Agriculture plays a vital role in the economic growth of any country. With the increase of population, frequent changes in climatic conditions and limited resources, it becomes a challenging task to fulfil the food requirement of the present population. Precision agriculture also known as smart farming, has emerged as an innovative tool to address current challenges in agricultural sustainability. The mechanism that drives this cutting-edge technology is machine learning (ML). It gives the machine ability to learn without being explicitly programmed. ML together with IoT (Internet of Things) enabled farm machinery are key components of the next agriculture revolution. This article presents a comprehensive review of machine learning applications in agriculture, with a focus on soil property and weather prediction, crop yield forecasting, plant disease and pest detection, weed identification, and precision irrigation management. The adaptability and cost-effectiveness of ML make it a powerful tool for analyzing the complex input?output relationships of agricultural systems. Such systems exhibit non-linearity, temporal variability, and multiple unknown parameters, making machine learning approaches more suitable than traditional analytical methods. Overall, this review underscores the potential of ML to transform agriculture into a more efficient, resilient, and sustainable system and outlines future research directions for the successful integration of intelligent technologies in precision farming.