Enhancing agriculture productivity with machine learning in crop yield optimization

Abstract

The majority of the GDP of an agriculture-based economy comes from farming. This initiative was inspired by the rising suicide rates among farmers, which may be related to poor crop yields. The field of agriculture is now seriously threatened by changes in the climate and other environmental factors. For this problem to be solved effectively and practically, machine learning is a crucial strategy. Estimating agricultural output based on historical information such as Ph, humidity temperature, rainfall, N, P, K. We used Machine Learning method to achieve this. We constructed and compared a number of various machine learning algorithms and ultimately settled on the Random Forest Algorithm, which provided an accuracy of 97.87%.