Sustainable Agriculture with Advanced Plant Disease Detection using YOLOv11 and XAI

India has agriculture high on its list, but as plant diseases do not get noticed early enough, agricultural waste increases. This study proposes using XAI and leading computer vision algorithms to spot plant diseases in the right fashion. The work employs a YOLOv11 model especially trained using a Roboflow dataset that has used images from both PlantVillage and PlantDoc for the purpose of an agricultural context. Anchor-free detection as well as instance segmentation are catered to by its architecture. With the assistance of YOLOv11, it is applied to accurately classify 20 distinct disease types on several crops. For this application, each XAI-enhanced disease condition is described in simple terms, encompassing symptoms, possible causes, and treatments, especially for farmers with non-technical backgrounds. Since the mean Average Precision (mAP) for detecting diseases reaches as high as 97.5%, it proves that the studies showed robustness in the YOLOv11 model. This has further demonstrated the exceptional combination of high adaptability and high reliability, under a variety of environmental conditions, through graphical studies like Precision-Recall and Confidence Curve, with the model. It particularly indicates how this particular combination of YOLOv11 and XAI offers superb precision for scalable yet straightforward methods to address plant disease control.