Intelligent identification and control method and system for pine wood nematode disease based on artificial intelligence

Abstract

The application discloses an intelligent recognition and control method and system for pine wood nematode disease based on artificial intelligence, relates to the technical field of forest control, and discloses a pine forest area division control module, a pine wood nematode disease recognition module, a pine wood nematode disease treatment analysis module, and a regional control sequencing module. The pine forest area division control module and the pine wood nematode disease recognition module are arranged to reasonably control the area of a pine forest, accurately recognize the pine wood nematode disease of the pine forest area through multi-dimensional disease feature deep analysis, the pine wood nematode disease treatment analysis module and the regional control sequencing module are arranged, a pine forest simulation control model of a pine wood nematode disease recognition area is constructed, the actual situation of the pine wood nematode disease recognition area in subsequent control and treatment is accurately analyzed, and the current disease situation, the subsequent disease treatment situation and the disease influence situation of the pine wood nematode disease recognition area are quantitatively analyzed.

Description

Technical Field

[0001] This invention relates to the field of forest management technology, and more specifically, to an intelligent identification and management method and system for pine wilt disease based on artificial intelligence. Background Technology

[0002] Pine wilt disease is a deadly disease affecting pine trees. The pathogen, a nematode, is transmitted by pine-borne insects (such as the pine sawyer beetle) and invades the tree, causing it to wither and die rapidly. This disease poses a serious threat to forest resources globally, particularly in regions where pine is a dominant tree species or economically important timber.

[0003] Traditional methods for identifying and controlling pine wilt disease mainly rely on manual inspections and pathological analysis. This approach is not only time-consuming and labor-intensive, but also easily affected by human factors and environmental conditions, resulting in low accuracy and efficiency in identification and control. With the continuous expansion of forest areas and the increasing complexity of the disease, traditional methods are no longer sufficient to meet the actual needs of current pine wilt disease control efforts.

[0004] In recent years, the rapid development of artificial intelligence (AI) technology has provided new possibilities for the intelligent identification and control of pine wilt disease. By utilizing advanced technologies such as computer vision, efficient and accurate feature extraction and classification of pine disease images can be achieved, thus enabling rapid identification of pine wilt disease. However, relying solely on intelligent identification technology is insufficient for effective control of pine wilt disease. Therefore, how to combine AI technology to construct a complete intelligent identification and control method and system for pine wilt disease, achieving accurate identification, scientific management, and efficient control of pine wilt disease in pine forest areas, has become an urgent problem to be solved. Summary of the Invention

[0005] In view of the shortcomings of existing technologies, the purpose of this invention is to provide an intelligent identification and control method and system for pine wilt disease based on artificial intelligence.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The AI-based intelligent identification and control system for pine wilt disease includes a pine forest area division and control module, a pine wilt disease identification module, a pine wilt disease control analysis module, and an area control ranking module. The pine forest area division and control module is used to divide the target pine forest area into multiple pine forest control areas. The pine wilt disease identification module is used to set the pine forest management cycle. After each pine forest management cycle, aerial images of the pine forest area in each pine forest management area are obtained, and then the pine wilt disease index of each pine forest management area is obtained. Based on the comparison results between the pine wilt disease index and the standard index of pine wilt disease, it is determined whether to mark the pine forest management area as a pine wilt disease identification area. The pine wilt disease control and analysis module is used to construct a simulated management model of pine forests in the pine wilt disease identification area. The simulated management model of pine forests is used to simulate management and control, thereby obtaining the pine wilt disease control index of the pine wilt disease identification area. The regional control and sorting module is used to obtain the control emergency value of each pine wilt disease identification area, sort all pine wilt disease identification areas in descending order of control emergency value, and control the pine wilt disease identification areas according to the sorting order.

