A method for predicting the occurrence of pine wood nematode disease, electronic equipment and storage medium

Abstract

A method for predicting the occurrence of pine wilt disease, an electronic device and a storage medium belong to the technical field of big data prediction and control of forest pests and diseases. In order to improve the accuracy of the prediction of the occurrence of pine wilt disease, the present invention establishes a data set of multi-source influencing factors of pine wilt disease; divides the data into time and space, and then performs data cleaning, data integration, data conversion and normalization processing to divide it into corresponding training sets and prediction sets; constructs a cellular automaton model for pine wilt disease; constructs a temporal convolutional network model for pine wilt disease; uses the processed prediction set of the multi-source influencing factor data set of pine wilt disease to input into the trained cellular automaton model of pine wilt disease and the temporal convolutional network model for pine wilt disease, and predicts the occurrence of pine wilt disease; generates an integrated layer based on the ArcGIS visualization geographic information system for the prediction results of the occurrence of pine wilt disease. The present invention predicts accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data prediction and prevention and control of forest pests and diseases, and specifically relates to a method for predicting the occurrence of pine wood nematode disease, an electronic device and a storage medium. Background Art

[0002] Pine wilt disease is a forest disease caused by pine wood nematodes. The disease is widely found in pine forests around the world, posing a huge threat to the health and stability of forest ecosystems. Therefore, timely and accurate prediction of the occurrence of pine wilt disease is crucial for taking effective prevention and control measures. Traditional predictions of pine wilt disease are mainly based on traditional statistical models and small sample data. These methods are usually unable to capture complex data relationships and spatiotemporal changes, resulting in inaccurate and unreliable prediction results. In addition, traditional statistical models are also difficult to handle large-scale multi-source data, limiting the flexibility and effectiveness of prediction models. Summary of the invention

[0003] The present invention aims to improve the accuracy of prediction of pine wood nematode disease occurrence, and proposes a pine wood nematode disease occurrence prediction method, electronic equipment and storage medium.

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

[0005] A method for predicting the occurrence of pine wood nematode disease comprises the following steps:

[0006] S1. Collect meteorological data, soil data, geographic information data, remote sensing data and historical data of pine wood nematode disease to establish a dataset of multi-source influencing factors of pine wood nematode disease;

[0007] S2. The data in the pine wood nematode disease multi-source influencing factor data set established in step S1 is divided into time and space, and then data cleaning, data integration, data conversion and normalization are performed to obtain a processed pine wood nematode disease multi-source influencing factor data set for standby use;

[0008] S3. dividing the processed pine wood nematode disease multi-source influencing factor data set obtained in step S2 into a training set and a prediction set;

[0009] S4. constructing a cellular automaton model for pine wilt disease, inputting the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 into the cellular automaton model for pine wilt disease for training, and outputting the spatial prediction data of pine wilt disease occurrence;

[0010] S5. Construct a temporal convolutional network model for pine wood nematode disease, combine the pine wood nematode disease multi-source influencing factor data set training set obtained in step S3 and the spatial prediction data of pine wood nematode disease occurrence obtained in step S4, and input them into the temporal convolutional network model for pine wood nematode disease for training, and output the predicted probability of pine wood nematode disease occurrence based on the zoning code under the influence of the influencing factors;

[0011] S6. using the prediction set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 to be input into the trained cellular automaton model of pine wilt disease and the temporal convolutional network model for pine wilt disease to predict the occurrence of pine wilt disease;

[0012] S7. Generate an integrated layer based on the ArcGIS visual geographic information system based on the pine wood nematode disease occurrence prediction result obtained in step S6.

[0013] Furthermore, in step S2, the data in the pine wood nematode disease multi-source influencing factor data set established in step S1 are divided into space and time. First, the data of the smallest spatial unit studied in the same area are put together according to the zoning code to complete the spatial division; on the basis of the spatial division, they are sorted according to time to complete the temporal division.

[0014] Furthermore, in step S3, the data division ratio of the training set and the prediction set is 7:3.

