Geospatial Analysis of Sustainable Forestry: Using GIS and Improved Particle Swarm Optimization (PSO) Algorithms to Detect and Predict Pine Wilt Disease

This study seamlessly integrates Geographic Information System (GIS) with an enhanced Particle Swarm Optimization (PSO) algorithm to conduct a detailed geospatial analysis of pine wood nematode disease, a severe forest affliction. Our research team curated a comprehensive disease database and utilized GIS technology to delve into the spatial distribution characteristics of the disease. By merging this data with the PSO algorithm, we developed a disease recognition model capable of precise detection and analysis of the disease. Experimental outcomes highlight that the fusion of GIS and Memetic Computing (MC) methods provides a more accurate reflection of the spatiotemporal distribution of the disease. Notably, the recognition model forged with the PSO algorithm achieved an exceptional accuracy rate of 98.41%, outperforming other methodologies. This research not only deepens the understanding of the spatiotemporal patterns of pine wood nematode disease but also offers a scientific foundation for the formulation of more effective prevention and control strategies, significantly contributing to the monitoring and management of forest diseases.