Artificial Intelligence and Novel Sensing Technologies for Assessing Downy Mildew in Grapevine

Plant diseases and pests cause a large loss of world agricultural production. Downy mildew is major disease in grapevine. Conventional techniques for plant evaluations are time-consuming require expert personnel. This work investigates novel sensing technologies artificial intelligence applications assessing downy grapevine under laboratory conditions. In our methodology, machine vision applied to assess sporulation, while hyperspectral imaging used explore its potential capability towards early detection this disease. Image analysis RGB leaf disc images estimate (Plamopara viticola) severity (Vitis vinifera L. cv Tempranillo). A determination coefficient (R2) 0.76 ** root mean square error (RMSE) 20.53% observed the correlation between by computer expert’s visual assessment. Furthermore, an accuracy 81% achieved detect using images. These results indicate that non-invasive can be quantify sporulation leaves. The key evaluated conclusion, vision, learning could important