[0015] Furthermore, the specific implementation method of step S4 includes the following steps:

[0016] S4.1. Based on geographic information data, a two-dimensional grid network is constructed. The cells in each grid are used as the basic units of the cellular automaton model for pine wood nematode disease. The cell states are set to include healthy, infected, dead, and empty. The properties of the cell states are as follows:

[0017] Health status: The pine tree in the cell is in a healthy state and is susceptible;

[0018] Infection status: The pine trees in the cell exceed a certain threshold according to the rules, resulting in infection with pine wilt disease, which begins to infect the pine trees;

[0019] Death state: In the late stage of pine wilt disease, after a period of time, the pine trees die, but the disease is still contagious in this state;

[0020] Hollow state: After the pine tree dies, the infected wood is promptly treated and the area is hollowed out, and the cells are defined as hollow;

[0021] S4.2. Based on the cell state set in step S4.1, the objective function of the cellular automaton model for pine wood nematode disease is designed, and the expression is:

[0022]

[0023] in, is the objective function of cell j at time t, is the state of cell j at time t, P, T, and R are the adjacent boundary length, road density, and Euclidean distance of cell j, respectively. ω1, ω2, and ω3 are the weight coefficients of the corresponding adjacent boundary length, road density, and Euclidean distance, respectively. is the state combination of N neighbors at time t;

[0024] S4.3. Design state transition function: The state transition function is the rule for a cell to update its state according to the state of its neighbors at time t+1. The expression is:

[0025]

[0026] Where f is the local mapping or local rule of the cellular automaton. Under the mapping of f, the state of cell j at the next moment can be obtained through the state of cell j at time t and the objective function of cell j.

[0027] S4.4. Based on the data in the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3, the objective function of the cellular automaton model for pine wilt disease in step S4.2 is iteratively updated using the stochastic gradient descent method, and the expression is:

[0028]

[0029] Among them, ω i is the i-th weight coefficient, α is the learning rate, that is, the iteration step length;

[0030] The weight coefficient was modified to improve the prediction accuracy, and finally the spatial prediction data of pine wood nematode occurrence was obtained.

[0031] Furthermore, the specific implementation method of step S5 includes the following steps:

[0032] S5.1. Construct a temporal convolutional network model for pine wood nematode disease, including a multi-channel input layer, a 3*3 dilated causal convolution layer, a 1*1 residual convolution layer, a normalization layer, and a Dropout layer. The output of the multi-channel input layer is connected to the input of the 3*3 dilated causal convolution layer, the output of the 3*3 dilated causal convolution layer is connected to the input of the normalization layer, the output of the normalization layer is connected to the input of the Dropout layer, and the output of the Dropout layer is the final output. Each layer is connected through a 1*1 residual convolution layer, and RELU is selected as the activation function.

[0033] S5.2. Add the spatial prediction data of pine wilt disease occurrence obtained in step S4 to the processed pine wilt disease multi-source influencing factor dataset according to the geographic information data, and obtain an updated training set of the processed pine wilt disease multi-source influencing factor dataset, and read it through the multi-channel input layer to obtain the input sequence X = {x1,…,x T};

[0034] Dilated causal convolution is a convolution operation based on causal convolution. A 3*3 convolution kernel is used. The expression of dilated causal convolution is:

[0035]

[0036] Where G(s) is the dilated causal convolution, d is the dilation factor, k is the filter size, and x s-d·i is the past direction data value of the input sequence, f(i) is the filter in the residual function;

[0037] The connection between layers is set to a 1*1 residual convolution layer. The 1*1 residual convolution layer contains branches leading to a series of transformations G(s), expressed as:

[0038] output=Activation(x+G(x))

[0039] Among them, G(x) is the module output of the residual convolution layer for the input x, output is the result of the sum of input x and G(x) under the action of the activation function, and Activation is the activation function;

[0040] S5.3. Based on multiple iterations, the temporal convolutional network model for pine wood nematode disease is trained, and the evaluation index R2_score is introduced to correct the weights and biases of each neural network layer and each neuron in each layer. The calculation expression of R2_score is:

[0041]

[0042] in, is the predicted value of the i-th data, y (i) is the true value of the i-th data, is the average value;

[0043] According to the model update results, the data is reduced in dimension again through the Dropout layer, and the output result is the predicted probability of pine wood nematode disease for the zoning code under the influence of the influencing factors.

