Prediction method of greenhouse tomato disease and insect pest diffusion distribution diagram

Abstract

The invention belongs to the technical field of crop disease and pest control, and discloses a greenhouse tomato disease and pest diffusion distribution diagram prediction method, which comprises the following steps: S1, collecting current growth data of tomatoes in a greenhouse in real time; s2, according to the current growth data, constructing a diffusion velocity model of diseases and insect pests, and predicting a disease radius # imgabs1 # after the time # imgabs0 # of the diseases and insect pests through the diffusion velocity model; and S3, predicting according to the current growth data acquired in the step S1 and the disease radius # imgabs2 # predicted in the step S2 to obtain a disease and pest diffusion distribution diagram. The current pest and disease damage data of the tomatoes in the greenhouse are collected in real time, environmental factors (temperature, humidity and carbon dioxide concentration) and interaction among different pest and disease damage are comprehensively considered, then the pest and disease damage diffusion distribution diagram is predicted and generated, and the generated result is higher in credibility and more accurate. A user can treat diseased plants according to the diffusion distribution diagram and prevent and treat infected plants, so that accurate prevention and treatment of plant diseases and insect pests by the user are facilitated.

Description

Technical Field

[0001] The invention belongs to the technical field of crop pest control, and in particular relates to a method for predicting a diffusion distribution map of greenhouse tomato pests and diseases. Background Art

[0002] In modern agricultural production, crop pest and disease management is the core link to ensure food safety and improve yield and quality. As one of the most widely grown vegetables in the world, tomatoes are particularly susceptible to pests and diseases, which not only seriously affect the growth and development of tomatoes, reduce yield and quality, but also may cause economic losses to the entire industry chain.

[0003] With the rapid development of information technology and biotechnology, pest and disease monitoring technology is also constantly being optimized. At present, the use of drones, intelligent inspection robots, remote sensing technology, etc. to conduct real-time monitoring and health assessment of crops has become a hot topic in research and application. These technologies can monitor the health of crops on a large scale, with high efficiency and high precision, and promptly detect and diagnose pest and disease problems. However, how to accurately predict the spread trend of pests and diseases based on monitoring data, assess disease risks, and formulate effective management strategies remains a challenge. In addition, the planting environment (such as temperature, humidity, carbon dioxide concentration, etc.) and the interaction between different pests and diseases are also important factors in predicting the spread trend of pests and diseases. Summary of the invention

[0004] In view of this, in order to solve the problems raised in the above background technology, the purpose of the present invention is to provide a method for predicting the diffusion distribution map of greenhouse tomato pests and diseases.

[0005] To achieve the above object, the present invention provides the following technical solutions: A method for predicting a diffusion distribution map of greenhouse tomato pests and diseases, comprising: S1. Real-time collection of current growth data of tomatoes in the greenhouse; S2. Construct a diffusion rate model of pests and diseases based on the current growth data, and predict the time after which pests and diseases will pass through the diffusion rate model The disease radius ; S3. Based on the current growth data collected in step S1 and the disease radius predicted in step S2 Predict the spread and distribution map of pests and diseases; S4. Predict and calculate the elapsed time based on the pest diffusion distribution map Later infected tomato plants.

[0006] Preferably, in step S1, the current growth data includes current pest types, distribution data of various pests and diseases, and environmental parameters.

[0007] Preferably, in step S1, a current distribution map of pests and diseases is drawn according to the distribution data of various pests and diseases, and the current distribution center and current distribution intensity of various pests and diseases are determined based on the current distribution map of pests and diseases.

[0008] Preferably, in step S1, drawing the current distribution map of the pests and diseases includes: For diseases The mean-shift clustering method is used to cluster the distribution data of this type of pests and diseases to obtain the distribution of pests and diseases. high-density areas; Determine the centroid of the high-density area and the corresponding fitting radius , and about diseases The current distribution center is all the information about the disease The set of centroids of high-density regions; Obtain information about the disease in the high-density area The number of diseased plants is determined, and the disease intensity of the current high-density area is determined based on the number of diseased plants, and the disease intensity of the current high-density area is determined based on the number of diseased plants. The current distribution intensity is the total intensity of all diseases The collection of disease intensity in high-density areas.

[0009] Preferably, in step S1, the disease intensity expression of the high-density area is: ; In the formula, About the disease The intensity of the disease in high-density areas, Indicates the corresponding high-density area about the disease The number of diseased plants.

[0010] Preferably, in step S1, the environmental parameters include the ambient temperature , ambient humidity , ambient carbon dioxide concentration .

