Crop Yield Prediction and Fertilizer Recommendation System Using Hybrid Machine Learning Algorithms
K. P. K. Devan, B Swetha, Patlolla Sruthi, S Varshini
Abstract
Progressions in machine learning and crop simulation techniques have created new opportunities for improving agro-based prediction. In crop yield analysis, machine learning is a rapidly expanding research area. Predicting yield is a crucial issue in agriculture. Machine learning (ML), on the other hand, aims to make forecast by discovering associations between input and response variables. Various elements, including weather and soil, are making it challenging for farmers to cultivate crops. Developing effective agricultural and food policies on a regional and international scale requires accurate crop yield forecasts. Our proposed solution combines two machine learning algorithms to optimize agriculture by predicting crop yield and recommending fertilizer. This script is innovative because it allows the user to predict the most suitable crop based on basic information such as soil characteristics and weather conditions. We have utilized Random Forest and Logistic Regression for the system’s implementation. This model serves as an example of hybrid ML approaches which could solve the above mentioned issues and increase the yield.