Artificial Intelligence (AI) and Machine Learning (ML) are transforming agriculture by enhancing productivity, resource efficiency, and sustainability. This review examines recent advances in AI- and ML-driven smart farming applications, including crop disease detection, yield prediction, precision irrigation, weed management, soil analysis, livestock health monitoring, and drone-based crop surveillance. Deep learning techniques, particularly Convolutional Neural Networks (CNNs), have demonstrated high accuracy in plant disease diagnosis, while machine learning algorithms such as Random Forest and Support Vector Machines have improved crop yield prediction and soil classification. The integration of AI with the Internet of Things (IoT) enables real-time monitoring, predictive analytics, and informed decision-making across agricultural systems. Despite these advances, widespread adoption remains constrained by high implementation costs, data quality issues, limited digital infrastructure, and inadequate technical expertise, particularly in developing regions. The review highlights recent developments, discusses key challenges, and identifies future research opportunities for developing resilient, intelligent, and sustainable agricultural systems.

Keywords: Artificial Intelligence, Machine Learning, Smart Agriculture, Precision Farming, Deep Learning.