level of other grids in the same similar grid group except the sample grid is obtained; The pest monitoring and alarm module is used to analyze the distribution changes of pest severity levels of N grids at current and historical times, obtain the change in severity level of each pest, determine the pest situation in the forest and issue corresponding alarm signals.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting forest pests according to any one of claims 1 to 4 is implemented.

Images