[0044] 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 occurrence of pine wood nematode disease when executing the computer program.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for predicting the occurrence of pine wood nematode disease.

[0046] Beneficial effects of the present invention:

[0047] The method for predicting the occurrence of pine wilt disease described in the present invention comprehensively utilizes cellular automata (CA) and temporal convolutional networks (TCN) models to predict the occurrence of pine wilt disease. The accuracy and reliability of the prediction are improved by combining the simulation of spatial pattern and multi-source data modeling. The method of using multiple models in series makes up for the limitations of a single model, has high timeliness, high accuracy and scalability, and can be applied to the prediction and management of a wide range of pine wilt disease.

[0048] The method for predicting the occurrence of pine wilt disease described in the present invention has achieved new breakthroughs in the field of predicting the occurrence of pine wilt disease, provided more scientific and accurate decision-making support for the protection and management of forest resources, made positive contributions to related research and practical work, and achieved effective management and prevention of pine wilt disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of a method for predicting the occurrence of pine wood nematode disease according to the present invention;

[0050] Figure 2 This is a schematic diagram of the temporal convolutional network model for pine wood nematode disease described in the present invention. DETAILED DESCRIPTION

[0051] 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.

[0052] 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.

[0053] 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 and attached Figure 2 The detailed instructions are as follows: Specific implementation method one:

[0055] A method for predicting the occurrence of pine wood nematode disease comprises the following steps:

[0056] S1. Collect meteorological data, soil data, geographic information data, remote sensing data and historical data of pine wood nematode disease to establish a dataset of multi-source influencing factors of pine wood nematode disease;

[0057] Furthermore, the data in step S1 include background data of pine wood nematode disease, temperature, precipitation, road density and diseased wood transportation conditions;

[0058] S2. The data in the pine wood nematode disease multi-source influencing factor data set established in step S1 is divided into time and space, and then data cleaning, data integration, data conversion and normalization are performed to obtain a processed pine wood nematode disease multi-source influencing factor data set for standby use;

[0059] Furthermore, in step S2, the data in the pine wood nematode disease multi-source influencing factor data set established in step S1 are divided into space and time. First, the data of the smallest spatial unit studied in the same area are put together according to the zoning code to complete the spatial division; on the basis of the spatial division, the data are sorted according to time to complete the temporal division;

[0060] Furthermore, the method of completing the spatial division by putting together the data of the smallest spatial unit studied in the same area according to the zoning code is to subdivide it based on the smallest unit township, first classify it together according to the same province, city, district, and county, and then divide the space based on the smallest unit township.

[0061] S3. dividing the processed pine wood nematode disease multi-source influencing factor data set obtained in step S2 into a training set and a prediction set;

[0062] Furthermore, in step S3, the data division ratio of the training set and the prediction set is 7:3;

[0063] S4. constructing a cellular automaton model for pine wilt disease, inputting the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 into the cellular automaton model for pine wilt disease for training, and outputting the spatial prediction data of pine wilt disease occurrence;

[0064] Furthermore, the specific implementation method of step S4 includes the following steps:

[0065] S4.1. Based on geographic information data, a two-dimensional grid network is constructed. The cells in each grid are used as the basic units of the cellular automaton model for pine wood nematode disease. The cell states are set to include healthy, infected, dead, and empty. The properties of the cell states are as follows:

[0066] Health status: The pine tree in the cell is in a healthy state and is susceptible;

[0067] Infection status: The pine trees in the cell exceed a certain threshold according to the rules, resulting in infection with pine wilt disease, which begins to infect the pine trees;

[0068] Death state: In the late stage of pine wilt disease, after a period of time, the pine trees die, but the disease is still contagious in this state;

[0069] Hollow state: After the pine tree dies, the infected wood is promptly treated and the area is hollowed out, and the cells are defined as hollow;

[0070] S4.2. Based on the cell state set in step S4.1, the objective function of the cellular automaton model for pine wood nematode disease is designed, and the expression is:

[0071]

[0072] in, is the objective function of cell j at time t, is the state of cell j at time t, P, T, and R are the adjacent boundary length, road density, and Euclidean distance of cell j, respectively. ω1, ω2, and ω3 are the weight coefficients of the corresponding adjacent boundary length, road density, and Euclidean distance, respectively. is the state combination of N neighbors at time t;

[0073] Furthermore, the weight of each influencing factor is controlled by adjusting the weight coefficient. The cell neighborhood adopts a Moore-type structure, and the boundary extends infinitely, that is, the neighbor of a cell can be a cell on the other side of the model, so the infection probability P can be solved through the neighbor state. According to the range of the objective function, a threshold β is set, and the cell state can be updated when the threshold β is exceeded.

