ML based methods XGBoost and Random Forest for Crop and Fertilizer Prediction

Abstract

India's economy is heavily dependent on rising agricultural yields and agro-industry goods. In this paper, we explore various machine learning techniques utilized in crop yield estimation and provide the detailed analysis of accuracy of the techniques. Machine learning techniques learn from data set related to the environment on which the estimations and estimation are to be made. The outcome of the learning process is used by farmers for corrective measures for yield optimization. To anticipate the crop and to suggest fertilizer, also to detect plant disease, sophisticated models were devised and constructed for this proposed system. From a photograph of a leaf, an algorithm determines whether the plant is diseased or not. The Random Forest [RF] model provide suggestions for enhancing soil fertility and to recommend fertilizer depending on the soil's nutrient composition.