Predictive Modeling of Rice Yield Using Environmental Factors and Machine Learning

In India, agriculture is one of the most common and least-paid professions. Growing the best crop can change the income scenario, leading to a boom in agriculture. This study aims to make predictions of forecast agricultural yield using a variety of machine learning approaches. The outcomes of these methodologies are evaluated on the basis of the mean absolute error. Here we have used random forest regression, gradient boosting regression, and decision tree regression in order to predict the rice yield. From the experiments we got random forest regression to be the best with 99% accuracy. The farmers could choose which crop to cultivate to receive the most significant yield by using the predictions provided by machine learning algorithms by considering variables like temperature, rainfall, area, and PH.