Spectral detection of basal stem rot in oil palm plantations using UAV hyperspectral imagery, deep learning segmentation, and machine learning classification: a case study at the sembawa plantation

Detection of Basal Stem Rot (BSR) caused by Ganoderma boninense remains difficult in oil palm disease management because spectral and physiological changes in the canopy accompany infection well before palms enter terminal decline. This study developed a pipeline combining UAV‐borne hyperspectral imagery at 5 cm spatial resolution, deep learning-based instance segmentation, machine learning classification, and spatial analysis to discriminate symptomatic BSR‐affected palms from healthy ones at the individual-tree scale, map disease distribution, and explore associations with environmental variables. Ground truth was established through field observation conducted with plantation biologist researchers: infected trees were identified by physical canopy symptoms including chlorosis, necrosis, reduced crown density, and premature frond collapse, assessed using a composite three-indicator scoring protocol. A Mask R‐CNN model delineated individual tree canopies with 89.0% Average Precision (AP50). A Support Vector Machine classifier applied to the full 95-band hyperspectral dataset achieved 86.50% overall accuracy (kappa = 0.82) in pixel‐level classification. Tree‐level validation against field‐assessed labels yielded 84.3% accuracy and kappa = 0.71. Spatial analysis identified five statistically significant local hotspots of infection (Getis‐Ord Gi*), whereas global clustering was non-significant (Z = 1.27, p = 0.204). Associations between BSR incidence and eight environmental variables were weak and non‐significant in this exploratory analysis, with soil pH showing the highest positive association (r = 0.142) and soil nitrogen the strongest negative association (r = −0.151). The approach produces spatially explicit discrimination of symptomatic BSR‐affected trees from healthy ones, with scope conditions defined for future extension.