A method for predicting the probability of occurrence of white moth pests, electronic equipment and storage medium

Abstract

A method for predicting the occurrence probability of gypsy moth diseases and insect pests, an electronic device and a storage medium belong to the technical field of gypsy moth disease and insect pest prediction. In order to efficiently and accurately predict gypsy moth diseases and insect pests, the present invention collects historical occurrence data of gypsy moth diseases and insect pests, forest ecological environment data and meteorological data, performs data cleaning and normalization processing; uses the Pearson correlation coefficient to analyze the influence of the pre-processed data on gypsy moth diseases and insect pests and the correlation between the data, extracts the relevant variables with the greatest correlation with the influence of gypsy moth diseases and insect pests, and constructs a training data set and a test data set; constructs a gypsy moth disease and insect pest occurrence probability prediction model based on a Transformer neural network; sets an evaluation index for the prediction accuracy of gypsy moth disease and insect pest occurrence probability; obtains monitoring data in real time, uses the gypsy moth disease and insect pest occurrence probability prediction model to conduct simulation experiments, and predicts the occurrence probability of gypsy moth diseases and insect pests.

Description

Technical Field

[0001] The invention belongs to the technical field of prediction of gypsy moth pests and diseases, and specifically relates to a method for predicting the occurrence probability of gypsy moth pests and diseases, an electronic device and a storage medium. Background Art

[0002] The gypsy moth is a serious pest that harms forest health. It can cause tree leaves to fall off and even cause large-scale mortality, posing a serious threat to forest ecosystems. Currently, there is still a lack of monitoring and prevention methods for this pest, and an efficient and accurate prediction strategy is needed. Summary of the invention

[0003] The problem to be solved by the present invention is to efficiently and accurately predict the occurrence probability of the American white moth pests and diseases, and a method for predicting the occurrence probability of the American white moth pests and diseases, an electronic device and a storage medium are proposed.

[0004] To achieve the above object, the present invention is implemented through the following technical solutions:

[0005] A method for predicting the probability of occurrence of white moth pests and diseases, comprising the following steps:

[0006] S1. Collect historical data on the occurrence of white moth pests and diseases, forest ecological environment data, and meteorological data, perform data cleaning and normalization, and obtain pre-processed data;

[0007] S2. For the pre-processed data obtained in step S1, the influence of the pre-processed data on the American white moth pests and diseases and the correlation between the data are analyzed using the Pearson correlation coefficient, and the relevant variables with the greatest correlation with the influence of the American white moth pests and diseases are extracted to construct a training data set and a test data set;

[0008] S3. Construct a prediction model for the occurrence probability of white moth pests based on Transformer neural network;

[0009] S4. Use the training set obtained in step S2 to train the probability prediction model of gypsy moth pests and diseases constructed in step S3, set the prediction accuracy evaluation index of the probability of occurrence of gypsy moth pests and diseases, and obtain a trained gypsy moth pests and diseases probability prediction model;

[0010] S5. Acquire monitoring data in real time, merge it with the test data set constructed in step S2, and use the trained prediction model for the occurrence probability of gypsy moth obtained in step S4 to conduct simulation experiments and predict the occurrence probability of gypsy moth.

[0011] Furthermore, the specific implementation method of step S1 includes the following steps:

[0012] S1.1. Collect historical data on the occurrence of white moth pests and diseases, and download historical data on the occurrence of white moth pests and diseases from the National Geographic Data Center;

[0013] S1.2. Data cleaning is performed on the historical occurrence data of the American white moth pests collected in step S1.1. The calculation expression for outlier processing is:

[0014]

[0015] Among them, X is the historical occurrence data of white moth pests, μ is the mean value, and σ is the standard deviation;

[0016] S1.3. Perform data normalization on the historical occurrence data of the gypsy moth pest after data cleaning in step S1.2. The calculation expression for data normalization is:

[0017]

[0018] Among them, X min is the minimum value of the historical occurrence data of the American white moth pest, X max This is the highest historical occurrence data of the white moth disease and pest in the United States.

[0019] Furthermore, step S2 uses the Pearson correlation coefficient to analyze the preprocessed data. The calculation expression of the Pearson correlation coefficient r is:

[0020]

[0021] Among them, m i and z i They represent the values ​​of the two variables at the i-th observation value, and points It represents the mean of two variables.