[0011] Preferably, in step S2, the expression of the diffusion velocity model is: ; In the formula, Indicates disease The diffusion capacity coefficient function is Indicates disease For diseases The influence coefficient function of the diffusion velocity, represents the parameter vector.

[0012] Preferably, in the diffusion rate model: ; ; In the formula, , , All represent coefficient constants; are the indices of temperature, humidity and carbon dioxide concentration respectively; Indicates disease For diseases The weight coefficient of the diffusion influence degree, positive value indicates promotion, negative value indicates inhibition; Represents a saturation constant. When the disease The strength reaches When the disease The influence of tends to a stable value; is a parameter Weight The mediation coefficient of the effect.

[0013] Preferably, in step S2, the disease radius The prediction expression is .

[0014] Compared with the prior art, the present invention has the following beneficial effects: The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases provided by the present invention collects the current pest and disease data of tomatoes in the greenhouse in real time, and comprehensively considers environmental factors (temperature, humidity and carbon dioxide concentration) and the interaction between different pests and diseases, and then predicts and generates a diffusion distribution map of pests and diseases. The generated result has higher credibility. Users can treat diseased plants and prevent and control diseased plants based on the diffusion distribution map, which is more conducive to users' precise prevention and control of pests and diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The flowchart of the method for predicting the diffusion distribution map of greenhouse tomato pests and diseases of the present invention is as follows; Figure 2 The current distribution map of pests and diseases generated in the present invention; Figure 3 This is the distribution map of the pests and diseases predicted in the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] like Figure 1 As shown, the method for predicting the diffusion distribution map of greenhouse tomato pests and diseases provided by the present invention specifically includes the following steps: S1. Real-time collection of current growth data of tomatoes in the greenhouse, wherein the current growth data includes current pest and disease types, distribution data of various pest and disease types, and environmental parameters; Specific: like Figure 2 In the example, assume that the length of a single row of plants is 1, the distance between two rows of plants is d1, the distance between two columns of plants is d2, and the number of tomato plants in each row is , the number of tomato plants in each row is ,When collecting data specifically, the inspection robot walks in the aisle between two plants to collect the current growth data of tomatoes in the greenhouse; The current growth data includes the current types of pests and diseases, distribution data of various pests and diseases, and environmental parameters; the distribution data of various pests and diseases specifically refers to the distribution location of diseased leaves; the environmental parameters mainly include the ambient temperature , ambient humidity , ambient carbon dioxide concentration .

[0018] For diseases The mean-shift clustering method is used to cluster the distribution data of this type of pests and diseases to obtain the distribution of pests and diseases. The high-density area is the concentrated area of ​​diseased leaves (the scattered diseased leaf points are regarded as the early stage of pests and diseases, and alarm processing is directly carried out for them); Based on the high-density areas obtained by clustering, the following Figure 2 Current distribution of pests and diseases shown. Figure 2 It is known that disease There are three high-density areas, and the centroids of the three high-density areas are determined as , , , the corresponding fitting radius is , , , and the set of three centroids Regarding disease Current distribution centers of; Get information about the disease in each high-density area. The number of diseased plants is determined, and the disease intensity of the current high-density area is determined based on the number of diseased plants; ; In the formula, About the disease The intensity of the disease in high-density areas, Indicates the corresponding high-density area about the disease The number of diseased plants. Figure 2 The disease intensities of the three high-density areas are , , , and the set of three disease intensities Regarding disease The current distribution strength.

[0019] S2. Construct a diffusion rate model of pests and diseases based on the current growth data, and predict the time after which pests and diseases will pass through the diffusion rate model The disease radius ; (21) Diffusion velocity model The expression of the diffusion velocity model is: .

[0020] The above, Indicates disease The diffusion capacity coefficient function is used to characterize the comprehensive impact of environmental factors on virus diffusion. The specific calculation formula is: In the formula, , , All represent coefficient constants; are indices of temperature, humidity and carbon dioxide concentration respectively.

[0021] The above, Indicates disease For diseases The influence coefficient function of the diffusion rate is used to characterize the mutual influence between different diseases. The specific calculation formula is: In the formula, , , All represent coefficient constants; are the indices of temperature, humidity and carbon dioxide concentration respectively; Indicates disease For diseases The weight coefficient of the diffusion influence degree, positive value indicates promotion, negative value indicates inhibition; Represents a saturation constant. When the disease The strength reaches When the disease The influence of tends to a stable value; is a parameter Weight mediation coefficient of the effect; represents the parameter vector.

[0022] (22) Disease radius Taking into account that the diffusion rate may vary with time and space, a differential equation is used to calculate the elapsed time Post-disease radius Size: ; Integrate the above equation to obtain the disease radius: The calculation formula .

