354 Indian J. Hortic. 82(3), September 2025: 354-358 INTRODUCTION Mango (Mangifera indica L.), a member of the Anacardiaceae family, is referred to as the “King of Fruits,” originated from Indian subcontinent, Andaman Islands and southern Asia. Due to its wider adaptability, the mango is successfully cultivated in tropical and subtropical climatic conditions worldwide (Ahmad et al., 1). India produces 26 MT of mango, the highest in the world, according to 2022, latest officially available FAOSTAT data (FAO, 4). Mango are prone to a number of pests and diseases that can considerably affect their development, total yield, and ultimately fruit quality. Mango cultivars vary based on the soil type, climate, and geographic location. India is home to around 1000 varieties of mangoes, out of the few hundred that are known to exist. Dinesh et al. (3) variety’s success in a given area does not always apply to another area as a consequence, different locations have different methods for combating pests and diseases. In order to prevent these diseases, mango cultivation faces various challenges. The common diseases of mango leaves are caused by bacteria and fungi. Farmers have relied on visual examinations and chemical treatments to identify and mitigate these diseases (Gupta and Tripathi, 5). Nevertheless, these approaches can be labor-intensive and liable to mistakes. With the advancement in AI and IoT based early disease detection, techniques like machine learning and digital image processing are being used more frequently (Xu et al., 17). This method is helpful in utilizing artificial intelligence and machine learning strategies to examine large datasets, reveal significant themes, and forecast future directions for research. In agriculture, early disease detection through incorporating AI and IoT technologies has made remarkable progress in the farming industry by offering significant insights that enable farmers to make well-informed decisions (Nargundkar et al., 8; Salimath et al., 13). Explainability in AI is critical for agricultural applications. Rayed et al. (10) developed MangoLeafXNet, for predictions of mango leaf diseases. Similarly, Rizvee et al. (11) also anticipated LeafNet, for prediction of seven mango leaf diseases. Prabu et al. (9) employed a pre-trained model, MobileNetV2, for the purpose of feature selection and reaches an accuracy rate of 94.5% in detecting Explainable AI for mango leaf disease detection: bridging the gap between model accuracy and farmers usability Mohammad Nasar 1 , Mohammad Abu Kausar 2 , Md. Abu Nayyer *3 , Vikash Kumar 3 and Md. Arshad Anwer 4 1 Computing & Informatics Department, Mazoon College, Muscat, P.O. Box 2805, Oman ABSTRACT Mango leaf diseases can seriously impact on the yield and vitality of mango trees, resulting in considerable financial losses. Prompt and precise identification of these diseases are essential for facilitating quick action and improving agricultural management practices. In the past few years, convolutional neural network (CNN) models have gained significant popularity towards image recognition and classification. Using CNN models, approaches for image-based disease diagnosis in the crops have become increasingly popular within the current scientific community. Mango leaves disease represents considerable threats to mango cultivation globally, making it essential to develop precise and efficient classification methods for timely disease control. Our research focuses on introducing an Explainable AI (XAI) framework that incorporates a modified VGG-16 CNN, alongside Gradient-weighted Class Activation Mapping (Grad-CAM), to recognize seven major mango leaf diseases using the publicly available MangoLeafBD dataset (3,500 images across seven classes). Our model demonstrated outstanding effectiveness in classification, achieving 92.8% accuracy, while as providing precise and graphical explanations to enhance use and foster farmer trust. Our results provide important insights for implementing CNN models that improve the accuracy and effectiveness of monitoring plant diseases in agricultural environments, ensuring greater clarity in model decision-making to optimize the framework for low-resource devices, expanding the dataset to include diverse mango varieties, and exploring multi-crop applications. Key words: Precision agriculture, monitoring, IoT, mango leaf disease, CNN model. *Corresponding author email: nayyer123@gmail.com 2 Department of Information Systems, University of Nizwa, P.O. Box 33, Oman 3 Department of Horticulture (Fruit& Fruit Technology), Bihar Agricultural University, Sabour 813210, India 4 Department of Plant Pathology, Bihar Agricultural University, Sabour 813210, India DOI : 10.58993/ijh/2025.82.3.16