As one of the most devastating disasters to pine forests, pine wilt disease (PWD) has caused tremendous ecological and economic losses in China. An effective way to prevent large-scale PWD outbreaks is to detect and remove the damaged pine trees at the early stage of PWD infection. However, early infected pine trees do not show obvious changes in morphology or color in the visible wavelength range, making early detection of PWD tricky. Unmanned aerial vehicle (UAV)-based hyperspectral imagery (HI) has great potential for early detection of PWD. However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data. In this paper, we applied the residual block to 3D-CNN and constructed a 3D-Res CNN model, the performance of which was then compared with that of 3D-CNN, 2D-CNN, and 2D-Res CNN in identifying PWD-infected pine trees from the hyperspectral images. The 3D-Res CNN model outperformed the other models, achieving an overall accuracy (OA) of 88.11% and an accuracy of 72.86% for detecting early infected pine trees (EIPs). Using only 20% of the training samples, the OA and EIP accuracy of 3D-Res CNN can still achieve 81.06% and 51.97%, which is superior to the state-of-the-art method in the early detection of PWD based on hyperspectral images. Collectively, 3D-Res CNN was more accurate and effective in early detection of PWD. In conclusion, 3D-Res CNN is proposed for early detection of PWD in this paper, making the prediction and control of PWD more accurate and effective. This model can also be applied to detect pine trees damaged by other diseases or insect pests in the forest.

Pine wilt disease (PWD) has caused huge economic and environmental losses since it invaded China. Although early monitoring is an effective way to control this hazard, the monitoring window for the early stage is hard to identify, and varies in different hosts and environments. We used UAV-based multispectral images of Pinus thunbergii forest in East China to identify the change in the number of infected trees in each month of the growing season. We built classification models to detect different PWD infection stages by testing three machine learning algorithms—random forest, support vector machine, and linear discriminant analysis—and identified the best monitoring period for each infection stage (namely, green attack, early, middle, and late). From the obtained results, the early monitoring window period was determined to be in late July, whereas the monitoring window for middle and late PWD stages ranged from mid-August to early September. We also identified four important vegetation indices to monitor each infection stage. In conclusion, this study demonstrated the effectiveness of using machine learning algorithms to analyze multitemporal multispectral data to establish a window for early monitoring of pine wilt disease infestation. The results could provide a reference for future research and guidance for the control of pine wilt disease.

Early detection of pine wilt disease (PWD) before visible crown discoloration is important for field inspection, confirmatory sampling, and timely management. However, because individual trees reach visible discoloration at different times, calendar-based analyses can blur the development of pre-visual spectral responses. Weekly UAV multispectral data from two Pinus massoniana forest sites were therefore aligned to the first visible crown discoloration of each tree. Crown-level band reflectance and vegetation indices (VIs) were examined from eight to one weeks before first visible discoloration, and healthy reference observations at each relative week were used to define 5th–95th percentile reference ranges for detection-rate (DR) analysis. Several VIs showed significant group-level differences from approximately seven weeks before first visible discoloration, whereas mean VI-based DR increased markedly to 0.52 at two weeks and 0.68 at one week before discoloration; single-band DRs were less stable. These results indicate a progressive pre-visual spectral response, with an exploratory early group-level indication emerging approximately seven weeks before discoloration and a stronger, more consistent spectral departure during the final two weeks. This onset-aligned framework provides a practical basis for scheduling repeated UAV surveillance and prioritizing field verification before obvious symptoms emerge.