[0007] Furthermore, the method for obtaining the pine wilt disease index in the pine forest control area is as follows: Identify the prominent disease-affecting features and the features unaffected by disease impact in the pine forest control area. Mark the total number of prominent disease-affecting features as Lgst and the total number of unaffected features as Kdtp. Pair all prominent disease-affecting features into disease-affecting groups. Summate the pine wilt disease identification feature values ​​of the two prominent disease-affecting features in each disease-affecting group to obtain the disease-affecting group's additional disease impact value. Set an additional disease impact limit. When the additional disease impact value of a disease-affecting group is greater than or equal to the additional disease impact limit, the disease-affecting group is marked as a disease-affecting additional group. The total number of disease-affecting additional groups is marked as Zdes. The formula is then used... The pine wilt disease index (Dise) was obtained for the pine forest control area, where e1 is the prominent factor of disease impact, e2 is the irrelevant factor of disease impact, and e3 is the additional factor of disease impact.

[0008] Furthermore, the study identifies prominent disease-affecting features and irrelevant disease-affecting features within the pine forest management area. Specifically, aerial images of the pine forest management area are used to extract various pine wilt disease identification features. Real feature data for each pine wilt disease identification feature is extracted, and disease feature analysis models for each feature are obtained. The real feature data for each pine wilt disease identification feature are input into the corresponding disease feature analysis models, and pine wilt disease identification feature values ​​are output. A threshold for pine wilt disease identification features is set. When the pine wilt disease identification feature value is greater than or equal to the threshold, the feature is marked as a prominent disease-affecting feature; when the value is less than the threshold, the feature is marked as an irrelevant disease-affecting feature.

[0009] Furthermore, the method for obtaining the pine wilt disease control index Zaw in the identified pine wilt disease area is as follows: A simulation interval of T is set. During the simulation control process, the pine wilt disease index of the pine forest simulation control model is obtained after each simulation interval T, until the pine forest simulation control model completes the simulation control. The total number of pine wilt disease indices is marked as Nukp, and the disease duration Bzdg is obtained. The formula is then used... The pine wilt disease control index Zaw was obtained for the identified areas of pine wilt disease, where ma is the disease control coefficient and mb is the disease persistence coefficient.

[0010] Furthermore, the method for obtaining the duration of disease Bzdg is as follows: All pine wilt disease indices are sorted sequentially according to the acquisition time. The sum of two adjacent pine wilt disease indices after sorting is obtained to obtain the duration value of pine wilt disease. A pine wilt disease duration threshold is set. When the duration value of pine wilt disease is greater than or equal to the pine wilt disease duration threshold, the duration of disease is increased by one, and the duration of disease is marked as Bzdg.

[0011] Furthermore, the emergency control value for pine wilt disease identification areas is obtained as follows: The pine wilt disease index (Dise) and the pine wilt disease control index (Zaw) for a pine wilt disease identification area are obtained, and the potential impact quantity (Rek) is simultaneously obtained. The value is then calculated using the formula... The emergency control value EMbt for the pine wilt disease identification area was obtained.

[0012] Furthermore, the potential impact number Rek is obtained as follows: the remaining pine wilt disease identification areas are marked as potential impact identification areas, the distance between the pine wilt disease identification areas and each potential impact identification area is measured, the regional distance between the pine wilt disease identification areas and each potential impact identification area is obtained, a regional standard distance is set, and when the regional distance is less than the regional standard distance, the potential impact number is increased by one, and the potential impact number is marked as Rek.

[0013] Furthermore, the AI-based intelligent identification and control method for pine wilt disease includes the following steps: Step 1: Divide the target pine forest area into multiple pine forest management zones; Step 2: After each pine forest management cycle, aerial images of the pine forest areas in each management zone are obtained, and then the pine wilt disease index of each management zone is obtained. Step 3: Based on the comparison results between the pine wilt disease index and the pine wilt disease standard index, determine whether to mark the pine forest control area as a pine wilt disease identification area; Step 4: Construct a simulated management model of pine forests in the identified pine wilt disease area. The simulated management model of pine forests is used to simulate management and control, thereby obtaining the pine wilt disease control index in the identified pine wilt disease area. Step 5: Obtain the control emergency value for each pine wilt disease identification area, and sort all pine wilt disease identification areas in descending order of control emergency value; Step 6: Control the identified areas of pine wilt disease according to the sorting order.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The method of the present invention ensures reasonable control of pine wilt disease in pine forest areas by quantitatively analyzing the current disease status, subsequent disease control status, and disease impact in the identified pine wilt disease area; 2. Set up a pine forest area division and control module and a pine wilt disease identification module to implement reasonable regional control of pine forest areas. Through in-depth analysis of multi-dimensional disease characteristics, accurately identify pine wilt disease in pine forest areas. Set up a pine wilt disease control analysis module and a regional control ranking module. By constructing a pine forest simulation control model of the identified pine wilt disease areas, accurately analyze the actual situation of the identified pine wilt disease areas in the subsequent control and treatment process, and then prioritize the control of pine wilt disease identified areas with high control needs. Attached Figure Description

