Crop Recommendation and Yield prediction Using Machine Learning based Approaches

India is an agricultural country, supporting a significant portion of the population. Agriculture is a source of income for millions of Indians. But due to lack of knowledge and the state's diverse climate and soil conditions often leave farmers grappling with the critical decisions of which crops to cultivate and what yields to expect. This in turn makes the farmers suffering from losses as they cultivate a crop hoping they will get a good harvest but in reality, they don’t get the expected amount of production. To address these challenges prior researchers have used soil and climatic conditions data to recommend crops for a particular soil and predict its expected yield using various types of machine learning and deep learning algorithms. This paper presents a survey of previous works where deep learning and machine learning techniques are used and performs a comparative examination of some bagging and boosting machine learning techniques including random forest, gradient boost, XG boost, Ada boost, light bgm and cat boost for effective recommendation of crop and prediction of its expected yield