[0074] S4.3. Design state transition function: The state transition function is the rule for a cell to update its state according to the state of its neighbors at time t+1. The expression is:

[0075]

[0076] Where f is the local mapping or local rule of the cellular automaton. Under the mapping of f, the state of cell j at the next moment can be obtained through the state of cell j at time t and the objective function of cell j.

[0077] S4.4. Based on the data in the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3, the objective function of the cellular automaton model for pine wilt disease in step S4.2 is iteratively updated using the stochastic gradient descent method, and the expression is:

[0078]

[0079] Among them, ω i is the i-th weight coefficient, α is the learning rate, that is, the iteration step length;

[0080] The weight coefficients were modified to improve the prediction accuracy, and finally the spatial prediction data of pine wood nematode occurrence were obtained;

[0081] Furthermore, if α is set too large, there will be oscillation problems and the gradient cannot be reduced; if it is set too small, the model iteration time will be increased. It is stipulated that the parameter update can be stopped when the gradient drops to a small value not greater than a certain value to prevent the model from falling into a local optimal solution and affecting the generalization ability; the spatial prediction data of pine wood nematode disease will be added to the data set based on the geographic information data to ensure that the output spatial prediction data has the same dimension as the data set data;

[0082] S5. Construct a temporal convolutional network model for pine wood nematode disease, combine the pine wood nematode disease multi-source influencing factor data set training set obtained in step S3 and the spatial prediction data of pine wood nematode disease occurrence obtained in step S4, and input them into the temporal convolutional network model for pine wood nematode disease for training, and output the predicted probability of pine wood nematode disease occurrence based on the zoning code under the influence of the influencing factors;

[0083] Furthermore, the specific implementation method of step S5 includes the following steps:

[0084] S5.1. Construct a temporal convolutional network model for pine wood nematode disease, including a multi-channel input layer, a 3*3 dilated causal convolution layer, a 1*1 residual convolution layer, a normalization layer, and a Dropout layer. The output of the multi-channel input layer is connected to the input of the 3*3 dilated causal convolution layer, the output of the 3*3 dilated causal convolution layer is connected to the input of the normalization layer, the output of the normalization layer is connected to the input of the Dropout layer, and the output of the Dropout layer is the final output. Each layer is connected through a 1*1 residual convolution layer, and RELU is selected as the activation function.

[0085] S5.2. Add the spatial prediction data of pine wilt disease occurrence obtained in step S4 to the processed pine wilt disease multi-source influencing factor dataset according to the geographic information data, and obtain an updated training set of the processed pine wilt disease multi-source influencing factor dataset, and read it through the multi-channel input layer to obtain the input sequence X = {x1, ..., x T};

[0086] Dilated causal convolution is a convolution operation based on causal convolution. A 3*3 convolution kernel is used. The expression of dilated causal convolution is:

[0087]

[0088] Where G(s) is the dilated causal convolution, d is the dilation factor, k is the filter size, and x s-d·i is the past direction data value of the input sequence, f(i) is the filter in the residual function;

[0089] The connection between layers is set to a 1*1 residual convolution layer. The 1*1 residual convolution layer contains branches leading to a series of transformations G(s), expressed as:

[0090] output=Activation(x+G(x))

[0091] Among them, G(x) is the module output of the residual convolution layer for the input x, output is the result of the sum of input x and G(x) under the action of the activation function, and Activation is the activation function;

[0092] S5.3. Based on multiple iterations, the temporal convolutional network model for pine wood nematode disease is trained, and the evaluation index R2_score is introduced to correct the weights and biases of each neural network layer and each neuron in each layer. The calculation expression of R2_score is:

[0093]

[0094] in, is the predicted value of the i-th data, y (i) is the true value of the i-th data, is the average value;

