Precision Agriculture Using AI for Crop Yield Prediction and Disease Detection: A Comprehensive Review of Machine Learning and Deep Learning Approaches for Sustainable, Data-Driven Farming
Abstract
Abstract Precision agriculture amalgamates artificial intelligence (AI) with field-level sensors to enhance agricultural yield while reducing resource use. This article offers an extensive examination of the application of machine learning (ML) and deep learning (DL) methodologies to two essential functions: forecasting crop production based on environmental and soil information, and identifying plant diseases using leaf images. We investigate the historical evolution of the discipline, outline prevalent data sources and preprocessing methodologies, evaluate the reported efficacy of prominent model families across various benchmark analyses, showcase representative case-study workflows, and assess the resource and economic implications of AI-assisted agriculture. We provide a deeper examination of regional deployment trends, delineate the practical and technological obstacles hindering large-scale implementation, and suggest prospective research avenues such as federated learning, edge deployment, and interpretable AI. The evaluation aims to function as a comprehensive resource for scholars and professionals exploring this swiftly advancing domain.
