A method for predicting the spread of pine wood nematode disease

By establishing a PGNN physically guided neural network hybrid model based on infectious disease dynamics model, combined with historical occurrence data and impact factor data of pine nematode disease, the problem of low accuracy of existing prediction methods is solved, and the high accuracy of spatio-temporal pattern distribution prediction of pine nematode disease is achieved, supporting the stability of forest ecosystems and the timely adoption of prevention and control measures.

CN118246596BActive Publication Date: 2025-03-28NORTHEAST FORESTRY UNIV +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202410334837.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-22
Publication Date
2025-03-28
Estimated Expiration
2044-03-22

AI Technical Summary

Technical Problem

The existing prediction methods for pine nematode disease have low accuracy, lacking methods that combine physical dynamics models and data-driven models, and cannot take into account the interpretability of the model and the accuracy of the data model.

Method used

Using a hybrid-driven continuous high-accuracy prediction method, a PGNN physically guided neural network hybrid model based on infectious disease dynamics model is established to predict the spatiotemporal pattern distribution of pine nematode disease by collecting and analyzing the historical occurrence data and influencing factor data of pine nematode disease.

Benefits of technology

It has achieved high accuracy prediction of pine nematode disease, provided dynamic changes in the distribution of time and space pattern, helped to take timely prevention and control measures, and ensure the stability of forest ecosystems and social development.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention proposes a method for predicting the spread of pine wood nematode disease, which belongs to the technical field of forest protection. The method comprises the following steps: S1. Collecting historical occurrence data of pine wood nematode disease and storing it as raster data, and then converting the raster data into vector data; S2. Obtaining historical occurrence data of influencing factors of pine wood nematode disease and analyzing the correlation of influencing factors; S3 constructing an infectious disease dynamics model based on pine wood nematode disease; S4. Constructing a PGNN physical-guided neural network hybrid model; S5. Inputting historical occurrence data of pine wood nematode disease and data of influencing factors with strong correlation into the PGNN physical-guided neural network hybrid model, and outputting the spread of pine wood nematode disease. S6. Optimizing the parameters of the PGNN physical-guided neural network model based on a genetic optimization algorithm, and returning to S5; solving the technical problem of the lack of efficient and accurate prediction methods in the prior art.
Need to check novelty before this filing date? Find Prior Art