Intelligent Techniques for Prediction of Kharif Food Grains Yield in Gujarat

Abstract

Machine learning is a vital decision support tool for crop yield prediction. Yield prediction could be a very important agricultural issue. Any farmer is inquisitive about knowing what quantity of yield he's getting ready for. In the past, yield prediction was performed by considering farmers' expertise in specific fields and crops. Based on previous data, we are able to predict crop yield victimization using a machine-learning technique. Crop yield prediction is an important area of research that helps in ensuring food security all around the world. Developing higher techniques to predict crop productivity in several climates can assist farmers and other stakeholders in making important decisions in terms of scientific agriculture and crop choice. This paper reports on the utilization of multiple linear regression (MLR), Gaussian Process, SMOreg and random forest to predict Kharif food grain crop yield for Gujrat state, India. The parameters chosen for the study were precipitation, minimum temperature, average temperature, maximum temperature, reference crop evapotranspiration, area, production, and yield for the Kharif season (June to November) for the years 2000 to 2020. The dataset was processed victimisation the WEKA tool.