Pine wilt disease (PWD) is the most dangerous biohazard of pine species and poses a serious threat to forest resources. Coupling satellite remote sensing technology and deep learning technology for the accurate monitoring of PWD is an important tool for the efficient prevention and control of PWD. We used Gaofen-2 remote sensing images to construct a dataset of discolored standing tree samples of PWD and selected three semantic segmentation models—DeepLabv3+, HRNet, and DANet—for training and to compare their performance. To build a GAN-based semi-supervised semantic segmentation model for semi-supervised learning training, the best model was chosen as the generator of generative adversarial networks (GANs). The model was then optimized for structural adjustment and hyperparameter adjustment. Aimed at the characteristics of Gaofen-2 images and discolored standing trees with PWD, this paper adopts three strategies—swelling prediction, raster vectorization, and forest floor mask extraction—to optimize the image identification process and results and conducts an application demonstration study in Nanping city, Fujian Province. The results show that among the three semantic segmentation models, HRNet was the optimal conventional semantic segmentation model for identifying discolored standing trees of PWD based on Gaofen-2 images and that its MIoU value was 68.36%. Additionally, the GAN-based semi-supervised semantic segmentation model GAN_HRNet_Semi improved the MIoU value by 3.10%, and its recognition segmentation accuracy was better than the traditional semantic segmentation model. The recall rate of PWD discolored standing tree monitoring in the demonstration area reached 80.09%. The combination of semi-supervised semantic segmentation technology and high-resolution satellite remote sensing technology provides new technical methods for the accurate wide-scale monitoring, prevention, and control of PWD.

Climatic factors have a strong influence on the occurrence of forest diseases and pests, but few studies have systematically analyzed the influence of spring climatic factors on the occurrence of forest diseases and pests in China. We collected inventory data of forest resources, forest diseases, and pest occurrences and then analyzed the spatial and temporal characteristics of China’s forest diseases and pests from 1992–2019. Next, we took spring temperature accumulations ≥ 10 °C, spring average precipitation, and spring average radiation as the spring climatic factors and analyzed their influence on China’s forest diseases and pests with partial correlation and piecewise trend methods. The results showed that the incidence rate of forest diseases and pests in China had a nonlinear decreasing trend that occurred simultaneously with the growth of forested areas and the increase in forest pest and disease areas. Ultimately, the increase in forest pest and disease areas stabilized at low levels of 1% and 4%, respectively. This change generated a spatial shift from an east–west to a north–south pattern in China. Additionally, the average turning points of forest disease and pest incidence trends in China occurred in 2000 and 2005, where 56.7% and 63.3% of provinces, respectively, experienced significant shifts in forest disease and pest incidence. Finally, spring meteorological elements had a significant role in driving the mechanisms of forest disease and pest incidence in China. Among these, spring temperature accumulation was a major contributor in disease and pest variability in China. However, spring radiation and spring precipitation were important local drivers in Southwest China, though these two factors had two opposing shifts in forest diseases and pests reflected over time. This study systematically analyzed the impact of climate change on the development of forest diseases and pests in China, helping clarify the future control of forest diseases and pests in China.

Pine wilt disease has caused severe damage to China’s forest ecosystems. Utilizing the rich information from very-high-resolution (VHR) satellite imagery for large-scale and accurate monitoring of pine wilt disease is a crucial approach to curbing its spread. However, current research on identifying infected trees using VHR satellite imagery and deep learning remains extremely limited. This study introduces several advanced self-attention algorithms into the task of satellite-based monitoring of pine wilt disease to enhance detection performance. We constructed a dataset of discolored pine trees affected by pine wilt disease using imagery from the Gaofen-2 and Gaofen-7 satellites. Within the unified semantic segmentation framework MMSegmentation, we implemented four single-head attention models—NLNet, CCNet, DANet, and GCNet—and two multi-head attention models—Swin Transformer and SegFormer—for the accurate semantic segmentation of infected trees. The model predictions were further analyzed through visualization. The results demonstrate that introducing appropriate self-attention algorithms significantly improves detection accuracy for pine wilt disease. Among the single-head attention models, DANet achieved the highest accuracy, reaching 73.35%. The multi-head attention models exhibited an excellent performance, with SegFormer-b2 achieving an accuracy of 76.39%, learning the features of discolored pine trees at the earliest stage and converging faster. The visualization of model inference results indicates that DANet, which integrates convolutional neural networks (CNNs) with self-attention mechanisms, achieved the highest overall accuracy at 94.43%. The use of self-attention algorithms enables models to extract more precise morphological features of discolored pine trees, enhancing user accuracy while potentially reducing production accuracy.

Plants, as producers in ecosystems, are an integral part of biodiversity in terms of their species diversity. Plant diversity not only enhances the quality of ecosystem services, but also provides habitat for a wide range of plants and animals. The invasion of pine wilt disease (PWD) has posed a significant threat to plant diversity in China, but it is not clear whether this threat would be significantly different in natural and planted forests. In this study, we collected a long time series of refined forest subcompartment data on PWD occurrence and plant diversity sample survey data to analyze the loss and recovery time of plant diversity in China caused by PWD invasion, especially the degree of impact on plant diversity in natural and planted forests. The results showed that after PWD invasion, the plant diversity levels of China’s national, natural, and planted forests reached a minimum in the third year of invasion, with a loss of 9.1%, 6.46%, and 9.82%, respectively, relative to the pre-invasion levels. Starting from the third year of invasion, the plant diversity levels of the three recovered gradually at different rates, among which there was a significant difference in the speed of recovery between natural forests and planted forests, which took two and three years to recover to the original level of plant diversity, respectively. This study revealed the differences in the response of plant diversity to PWD invasion between natural and planted forests and provided a theoretical basis for local governments and managers in preventing and controlling PWD and protecting plant diversity.