Crop Yield Prediction Using Machine Learning Approaches

Crop Yield Prediction Using Machine Learning Approaches

Dr.M.Sengaliappan1, Bharathkumar.K2

1Head of the Department, Department of Computer Applications,

Nehru college of management, Coimbatore, Tamilnadu, India

E-mail-ncmdrsengaliappan@nehrucolleges.com

2Student of II MCA, Department of Computer Applications,

Nehru College of Management, Coimbatore, Tamilnadu, India

E-mail-bk3006848@gmail.com

Abstract

Farming accounts for the majority of India's GDP, which is reliant on agriculture. This project is motivated by the rising suicide rates among farmers, which could be brought on by poor agricultural yields. The agricultural industry is now seriously threatened by changes in the climate and other environmental factors. To find workable and efficient solutions for this issue, machine learning is a crucial strategy. using past data, such as weather, soil, rainfall, and previous crop yield, to forecast crop yield. The machine learning algorithm helped us do this. KNN- K Nearest Neighbour, Random Forest, Decision tree, and Logistic Regression were among the machine learning methods we compared. The Random Forest approach yielded an accuracy rate. A web application that forecasts crop yields both generally and for a specific crop has been developed as part of this research. It also tells the user whether or not the time is ideal to apply the fertilizer.

Keywords-KNN, Decision tree, Random Forest, logistic regression, python programming; confusion matrix; correlation matrix