[0015] Figure 1 The flowchart shows a method for intelligent identification and control of pine wilt disease based on artificial intelligence. Figure 2 This is a system module diagram of an AI-based intelligent identification and control system for pine wilt disease. Figure 3 A flowchart for marking prominent features and unrelated features of disease. Detailed Implementation

[0016] Example 1: Refer to Figure 1 The AI-based intelligent identification and control method for pine wilt disease includes the following steps: Step 1: Divide the target pine forest area into multiple pine forest management zones; Step 2: After each pine forest management cycle, aerial images of the pine forest areas in each management zone are obtained, and then the pine wilt disease index of each management zone is obtained. Step 3: Based on the comparison results between the pine wilt disease index and the pine wilt disease standard index, determine whether to mark the pine forest control area as a pine wilt disease identification area; Step 4: Construct a simulated management model of pine forests in the identified pine wilt disease area. The simulated management model of pine forests is used to simulate management and control, thereby obtaining the pine wilt disease control index in the identified pine wilt disease area. Step 5: Obtain the control emergency value for each pine wilt disease identification area, and sort all pine wilt disease identification areas in descending order of control emergency value; Step 6: Control the identified areas of pine wilt disease according to the sorting order.

[0017] The above methods quantify and analyze the current disease status, subsequent disease control, and disease impact in the identified areas of pine wilt disease, ensuring reasonable control of pine wilt disease in pine forest areas.

[0018] Example 2: Refer to Figures 2 to 3 The AI-based intelligent identification and control system for pine wilt disease includes a pine forest area division and control module, a pine wilt disease identification module, a pine wilt disease control and analysis module, and an area control ranking module.

[0019] Pine Forest Area Division and Control Module: The target pine forest area is divided into regions (the regions are divided according to the distribution of pine forests and the characteristics of topography and landforms; the specific division method is not the focus of this application and will not be elaborated here), resulting in multiple pine forest control areas.

[0020] Pine wilt disease identification module: Set a pine forest management cycle. After each pine forest management cycle, acquire aerial images of the pine forest areas in each management area (these images can be obtained using UAV remote sensing monitoring technology). Then, acquire the pine wilt disease index of each management area and set a standard index for pine wilt disease (the standard index for pine wilt disease is a system preset value). When the pine wilt disease index of a management area is greater than or equal to the standard index, the management area is marked as a pine wilt disease identification area. When the pine wilt disease index of a management area is less than the standard index, no action is taken.

