Powdery Mildew Caused by Erysiphe cruciferarum on Wild Rocket (Diplotaxis tenuifolia): Hyperspectral Imaging and Machine Learning Modeling for Non-Destructive Disease Detection

Wild rocket is a widely cultivated salad crop. Typical signs and symptoms of powdery mildew were observed on leaves Diplotaxis tenuifolia, likely favored by climatic conditions occurring in greenhouse. Based morphological features molecular analysis, the disease agent was identified as fungal pathogen Erysiphe cruciferarum. To best our knowledge, this first report E. cruciferarum D. tenuifolia. Moreover, present study provides non-destructive high performing digital approach to efficiently detect disease. Hyperspectral image analysis allowed characterize spectral response wild affected adopted machine-learning (a trained Random Forest model with four most contributory wavelengths falling range 403–446 nm) proved be able accurately discriminate between healthy diseased leaves. Shifts irradiance absorption chlorophyll spectrum blue seems at base hyperspectral imaging detection mildew.