Biography

The practical deployment of current AI models in real-world agricultural environments remains limited due to challenges in interpretability, generalization across diverse crop types, and robustness under varying environmental conditions. To address these issues, hybrid ensemble learning has emerged as an effective solution, combining multiple predictive models to enhance stability, reduce overfitting, and improve overall accuracy. By integrating classifiers such as decision trees, support vector machines, convolutional neural networks, and recurrent neural networks, these hybrid approaches effectively capture both spatial and temporal dynamics of plant disease progression. Additionally, the incorporation of explainable artificial intelligence (XAI) techniques has gained significant importance, as they enable transparency in model predictions, allowing farmers and agronomists to understand the reasoning behind disease detection outcomes. This interpretability is crucial for building trust and ensuring the adoption of AI-driven solutions in agriculture. The proposed explainable hybrid ensemble learning framework aims to deliver accurate plant disease prediction along with interpretable crop management insights. By leveraging multi-modal feature extraction, feature selection, and ensemble-based classification, the system enhances prediction reliability across various crops and environmental conditions. Furthermore, the integration of XAI methods such as SHAP and LIME facilitates the identification of key features influencing disease detection, enabling targeted interventions and improved crop management strategies. Overall, this approach contributes to the advancement of precision agriculture by providing a robust, transparent, and scalable solution for effective plant disease management, thereby promoting intelligent, data-driven farming practices.