[0023] From the above, corresponding to Figure 2 Shown about the disease The three high-density areas are: , , .

[0024] S3. Based on the current growth data collected in step S1 and the disease radius predicted in step S2 Predict the spread and distribution map of pests and diseases; In step S1, the disease The centroids of the three high-density areas are: , , ; In step S2, the disease The three high-density areas have passed through time Predicted disease radius ; Combined with the above centroid position and disease radius The data is plotted as Figure 3 The distribution map of pests and diseases shown.

[0025] S4. Predict and calculate the elapsed time based on the pest diffusion distribution map Later infected tomato plants.

[0026] When calculating the number of infected plants, the overlap of each high-density disease area and the actual distribution of plants should be considered. Figure 2 and Figure 3 The distribution of plants shown, with the centroid as Take the high-density area as an example: First calculate the number of rows and columns affected: Furthermore, the number of affected plants was calculated based on the number of affected rows and columns, and the number of plants that were not infected due to incomplete pest and disease areas was subtracted to obtain the number of infected plants. for: =The actual number of affected rows × the actual number of affected columns - the number of unaffected plants.

[0027] In summary, the present invention realizes high-precision data collection based on the inspection robot, thereby being able to accurately realize the real-time positioning and classification of pests and diseases, and also comprehensively considers the environmental factors in the greenhouse (temperature, humidity and carbon dioxide concentration) and the mutual influence between different pests and diseases, and then predicts and generates a pest and disease diffusion distribution map, and the generated result is more credible. Users can treat diseased plants and prevent and control diseased plants according to the diffusion distribution map, which is more conducive to users' accurate prevention and control of pests and diseases, which not only improves the treatment effect, but also reduces the amount of pesticides and reduces costs.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting the diffusion distribution map of greenhouse tomato pests and diseases, characterized in that: include: S1. Real-time collection of current growth data of tomatoes in the greenhouse; S2. Construct a diffusion rate model of pests and diseases based on the current growth data, and predict the time after which pests and diseases will pass through the diffusion rate model The disease radius ; S3. Based on the current growth data collected in step S1 and the disease radius predicted in step S2 The distribution map of pests and diseases spread can be predicted.

2. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 1, characterized in that: In the step S1, the current growth data includes current pest types, distribution data of various pests and diseases, and environmental parameters.

3. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 2, characterized in that: In the step S1, a current distribution map of pests and diseases is drawn according to the distribution data of various pests and diseases, and the current distribution center and current distribution intensity of various pests and diseases are determined based on the current distribution map of pests and diseases.

4. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 3, characterized in that: In step S1, drawing the current distribution map of the pests and diseases includes: For diseases The mean-shift clustering method is used to cluster the distribution data of this type of pests and diseases to obtain the distribution of pests and diseases. high-density areas; Determine the centroid of the high-density area and the corresponding fitting radius , and about diseases The current distribution center is all the information about the disease The set of centroids of high-density regions; Obtain information about the disease in the high-density area The number of diseased plants is determined, and the disease intensity of the current high-density area is determined based on the number of diseased plants, and the disease intensity of the current high-density area is determined based on the number of diseased plants. The current distribution intensity is the total intensity of all diseases The collection of disease intensity in high-density areas.

5. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 4, characterized in that: In step S1, the disease intensity expression of the high-density area is: ; In the formula, About the disease The intensity of the disease in high-density areas, Indicates the corresponding high-density area about the disease The number of diseased plants.

6. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 5, characterized in that: In step S1, the environmental parameters include the ambient temperature , ambient humidity , ambient carbon dioxide concentration .

7. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 6, characterized in that: In step S2, the expression of the diffusion velocity model is: ; In the formula, Indicates disease The diffusion capacity coefficient function is Indicates disease For diseases The influence coefficient function of the diffusion velocity, represents the parameter vector.

8. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 7, characterized in that: In the diffusion velocity model: ； ； In the formula, , , All represent coefficient constants; are the indices of temperature, humidity and carbon dioxide concentration respectively; Indicates disease For diseases The weight coefficient of the diffusion influence degree, positive value indicates promotion, negative value indicates inhibition; Represents a saturation constant. When the disease The strength reaches When the disease The influence of tends to a stable value; is a parameter Weight The mediation coefficient of the effect.

9. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 8, characterized in that: In step S2, the disease radius The prediction expression is .

10. The method for predicting the diffusion distribution map of greenhouse tomato pests and diseases according to claim 9, characterized in that: Also includes: S4. Predict and calculate the elapsed time based on the pest diffusion distribution map Later infected tomato plants.

Images