[0022] Furthermore, the specific implementation method of step S3 includes the following steps:

[0023] S3.1. Based on the Transformer Chinese BERT model, a prediction model for the occurrence probability of white moth pests was constructed, including an autoencoder-like network and multiple BERT encoder layers;

[0024] S3.2. Construct a quasi-autoencoder network, including a 4-fold downsampling module, a feature fusion module, 4 dynamic feature enhancement modules, and a 4-fold upsampling module, wherein the feature fusion module includes 8 feature attention blocks, a multilayer perceptron, and two hidden layers;

[0025] S3.3. Construct the BERT encoder layer, including the multi-head self-attention mechanism module, the normalization module, the feedforward neural network module, and the residual connection module.

[0026] Furthermore, in step S3, x is set i is the i-th element of the input sequence of the attention mechanism, x j is the jth element of the input sequence of the attention mechanism, y i is the attention output corresponding to the i-th element of the input sequence of the attention mechanism, then the attention output y corresponding to the i-th element of the input sequence of the attention mechanism i The calculation expression is:

[0027]

[0028] Among them, Attention(x i ,x j ) is used to measure x i and x j The attention weight of the relationship between j For the corresponding x j The weight matrix of , i is any one of n, j is any one of n, i≠j.

[0029] Furthermore, in step S4, the evaluation indexes for the prediction accuracy of the occurrence probability of the gypsy moth pests and diseases include the recall rate and the precision;

[0030] The calculation expression of the recall rate is TP / (TP+FN)

[0031] Among them, TP represents the number of samples where the gypsy moth occurrence probability prediction model predicts the occurrence of gypsy moth and the number of samples where the gypsy moth occurrence probability prediction model actually occurs, and FN represents the number of samples where the actual positive examples are incorrectly predicted as negative examples.

[0032] The calculation expression of the accuracy is TP / (TP+FP)

[0033] Among them, FP represents the number of samples in which the probability prediction model of the occurrence of the American white moth pest mistakenly predicts that the event will occur when there is actually no event.

[0034] Furthermore, the specific implementation method of step S5 includes the following steps:

[0035] S5.1. Use sound sensors to capture sound data generated by white moths, use micro-weather station sensors to collect localized meteorological information data, use soil sensors to collect soil condition data, and use network cameras to collect vegetation coverage data and white moth activity data to obtain real-time monitoring data;

[0036] S5.2. Design simulation experiment parameters, including regional scope, historical data of the occurrence of the gypsy moth, road density, night light density, average precipitation, maximum and minimum temperatures, and average temperature;

[0037] S5.3. Using the trained model for the probability of occurrence of gypsy moth pests in step S4, a simulation experiment was conducted based on the simulation experiment parameters designed in step S5.2;

[0038] S5.4. Evaluate the control effect of the simulation experiment conducted in step S5.3. The calculation expression of the control effect t is:

[0039]

[0040] in, and is the mean of the first and second groups, and is the standard deviation of the first and second groups, n1 and n2 are the sample sizes of the first and second groups;

[0041] S5.5. Perform a cost-effectiveness evaluation on the simulation experiment conducted in step S5.3. The cost-effectiveness calculation expression is:

[0042] Cost-effectiveness = (control effect - cost input) / cost input.

[0043] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a method for predicting the probability of occurrence of American white moth pests when executing the computer program.

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for predicting the probability of occurrence of gypsy moth pests.

[0045] Beneficial effects of the present invention:

[0046] The method for predicting the occurrence probability of gypsy moth pests and diseases disclosed in the present invention constructs a complete gypsy moth occurrence probability prediction and spread trend analysis system based on Transformer neural network, uses ArcGIS technology to achieve seamless integration of multi-source data, and improves the accuracy and timeliness of gypsy moth monitoring; uses GIS spatial analysis capabilities and combines the Transformer model to construct a gypsy moth occurrence probability prediction model to provide a scientific basis for prevention and control decisions; and through a real-time monitoring and early warning system, timely grasps the spread of the gypsy moth, and helps timely response and adjustment of prevention and control work.