[0021] The method for obtaining the pine wilt disease index in the pine forest control area is as follows: Various pine wilt disease identification features are extracted from aerial images of the pine forest control area (the types of pine wilt disease identification features include resin secretion features, needle color features, vector insect trace features, etc.). Real feature data for each type of pine wilt disease identification feature are extracted, and disease feature analysis models for each type of pine wilt disease identification feature are obtained. The real feature data for each type of pine wilt disease identification feature are then input into the corresponding disease feature analysis model, and the pine wilt disease identification index for each type of pine wilt disease identification feature is output. The eigenvalue is set by defining a threshold for identifying pine wilt disease characteristics (the threshold is a system preset value). When the value of a pine wilt disease identification feature is greater than or equal to the threshold, the pine wilt disease identification feature is marked as a prominent feature affecting the disease. When the value of a pine wilt disease identification feature is less than the threshold, the pine wilt disease identification feature is marked as an irrelevant feature affecting the disease. The total number of prominent features affecting the disease is marked as Lgst, and the total number of irrelevant features affecting the disease is marked as Kdtp. All prominent disease impact features are paired into disease impact groups. The pine wilt disease identification feature values ​​of the two prominent disease impact features within each group are summed to obtain the disease impact added value for the group. A disease impact added limit is set (the limit is a system preset value). When the disease impact added value of a disease impact group is greater than or equal to the limit, the group is marked as a disease impact added group. When the added value is less than the limit, no action is taken. The total number of disease impact added groups is marked as Zdes. The formula is then used... The pine wilt disease index (Dise) was obtained for the pine forest control area. Among them, e1 is the disease impact prominence coefficient, e2 is the disease impact irrelevant coefficient, and e3 is the disease impact additional coefficient. The value of e1 is 1.41, the value of e2 is 0.97, and the value of e3 is 1.25.

[0022] Different types of pine wilt disease identification features correspond to different disease feature analysis models. For example, resin secretion features and needle color features correspond to two different disease feature analysis models. These models are all constructed based on neural network models. The difference in the construction of different disease feature analysis models lies in the different training data. This embodiment will disclose the construction process of the disease feature analysis model for resin secretion features: Collect real feature data of resin secretion features (if it is a disease feature analysis model for needle color features, then collect real feature data of needle color features), construct a neural network model, use the real feature data of resin secretion features as training data for the neural network model, and assign pine wilt disease identification feature values ​​to each training data point. The range of the disease identification feature value is (2.1~5.9). The larger the pine wilt disease identification feature value, the more abnormal the resin secretion of pine trees in the pine forest control area is, and the smaller the pine wilt disease identification feature value, the more normal the resin secretion of pine trees in the pine forest control area is. (If it is a disease feature analysis model based on needle color characteristics, the larger the pine wilt disease identification feature value, the more abnormal the needle color of pine trees in the pine forest control area is, and the smaller the pine wilt disease identification feature value, the more normal the needle color of pine trees in the pine forest control area is.) The training data is divided into a 60% training set, a 20% validation set, and a 20% test set. The neural network is iteratively trained on the training set, validation set, and test set. After training is completed, a disease feature analysis model based on resin secretion characteristics is constructed.

[0023] The system includes a pine forest area division and control module and a pine wilt disease identification module. This allows for reasonable regional control of pine forest areas and accurate identification of pine wilt disease in pine forest areas through in-depth analysis of multi-dimensional disease characteristics.

[0024] Pine wilt disease control analysis module: Construct a simulated management model of pine forests in the identified pine wilt disease area, and use the simulated management model to obtain the pine wilt disease control index Zaw in the identified pine wilt disease area.

[0025] The method for obtaining the pine wilt disease control index Zaw in the identified pine wilt disease area is as follows: Set the simulation interval time as T (the length of T is set according to actual needs). During the simulation control process, after each simulation interval time T, obtain the pine wilt disease index of the pine forest simulation control model until the pine forest simulation control model completes the simulation control. Mark the total number of pine wilt disease indices as Nukp. Sort all pine wilt disease indices in chronological order of acquisition time. Summate two adjacent pine wilt disease indices after sorting to obtain the pine wilt disease persistence value. Set a pine wilt disease persistence threshold (the pine wilt disease persistence threshold is a system preset value). When the pine wilt disease persistence value is greater than or equal to the pine wilt disease persistence threshold, increase the disease persistence count by one. When the pine wilt disease persistence value is less than the pine wilt disease persistence threshold, no action is taken, and the disease persistence count is marked as Bzdg. Then, use the formula... The pine wilt disease control index Zaw was obtained for the identified areas of pine wilt disease, where ma is the disease control coefficient and mb is the disease persistence coefficient, with ma taking a value of 0.43 and mb taking a value of 0.35.

