Early detection of pine shoot beetle attack using vertical profile of plant traits through UAV-based hyperspectral, thermal, and lidar data fusion

• Published in: International journal of applied earth observation and geoinformation Vol. 125; p. 103549
• Main Authors: Lin, Qinan, Huang, Huaguo, Wang, Jingxu, Chen, Ling, Du, Huaqiang, Zhou, Guomo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2023; Elsevier
• Subjects: algorithms; anthocyanins; carotenoids; China; chlorophyll; Coleoptera; data collection; Data fusion; Early detection; fluorescence; forests; insects; lidar; photochemistry; Pine shoot beetle; Pinus yunnanensis; Plant traits; radiative transfer; reflectance; spatial data; temperature; thermography; tree damage; trees; unmanned aerial vehicles; Vegetation indices; China; Data fusion; Pine shoot beetle; Plant traits; Vegetation indices; Early detection
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2023.103549

•A voxelization method was developed to fuse UAV-based multisensor data.•Quantifying 3D spatial distribution of PTs and VIs using fused UAV-based multisensor data.•Vertical profile of PTs and VIs has significant difference between different severity levels of trees.•Improved performance of tree severity mapping using vertical cluster predictors.•Chlorophylls, PRIs and STs were most important for early detection of PSB attack. Pine shoot beetle (PSB) is one of the most damaging forest insects of Yunnan pine plantations in southwest China. However, the subtle symptoms of heterogeneous tree crowns make it difficult to accurately detect at early stage of PSB attack. Here, we evaluated the potential of a combination of plant traits (PTs) and vegetation indices (VIs) to distinguish different levels of tree damage by integrating hyperspectral, thermal imagery, and light detection and ranging (lidar) data based on unmanned airborne vehicle (UAV) systems. A voxelization method was used to fuse hyperspectral reflectance, temperature, and lidar point cloud data. Subsequently, PTs such as pigments (i.e., chlorophyll, carotenoid, and anthocyanin contents) were retrieved from a radiative transfer model inversion, and structural, fluorescence, and thermal traits, as well as VIs, were derived from the fusion data. We developed a novel analytical approach using random forest (RF) algorithm with predictors from different spatial distributions (i.e., horizontal directions, vertical layers, and vertical clusters) to compare the performance of tree severity classification. The results showed that the difference of both PTs and VIs in vertical layers between different severity levels are more than that in horizontal directions. The performance of RF model with predictors of the vertical layers (OA = 74 %, kappa = 0.65) was better than that using the predictive variables in horizontal directions (OA = 69 % and kappa = 0.60) of tree crowns. Using the vertical clustering features RF model increased the accuracy (OA = 78 % and kappa = 0.70), especially for slightly and moderately damaged trees, with improvements of 10 % and 12 %, respectively. Among all variables analyzed, chlorophylls were the most important predictor, followed by photochemical reflectance index and structural traits. Our work demonstrates the effectiveness of using fused UAV-based multi-sensor data for early detection of PSB attack, and can be applied other potential forest diseases and insect monitoring.