In Ethiopia, potato is an important food-security crop, yet foliar diseases such as early blight and late blight threaten yields. This study describes a lightweight convolutional neural network (CNN) for classifying these diseases from potato leaf images.

The model is designed to be lightweight, which may help it run on modest hardware commonly found in agricultural regions. The research focuses specifically on the two major diseases, early blight and late blight, providing a targeted approach to a pressing problem.