[0047] The method for predicting the probability of occurrence of gypsy moth pests and diseases described in the present invention combines expert knowledge and historical experience to achieve scientific reference for prevention and control decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention provides a flow chart of a method for predicting the probability of occurrence of gypsy moth pests and diseases. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the specific embodiments described are only part of the embodiments of the present invention, rather than all of the specific embodiments. The components of the specific embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0050] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected specific embodiments of the present invention. Based on the specific embodiments of the present invention, all other specific embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0051] In order to further understand the content, features and effects of the present invention, the following specific implementation methods are given as examples, and the attached Figure 1 The detailed instructions are as follows: Specific implementation method one:

[0053] A method for predicting the probability of occurrence of white moth pests and diseases, comprising the following steps:

[0054] S1. Collect historical data on the occurrence of white moth pests and diseases, forest ecological environment data, and meteorological data, perform data cleaning and normalization, and obtain pre-processed data;

[0055] Furthermore, the specific implementation method of step S1 includes the following steps:

[0056] S1.1. Collect historical occurrence data of white moth pests and diseases, and download historical occurrence data of white moth pests and diseases from 2003 to 2021 from the National Geographic Data Center. The historical occurrence data includes the time column Year, the Chinese county code Region, the maximum temperature Factor1, the minimum temperature Factor2, the average temperature Factor3, the average precipitation Factor4, the occurrence of white moth in the next year Outcome, the night light density Factor5 and the road density Factor6;

[0057] S1.2. Data cleaning is performed on the historical occurrence data of the American white moth pests collected in step S1.1. The calculation expression for outlier processing is:

[0058]

[0059] Among them, X is the historical occurrence data of white moth pests, μ is the mean value, and σ is the standard deviation;

[0060] S1.3. Perform data normalization on the historical occurrence data of the gypsy moth pest after data cleaning in step S1.2. The calculation expression for data normalization is:

[0061]

[0062] Among them, X min is the minimum value of the historical occurrence data of the American white moth pest, X max This is the maximum historical occurrence data of white moth pests in the United States;

[0063] The historical occurrence data of white moth pests and diseases are shown in Table 1, where 1 means occurrence and 0 means no occurrence:

[0064] Table 1 Historical occurrence data of white moth pests and diseases

[0065]

[0066] S2. For the pre-processed data obtained in step S1, the influence of the pre-processed data on the American white moth pests and diseases and the correlation between the data are analyzed using the Pearson correlation coefficient, and the relevant variables with the greatest correlation with the influence of the American white moth pests and diseases are extracted to construct a training data set and a test data set;

[0067] Furthermore, step S2 uses the Pearson correlation coefficient to analyze the preprocessed data. The calculation expression of the Pearson correlation coefficient r is:

[0068]

[0069] Among them, m i and zi They represent the values ​​of the two variables at the i-th observation value, and points It represents the mean of two variables;

[0070] The value range of the Pearson correlation coefficient is between -1 and 1: r = 1 indicates a perfect positive correlation, that is, when one variable increases, the other variable also increases, and the change is completely linear. r = -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases, and the change is completely linear. r = 0 indicates no linear relationship;

[0071] S3. Construct a prediction model for the occurrence probability of white moth pests based on Transformer neural network;

[0072] Furthermore, the specific implementation method of step S3 includes the following steps:

[0073] S3.1. Based on the Transformer Chinese BERT model, a prediction model for the occurrence probability of white moth pests was constructed, including an autoencoder-like network and multiple BERT encoder layers;

[0074] S3.2. Construct a quasi-autoencoder network, including a 4-fold downsampling module, a feature fusion module, 4 dynamic feature enhancement modules, and a 4-fold upsampling module, wherein the feature fusion module includes 8 feature attention blocks, a multilayer perceptron, and two hidden layers;

[0075] S3.3. Construct the BERT encoder layer, including the multi-head self-attention mechanism module, the normalization module, the feedforward neural network module, and the residual connection module;

[0076] Furthermore, in step S3, x is set i is the i-th element of the input sequence of the attention mechanism, x j is the jth element of the input sequence of the attention mechanism, y i is the attention output corresponding to the i-th element of the input sequence of the attention mechanism, then the attention output y corresponding to the i-th element of the input sequence of the attention mechanism i The calculation expression is:

[0077]

[0078] Among them, Attention(x i ,x j ) is used to measure x i and x j The attention weight of the relationship between j For the corresponding x jThe weight matrix, i is any one of n, j is any one of n, i≠j;

[0079] S4. Use the training set obtained in step S2 to train the probability prediction model of gypsy moth pests and diseases constructed in step S3, set the prediction accuracy evaluation index of the probability of occurrence of gypsy moth pests and diseases, and obtain a trained gypsy moth pests and diseases probability prediction model;

[0080] Furthermore, in step S4, the evaluation indexes for the prediction accuracy of the occurrence probability of the gypsy moth pests and diseases include the recall rate and the precision;

[0081] The calculation expression of the recall rate is TP / (TP+FN)

[0082] Among them, TP represents the number of samples where the gypsy moth occurrence probability prediction model predicts the occurrence of gypsy moth and the number of samples where the gypsy moth occurrence probability prediction model actually occurs, and FN represents the number of samples where the actual positive examples are incorrectly predicted as negative examples.

