Comparative Analysis of Supervised Machine Learning Techniques in Crop Yield Prediction
Published: 2021
Author(s) Name: Sadakshya Sharma, Jeevan Singh Bhasin, Ashish, Haneet Kour and Karun Handa |
Author(s) Affiliation: B.Tech. Final Year Student, Department of Computer Science and Engineering, PIET, Haryana, India.
Locked
Subscribed
Available for All
Abstract
Machine learning techniques play an important role in solving real world problems. These techniques are also found to be successful in the field of Agriculture for crop yield prediction, leaf disease detection, fruit disease detection, vegetable quality assessment, etc. In this paper, the authors performed comparative analysis of various supervised machine learning techniques for crop yield prediction from soil parameters. Five supervised machine learning techniques such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT) and Random Forest (RF) have been taken for the experimental analysis. The experiments have been carried out for the prediction of the three most commonly grown crops in India: Rice, Wheat and Mustard. The performance of each technique for every crop taken in this study, has been evaluated on the basis of four metrics i.e. accuracy, recall, precision and f-score. The experimental results revealed that decision tree and random forest performed better than all the other supervised machine learning techniques taken in this study, for the prediction of each crop.
Keywords: DT, KNN, Mustard, RF, Rice, SVM, Wheat.
View PDF