Analysis of Flavescence dorèe leaf symptoms using hyperspectral imaging and machine learning

This work presents a novel approach for the detection and classification of Flavescence dorèe disease based on hyperspectral imaging. Three machine learning model are trained to classify leaf samples of Pinot Noir into healthy, asymptomatic, and diseased classes according to a combination of vegetation indexes calculated on the per-pixel spectrum of the sample. The dataset used includes 201 hypercubes collected from the same field in 2023 and 2024, equally divided into the three classes. Results highlight good performances (92% accuracy) for the model trained on the population of features extracted from the vegetation indexes for each leaf and normalized using z-score.