Agricultural Machine learning platform: Enhancing crop suggestion and crop yield estimates

Abstract

Crop analysis and prediction is a rapidly growing field that plays important role to improve farming methods. It provides farmers with the knowledge and skills to select the best crops for their specific climate and land. Machine learning techniques can be very helpful in automatically recommending crops and identifying pests and diseases, allowing farmers to maximize crop yield while simultaneously preserving soil fertility and replenishing important nutrients. Using seven different machine-learning algorithms, the crop recommendation and crop yield prediction is show in this paper.  The proposed system uses several features, including soil composition and climate data, to accurately predict which crops would be most suitable for a given location. Crop recommendation could be revolutionized by this system, which would help all farmers by increasing crop yields, sustainability, and overall profitability. Through extensive evaluation of an extensive historical data set, we have achieved near-perfect accuracy by training and testing models with various configurations of machine learning algorithms. We show that accuracy in this paper is 99.54% being the highest accuracy ever attained.