[0095] According to the model update results, the data is reduced in dimension again through the Dropout layer, and the output result is the predicted probability of pine wood nematode disease for the zoning code under the influence of the influencing factors;

[0096] S6. using the prediction set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 to be input into the trained cellular automaton model of pine wilt disease and the temporal convolutional network model for pine wilt disease to predict the occurrence of pine wilt disease;

[0097] Furthermore, the TCN model is used to analyze the output of the cellular automaton model and the time data to obtain the occurrence probability and the most relevant features under each influencing factor, and to capture the spatiotemporal relationship, thereby realizing the prediction and analysis of the occurrence of pine wilt disease. By training and optimizing the model, the probability or level of spatiotemporal occurrence of pine wilt disease can be obtained;

[0098] S7. Generate an integrated layer based on the ArcGIS visual geographic information system based on the pine wood nematode disease occurrence prediction result obtained in step S6.

[0099] Furthermore, according to the predicted pest occurrence results, ArcGIS-based visual geographic information system (GIS) integrated layers can be generated. These layers can intuitively display the probability distribution or grade distribution of pine wood nematode disease, assisting relevant departments in making decisions and implementing prevention and control measures. Specific implementation method 2:

[0101] An electronic device 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 of pine wood nematode disease described in a specific implementation mode 1 are implemented.

[0102] 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 occurrence of pine wood nematode disease when executing the computer program stored in the memory.

[0103] 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.

[0104] 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:

[0106] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, a method for predicting the occurrence of pine wood nematode disease as described in the first specific implementation manner is implemented.

[0107] The computer-readable storage medium of the present invention can be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, volatile memory, ferroelectric memory, etc. A computer program is stored on the computer-readable storage medium. 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 occurrence of pine wood nematode disease can be implemented.

[0108] 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.

[0109] 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.

[0110] 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 occurrence of pine wood nematode disease, characterized in that: The steps include: S1. Collect meteorological data, soil data, geographic information data, remote sensing data and historical data of pine wood nematode disease to establish a dataset of multi-source influencing factors of pine wood nematode disease; S2. The data in the pine wood nematode disease multi-source influencing factor data set established in step S1 is divided into time and space, and then data cleaning, data integration, data conversion and normalization are performed to obtain a processed pine wood nematode disease multi-source influencing factor data set for standby use; In step S2, the data in the pine wood nematode disease multi-source influencing factor data set established in step S1 are divided into space and time. First, the data of the smallest spatial unit studied in the same area are put together according to the zoning code to complete the spatial division; on the basis of the spatial division, they are sorted according to time to complete the temporal division; S3. dividing the processed pine wood nematode disease multi-source influencing factor data set obtained in step S2 into a training set and a prediction set; S4. constructing a cellular automaton model for pine wilt disease, inputting the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 into the cellular automaton model for pine wilt disease for training, and outputting the spatial prediction data of pine wilt disease occurrence; S5. Construct a temporal convolutional network model for pine wood nematode disease, combine the pine wood nematode disease multi-source influencing factor data set training set obtained in step S3 and the spatial prediction data of pine wood nematode disease occurrence obtained in step S4, and input them into the temporal convolutional network model for pine wood nematode disease for training, and output the predicted probability of pine wood nematode disease occurrence based on the zoning code under the influence of the influencing factors; S6. using the prediction set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3 and its corresponding spatial prediction data of pine wilt disease occurrence to be input into the trained cellular automaton model of pine wilt disease and the temporal convolutional network model for pine wilt disease, to predict the occurrence of pine wilt disease; S7. Generate an integrated layer based on the ArcGIS visual geographic information system based on the pine wood nematode disease occurrence prediction result obtained in step S6.

2. The method for predicting the occurrence of pine wood nematode disease according to claim 1, characterized in that: The data division ratio of the training set and the prediction set in step S3 is 7:

3.

3. A method for predicting the occurrence of pine wood nematode disease according to claim 2, characterized in that: The specific implementation method of step S4 includes the following steps: S4.

