Agriculture, which is regarded as the fundamental basis of the economy, has a major impact on a nation’s economic growth and its GDP (gross domestic product). Agriculture is most commonly associated with the production of essential crops. The farmers undergo several challenges in each stage of crop production, including soil preparation, seed selection, spotting of disease, irrigation problems, predicting yields, weed control, etc. This study presents an in-depth study of the recent advancements in the agricultural sector using machine learning (ML) techniques. Machine learning is nowadays used in almost every stage of the agricultural process. The study presents a detailed review of the different machine learning methods employed in agriculture, including the advantages of using the techniques and the challenges incurred in their adoption. The study further provides a comparison and contrast of different machine learning techniques to make it more informative for future researchers.

Artificial Intelligence (AI) Machine Learning (ML) Agriculture Support Vector Machine (SVM) Random Forest (RF) Artificial Neural Network (ANN)