[0083] The calculation expression of the accuracy is TP / (TP+FP)

[0084] Among them, FP represents the number of samples where the probability prediction model for the occurrence of the American white moth pest incorrectly predicts that the event will occur when the event does not actually occur;

[0085] S5. Real-time monitoring data is acquired and merged with the test data set constructed in step S2. The trained prediction model for the occurrence probability of gypsy moth pests and diseases obtained in step S4 is used to conduct simulation experiments to predict the occurrence probability of gypsy moth pests and diseases;

[0086] Furthermore, the specific implementation method of step S5 includes the following steps:

[0087] S5.1. Use sound sensors to capture sound data generated by white moths, use micro-weather station sensors to collect localized meteorological information data, use soil sensors to collect soil condition data, and use network cameras to collect vegetation coverage data and white moth activity data to obtain real-time monitoring data;

[0088] S5.2. Design simulation experiment parameters, including regional scope, historical data of the occurrence of the gypsy moth, road density, night light density, average precipitation, maximum and minimum temperatures, and average temperature;

[0089] S5.3. Using the trained model for the probability of occurrence of gypsy moth pests in step S4, a simulation experiment was conducted based on the simulation experiment parameters designed in step S5.2;

[0090] S5.4. Evaluate the control effect of the simulation experiment conducted in step S5.3. The calculation expression of the control effect t is:

[0091]

[0092] in, and is the mean of the first and second groups, and is the standard deviation of the first and second groups, n1 and n2 are the sample sizes of the first and second groups;

[0093] S5.5. Perform a cost-effectiveness evaluation on the simulation experiment conducted in step S5.3. The cost-effectiveness calculation expression is:

[0094] Cost-effectiveness = (control effect - cost input) / cost input. Specific implementation method 2:

[0096] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for predicting the probability of occurrence of a white moth pest and disease as described in implementation mode 1 are implemented.

[0097] The computer device of the present invention may be a device including a processor and a memory, such as a single chip microcomputer including a central processing unit, etc. Moreover, the processor is used to implement the steps of the above-mentioned method for predicting the probability of occurrence of American white moth pests when executing the computer program stored in the memory.

[0098] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Specific implementation method three:

[0101] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for predicting the probability of occurrence of a gypsy moth pest described in a first specific implementation manner.

[0102] The computer-readable storage medium of the present invention can be any form of storage medium that can be read by the processor of a computer device, including but not limited to non-volatile memory, volatile memory, ferroelectric memory, etc. The computer-readable storage medium stores a computer program. When the processor of the computer device reads and executes the computer program stored in the memory, the steps of the above-mentioned method for predicting the probability of occurrence of American white moth pests can be implemented.

[0103] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0104] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0105] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present application. In particular, as long as there is no structural conflict, the various features in the specific embodiments disclosed in the present application may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for predicting the probability of occurrence of gypsy moth pests, characterized in that: The steps include: S1. Collect historical data on the occurrence of white moth pests and diseases, forest ecological environment data, and meteorological data, perform data cleaning and normalization, and obtain pre-processed data; The specific implementation method of step S1 includes the following steps: S1.

1. Collect historical data on the occurrence of white moth pests and diseases, and download historical data on the occurrence of white moth pests and diseases from the National Geographic Data Center; S1.

2. Data cleaning is performed on the historical occurrence data of the American white moth pests collected in step S1.

1. The calculation expression for outlier processing is: Among them, X is the historical occurrence data of white moth pests, μ is the mean value, and σ is the standard deviation; S1.

3. Perform data normalization on the historical occurrence data of the gypsy moth pest after data cleaning in step S1.

2. The calculation expression for data normalization is: Among them, X min is the minimum value of the historical occurrence data of the American white moth pest, X max This is the maximum historical occurrence data of white moth pests in the United States; S2. For the pre-processed data obtained in step S1, the influence of the pre-processed data on the American white moth pests and diseases and the correlation between the data are analyzed using the Pearson correlation coefficient, and the relevant variables with the greatest correlation with the influence of the American white moth pests and diseases are extracted to construct a training data set and a test data set; S3. Construct a prediction model for the occurrence probability of white moth pests based on Transformer neural network; The specific implementation method of step S3 includes the following steps: S3.