1. Based on geographic information data, a two-dimensional grid network is constructed. The cells in each grid are used as the basic units of the cellular automaton model for pine wood nematode disease. The cell states are set to include healthy, infected, dead, and empty. The properties of the cell states are as follows: Health status: The pine tree in the cell is in a healthy state and is susceptible; Infection status: The pine trees in the cell exceed a certain threshold according to the rules, resulting in infection with pine wilt disease, which begins to infect the pine trees; Death state: In the late stage of pine wilt disease, after a period of time, the pine trees die, but the disease is still contagious in this state; Hollow state: After the pine tree died, the diseased wood was promptly treated. After this area was hollowed out, the cells were defined as hollow; S4.

2. Based on the cell state set in step S4.1, the objective function of the cellular automaton model for pine wood nematode disease is designed, and the expression is: in, is the objective function of cell j at time t, is the state of cell j at time t, P, T, and R are the adjacent boundary length, road density, and Euclidean distance of cell j, respectively. ω1, ω2, and ω3 are the weight coefficients of the corresponding adjacent boundary length, road density, and Euclidean distance, respectively. is the state combination of N neighbors at time t; S4.

3. Design state transition function: The state transition function is the rule for a cell to update its state according to the state of its neighbors at time t+1. The expression is: Where f is the local mapping or local rule of the cellular automaton. Under the mapping of f, the state of cell j at the next moment is obtained by the state of cell j at the moment t and the objective function of cell j. S4.

4. Based on the data in the training set of the processed pine wilt disease multi-source influencing factor data set obtained in step S3, the objective function of the cellular automaton model for pine wilt disease in step S4.2 is iteratively updated using the stochastic gradient descent method, and the expression is: Among them, ω i is the i-th weight coefficient, α is the learning rate, that is, the iteration step length; The weight coefficient was modified to improve the prediction accuracy, and finally the spatial prediction data of pine wood nematode occurrence was obtained.

4. A method for predicting the occurrence of pine wood nematode disease according to claim 3, characterized in that: The specific implementation method of step S5 includes the following steps: S5.

1. Construct a temporal convolutional network model for pine wood nematode disease, including a multi-channel input layer, a 3*3 dilated causal convolution layer, a 1*1 residual convolution layer, a normalization layer, and a Dropout layer. The output of the multi-channel input layer is connected to the input of the 3*3 dilated causal convolution layer, the output of the 3*3 dilated causal convolution layer is connected to the input of the normalization layer, the output of the normalization layer is connected to the input of the Dropout layer, and the output of the Dropout layer is the final output. Each layer is connected through a 1*1 residual convolution layer, and RELU is selected as the activation function. S5.

2. Add the spatial prediction data of pine wilt disease occurrence obtained in step S4 to the processed pine wilt disease multi-source influencing factor dataset according to the geographic information data, and obtain an updated training set of the processed pine wilt disease multi-source influencing factor dataset, and read it through the multi-channel input layer to obtain the input sequence X = {x1,…,x T }; Dilated causal convolution is a convolution operation based on causal convolution. A 3*3 convolution kernel is used. The expression of dilated causal convolution is: Where G(s) is the dilated causal convolution, d is the dilation factor, k is the filter size, and x s-d·i is the past direction data value of the input sequence, f(i) is the filter in the residual function; The connection between layers is set to a 1*1 residual convolution layer. The 1*1 residual convolution layer contains branches leading to a series of transformations G(s), expressed as: output=Activation(x+G(x)) Among them, G(x) is the module output of the residual convolution layer for the input x, output is the result of the sum of input x and G(x) under the action of the activation function, and Activation is the activation function; S5.

3. Based on multiple iterations, the temporal convolutional network model for pine wood nematode disease is trained, and the evaluation index R2_score is introduced to correct the weights and biases of each neural network layer and each neuron in each layer. The calculation expression of R2_score is: in, is the predicted value of the i-th data, y (i) is the true value of the i-th data, is the average value; According to the model update results, the data is reduced in dimension again through the Dropout layer, and the output result is the predicted probability of pine wood nematode disease for the zoning code under the influence of the influencing factors.

5. An electronic device, characterized in that: The method 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 occurrence of pine wood nematode disease as claimed in any one of claims 1 to 4 when executing the computer program.

6. 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 occurrence of pine wood nematode disease according to any one of claims 1 to 4 is implemented.

Images