Abstract
Grapevine yellows, a group of serious diseases affecting grapevines, have spread across grape-growing regions and represent a threat to vineyards, necessitating containment strategies. The identification of these diseases, particularly in the Chardonnay variety, remains a challenging and labor-intensive task. In this study, we present a comprehensive spectral dataset collected over five years from 700 grapevine leaves per year. The dataset includes leaves affected by yellows disease, healthy leaves as well as three additional classes consisting of leaves with visually similar symptoms, ensuring a diverse and representative sample. Spectral data were acquired under controlled laboratory conditions using a Labspec® 4i spectrometer, covering the spectral range from 350 nm to 2500 nm on grapevine leaves from areas of the experimental site of Comité Champagne. To facilitate further research, we performed basics analyses, including calculation of averaged spectra and principal component analysis, to explore spectral variations among different classes. This publicly available dataset serves as a valuable resource for researchers aiming to develop advanced techniques for robust detection and classification of yellows diseases.