Prognostic of Soil Nutrients and Soil Fertility Index Using Machine Learning Classifier Techniques

Abstract

Soil testing is a unique tool for finding the available soil reaction (pH), organic carbon, and nutrients status of the soil. It helps to select the suitable crops concerning available pH and soil nutrients level to increase crop production. In this current approach, the soil test prediction is used to differentiate several soil features like soil fertility indices of available pH, organic carbon, electrical conductivity, macro nutrients, and micro nutrients. The Classification and prediction of the soil parameters lead to reduce the artificial fertilizer inputs, increasing crop yield, improves soil health and crop growth and increase profitability. These problems are solved by using fast learning and classification techniques known as machine learning (ML) classifier techniques such as random forest, Gaussian naïve Bayes, logistic Regression, decision tree, k-nearest neighbour and support vector machine. After the analysis decision tree classifier attains the maximum performance to solve all problems which goes above 80% followed by other classifiers.