1. Based on the Transformer Chinese BERT model, a prediction model for the occurrence probability of white moth pests was constructed, including an autoencoder-like network and multiple BERT encoder layers; S3.

2. Construct a quasi-autoencoder network, including a 4-fold downsampling module, a feature fusion module, 4 dynamic feature enhancement modules, and a 4-fold upsampling module, wherein the feature fusion module includes 8 feature attention blocks, a multilayer perceptron, and two hidden layers; S3.

3. Construct the BERT encoder layer, including the multi-head self-attention mechanism module, the normalization module, the feedforward neural network module, and the residual connection module; In step S3, x is set i is the i-th element of the input sequence of the attention mechanism, x j is the jth element of the input sequence of the attention mechanism, y i is the attention output corresponding to the i-th element of the input sequence of the attention mechanism, then the attention output y corresponding to the i-th element of the input sequence of the attention mechanism i The calculation expression is: Among them, Attention(x i ,x j ) is used to measure x i and x j The attention weight of the relationship between j For the corresponding x j The weight matrix, i is any one of n, j is any one of n, i≠j; S4. Use the training set obtained in step S2 to train the probability prediction model of gypsy moth pests and diseases constructed in step S3, set the prediction accuracy evaluation index of the probability of occurrence of gypsy moth pests and diseases, and obtain a trained gypsy moth pests and diseases probability prediction model; S5. Real-time acquisition of monitoring data, fusion with the test data set constructed in step S2, simulation experiment using the trained gypsy moth pest occurrence probability prediction model obtained in step S4, to predict the probability of gypsy moth pest occurrence; The specific implementation method of step S5 includes the following steps: S5.

1. Use sound sensors to capture sound data generated by white moths, use micro-weather station sensors to collect localized meteorological information data, use soil sensors to collect soil condition data, and use network cameras to collect vegetation coverage data and white moth activity data to obtain real-time monitoring data; S5.

2. Design simulation experiment parameters, including regional scope, historical data of the occurrence of the gypsy moth, road density, night light density, average precipitation, maximum and minimum temperatures, and average temperature; S5.

3. Using the trained model for the probability of occurrence of gypsy moth pests in step S4, a simulation experiment was conducted based on the simulation experiment parameters designed in step S5.2; S5.

4. Evaluate the control effect of the simulation experiment conducted in step S5.

3. The calculation expression of the control effect t is: in, and is the mean of the first and second groups, and is the standard deviation of the first and second groups, n1 and n2 are the sample sizes of the first and second groups; S5.

5. Perform a cost-effectiveness evaluation on the simulation experiment conducted in step S5.

3. The cost-effectiveness calculation expression is: Cost-effectiveness = (control effect - cost input) / cost input.

2. The method for predicting the probability of occurrence of gypsy moth pests according to claim 1, characterized in that: Step S2 uses the Pearson correlation coefficient to analyze the preprocessed data. The calculation expression of the Pearson correlation coefficient r is: Among them, m i and z i They represent the values ​​of the two variables at the i-th observation value, and points It represents the mean of two variables.

3. A method for predicting the occurrence probability of gypsy moth pests according to claim 2, characterized in that: In step S4, the evaluation indexes for the prediction accuracy of the occurrence probability of the gypsy moth pests and diseases are set to include the recall rate and the precision; The calculation expression of the recall rate is TP / (TP+FN) Among them, TP represents the number of samples where the gypsy moth occurrence probability prediction model predicts the occurrence of gypsy moth and the number of samples where the gypsy moth occurrence probability prediction model actually occurs, and FN represents the number of samples where the actual positive examples are incorrectly predicted as negative examples. The calculation expression of the accuracy is TP / (TP+FP) Among them, FP represents the number of samples in which the probability prediction model of the occurrence of the American white moth pest mistakenly predicts that the event will occur when there is actually no event.

4. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for predicting the occurrence probability of a white moth disease and pest as claimed in any one of claims 1 to 3 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the probability of occurrence of gypsy moth pests and diseases as described in any one of claims 1 to 3 is implemented.

Images