[0026] A simulated management model for pine forests in areas identified by pine wilt disease is constructed. Specifically, this involves: acquiring real feature data of various pine wilt disease identification characteristics in the identified area; simultaneously setting expected feature data for these characteristics; acquiring historical environmental data of the identified area; selecting simulation software such as SpeedTree and Unreal Engine; creating a pine forest model in the simulation software based on the real feature data of various pine wilt disease identification characteristics; setting parameters such as growth status, leaf color, and branch morphology for each pine tree in the model; setting corresponding environmental parameters in the pine forest model based on the historical environmental data; and determining the management direction of the pine forest model based on the expected feature data of various pine wilt disease identification characteristics. This process leads to the construction of a simulated management model for pine forests in the identified area, which will then implement simulated management based on the management direction.

[0027] Regional control and sorting module: Obtain the control emergency value of each pine wilt disease identification area, sort all pine wilt disease identification areas in descending order of control emergency value, and control the pine wilt disease identification areas in the sorting order (prioritize the control of the pine wilt disease identification areas that are ranked higher, and refer to the simulation control method of the pine forest simulation control model for specific control methods).

[0028] The emergency control value for pine wilt disease identification areas is obtained as follows: Obtain the pine wilt disease index (Dise) and the pine wilt disease control index (Zaw) for a single pine wilt disease identification area. Mark the remaining pine wilt disease identification areas (excluding this one) as potential impact identification areas. Measure the distance between each potential impact identification area and the pine wilt disease identification area (this can be done using GIS measurement methods; import the boundary data between the pine wilt disease identification area and the potential impact identification area into the software using geographic information system software, and calculate the shortest distance between them using the software's spatial analysis tools). Obtain the regional distance between the pine wilt disease identification area and each potential impact identification area. Set a regional standard distance (the regional standard distance is a system preset distance). When the regional distance is greater than or equal to the regional standard distance, no action is taken. When the regional distance is less than the regional standard distance, increase the number of potential impacts by one and mark the number of potential impacts as Rek. Use the formula... The emergency control value EMbt for the pine wilt disease identification area was obtained.

[0029] The system includes a pine wilt disease control analysis module and a regional control ranking module. By constructing a simulated control model of pine forests in pine wilt disease identification areas, it accurately analyzes the actual situation of pine wilt disease identification areas in the subsequent control and treatment process. It quantitatively analyzes the current disease status, subsequent disease control status, and disease impact of pine wilt disease identification areas, and then prioritizes the control of pine wilt disease identification areas with high control needs, ensuring reasonable control of pine wilt disease in pine forest areas.

