The transmission of diseases from sick plants to healthy plants is one of the biggest threats to the agriculture industry. Transmitted diseases have the potential to spread like wildfire throughout the entire farm if they are not detected in time. The user can scale up the detection of plant diseases in an economical way and spot afflicted plants in their very early stages, thanks to methods for detecting plant diseases. Furthermore, artificial intelligence plays an essential role in microbial research, which complements plant disease detection by identifying and analyzing microbial factors that contribute to the spread of infections. The most recent convolutional neural network (CNN) generation has produced impressive results in the area of image classification, according to a number of studies. In order to identify plant diseases, CNN will be the type of machine-learning model used in this study. Accuracy, precision, recall, and F1-score were used to compare the effectiveness of the models. LIME and SHAP, an approach based on explainable artificial intelligence (XAI), are used to explain the models’ predictions. The XAI reveals and sheds light on the model’s decision-making process by highlighting the areas of the input image that are most important to the model’s conclusion. The results showed that the CNN model performed better than the other models on all four-assessment metrics. This article offers clear and practical insights for agricultural applications.