Crop Yield Prediction using Random Forest Algorithm
Rajesh Yamparla, Harisa Sultana Shaik, Naga Sai Pravallika Guntaka, Pallavi Marri, Srilakshmi Nallamothu
Abstract
India’s economy is based on agriculture; Agriculture has a great importance in the economic growth of the country. Agriculture has been put in jeopardy by environmental factors such as climate change and other environmental factors. Crop production assumptions developed ahead of time might aid farmers in making the required preparations for things like storage and marketing. As a result, to enhance the efficiency of crop yields via new technology is a critical step in obtaining competitive crops. So, Machine learning has become the critical component of finding practical and successful solutions to this issue. The focus of the research is on using several machine learning approaches to forecast agricultural yield. Forecasting agricultural yield based on past data such as rainfall, temperature, yield, and pesticides. Each of these data properties will be evaluated, and the data will be trained using multiple machine learning methods to create a model. A comparison of numerous Machine learning techniques, including, decision tree regression, linear regression, gradient boosting, SGD, K Nearest Neighbour, and random forest, was undertaken. Among them the random forest is the most accurate of the bunch, which gave an accuracy of 95%. This system will assist farmers in deciding which crop to plant in order to maximise production. This study offers a quick examination of agricultural yield forecasting using the Random Forest technique for estimating precise and accurate.