[0030] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0031] 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, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0032] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0033] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0034] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0035] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0036] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0037] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An intelligent identification and control system for pine wilt disease based on artificial intelligence, characterized in that, It includes modules for pine forest area division and management, pine wilt disease identification, pine wilt disease control and analysis, and area management ranking. The pine forest area division and control module is used to divide the target pine forest area into multiple pine forest control areas. The pine wilt disease identification module is used to set pine forest management cycles. After each pine forest management cycle, aerial images of the pine forest area in each pine forest management area are obtained, and then the pine wilt disease index of each pine forest management area is obtained. Based on the comparison results between the pine wilt disease index and the standard index of pine wilt disease, it is determined whether to mark the pine forest management area as a pine wilt disease identification area. The method for obtaining the pine wilt disease index in pine forest control areas is as follows: Identify the prominent disease-affecting features and irrelevant features in the pine forest control area. Mark the total number of prominent disease-affecting features as Lgst and the total number of irrelevant features as Kdtp. Pair all prominent disease-affecting features into disease-affecting groups. Summate the pine wilt disease identification feature values ​​of the two prominent disease-affecting features in each disease-affecting group to obtain the disease-affecting group's additional value. Set an additional limit for the disease-affecting group. When the additional value of the disease-affecting group is greater than or equal to the additional limit, the disease-affecting group is marked as a disease-affecting additional group. The total number of disease-affecting additional groups is marked as Zdes. The formula is then used... The pine wilt disease index Dise was obtained in the pine forest control area, where e1 is the disease impact prominence coefficient, e2 is the disease impact irrelevant coefficient, and e3 is the disease impact additional coefficient. The pine wilt disease control and analysis module is used to construct a simulated management model of pine forests in the pine wilt disease identification area. The simulated management model of pine forests is used to simulate management and control, thereby obtaining the pine wilt disease control index of the pine wilt disease identification area. The regional control and sorting module is used to obtain the control emergency value of each pine wilt disease identification area, sort all pine wilt disease identification areas in descending order of the control emergency value, and control the pine wilt disease identification areas according to the sorting order. The emergency control values ​​for pine wilt disease identification areas are obtained as follows: The pine wilt disease index (Dise) and the pine wilt disease control index (Zaw) for an identification area are obtained, along with the potential impact quantity (Rek). The values ​​are then calculated using the formula... The emergency control value EMbt for the identified pine wilt disease area was obtained. The method for obtaining the pine wilt disease control index Zaw in the identified pine wilt disease area is as follows: A simulation interval of T is set. During the simulation control process, the pine wilt disease index of the pine forest simulation control model is obtained after each simulation interval T, until the pine forest simulation control model completes the simulation control. The total number of pine wilt disease indices is marked as Nukp, and the disease duration Bzdg is obtained. The formula is then used... The pine wilt disease control index Zaw was obtained for the identified pine wilt disease area, where ma is the disease control coefficient and mb is the disease persistence coefficient. The method for obtaining the duration of pine wilt disease (Bzdg) is as follows: Sort all pine wilt disease indices in chronological order of acquisition time, sum the two adjacent pine wilt disease indices after sorting to obtain the duration value of pine wilt disease, set a pine wilt disease duration threshold, and when the duration value of pine wilt disease is greater than or equal to the pine wilt disease duration threshold, increase the duration of disease by one and mark the duration of disease as Bzdg; The potential impact number Rek is obtained as follows: mark the remaining pine wilt disease identification areas as potential impact identification areas, measure the distance between the pine wilt disease identification areas and each potential impact identification area, obtain the regional distance between the pine wilt disease identification areas and each potential impact identification area, set the regional standard distance, and when the regional distance is less than the regional standard distance, increase the potential impact number by one, and mark the potential impact number as Rek.

2. The intelligent identification and control system for pine wilt disease based on artificial intelligence according to claim 1, characterized in that, To determine the prominent and irrelevant features of pine wilt disease in the pine forest management area, the following steps are taken: Aerial images of the pine forest management area are used to extract various pine wilt disease identification features. Real feature data for each pine wilt disease identification feature is extracted, and disease feature analysis models for each feature are obtained. The real feature data for each pine wilt disease identification feature are input into the corresponding disease feature analysis models, and pine wilt disease identification feature values ​​are output. A threshold for pine wilt disease identification features is set. When the pine wilt disease identification feature value is greater than or equal to the threshold, the pine wilt disease identification feature is marked as a prominent disease impact feature; when the pine wilt disease identification feature value is less than the threshold, the pine wilt disease identification feature is marked as an irrelevant disease impact feature.

3. An AI-based intelligent identification and control method for pine wilt disease, applied to the AI-based intelligent identification and control system for pine wilt disease as described in any one of claims 1-2, characterized in that, Includes the following steps: Step 1: Divide the target pine forest area into multiple pine forest management zones; Step 2: After each pine forest management cycle, aerial images of the pine forest areas in each management zone are obtained, and then the pine wilt disease index of each management zone is obtained. Step 3: Based on the comparison results between the pine wilt disease index and the pine wilt disease standard index, determine whether to mark the pine forest control area as a pine wilt disease identification area; Step 4: Construct a simulated management model of pine forests in the identified pine wilt disease area. The simulated management model of pine forests is used to simulate management and control, thereby obtaining the pine wilt disease control index in the identified pine wilt disease area. Step 5: Obtain the control emergency value for each pine wilt disease identification area, and sort all pine wilt disease identification areas in descending order of control emergency value; Step 6: Control the identified areas of pine wilt disease according to the sorting order.

Images