Abstract
The use of Convolutional Neural Network (CNN) methods to diagnose diseases in maize plants based on leaf images is analyzed in this study. The dataset used consisted of 4188 images divided into two disease categories: leaf blight and rust. The CNN model developed showed an accuracy of 93% on training data and 87.5% on validation data. Testing on 50 new image data showed that the model could classify diseases with a high degree of accuracy. The results of this study indicate that the CNN method can be used as an efficient and accurate tool to help farmers identify diseases in maize plants early, which can improve the production and quality of maize yields in Indonesia.