Soil Analysis and Crop Recommendation using Machine Learning
Aditya Motwani, Param Patil, Vatsa Nagaria, Shobhit Verma, Sunil Ghane
Abstract
India is the land of agriculture and is among the top three global producers of many crops. The Indian farmer lies at the heart of the agricultural sector yet most Indian farmers remain at the bottom of the social strata. In addition, farmers find it difficult to decide which crop is best suitable and profitable for their soil, in spite of the few technological solutions that exist today, due to the variation in soil types across geographical regions. This paper proposes a crop recommendation system that uses a Convolutional Neural Network (CNN) and a Random Forest Model to predict the optimal crop to be grown by analyzing various parameters including the region, soil type, yield, selling price, etc. The CNN architecture gave an accuracy of 95.21 %, and the Random Forest Algorithm had an accuracy of 75%.