Prediction for rice yield using data mining approach in Ranga Reddy district of Telangana, India

Baby Akula Baby Akula,M P G Raj ,R S Parmar ,K Narasimha Reddy

doi:10.54386/jam.v23i2.75

Abstract

 In order to explore the possibility of crop estimation, data mining approach being multidisciplinary was followed. The district of Ranga Reddy, Telangana State, India has been chosen for the study and its year wise average yield data of rice and daily weather over a period of 31 years i.e. from 1988-2019 (30th to 47th Standard Meteorological Weeks). Data mining tool WEKA (V3.8.1). Min- Max Normalization technique followed by Feature Selection algorithm, ‘cfsSubsetEval’ was also adopted to improve quality and accuracy of data mining algorithms. Thus, after cleaning and sorting of data, five classifiers viz., Logistic, MLP (Multi Layer Perceptron), J48 Classifier, LMT (Logistic Model Trees) and PART Classifier were employed over the trained data. The results indicated that the function based and tree based models have better performance over rule based model. In case of function based two models examined, viz., Logistic and MLP, the later performed better over Logistic model. Between tree based two models, LMT performed better over J48. Thus, MLP classifier model found to be the best fit model in predicting rice yields as it recorded an accuracy of 74.19 %, sensitivity of 0.742 and precision of 0.743 as compared with other models. The MLP has also achieved the highest F1 score of (0.742) and MCC (0.581).

Highlights

Reliable prediction of crop yield plays a vital role in agricultural management in India as being agriculture based economy. Various classification techniques such as the Naive Bayes, J48, random forests, support vector machines, artificial neural networks were used for crop yield prediction (Sujatha et al, 2016)
In the light of these findings, the present study was devised with the main objective of examining the influence of weather parameters in estimation of rice crop yield in Ranga Reddy district of Telangana using data mining approach
Based on all the benchmarks used to measure the predictability of fitted models employed for rice yield estimation, it was discovered that Multilayer perceptron (MLP) classifier model performed better by achieving the highest prediction accuracy 74.19 %, sensitivity of 0.742 and precision of 0.743 as compared with other fitted models

Summary

Introduction

Reliable prediction of crop yield plays a vital role in agricultural management in India as being agriculture based economy Various classification techniques such as the Naive Bayes, J48, random forests, support vector machines, artificial neural networks were used for crop yield prediction (Sujatha et al, 2016). Mucherino et al, (2009) followed data mining techniques that include K-means, K nearest neighbor, ANN (Artificial Neural Network), and support vector machines in predicting the yields. Classification algorithms such as J48, REPTree, and Random Forest have been applied over agricultural data set for predicting crop productivity with prediction accuracy of 83% (Diriba and Borena, 2013). In the light of these findings, the present study was devised with the main objective of examining the influence of weather parameters in estimation of rice crop yield in Ranga Reddy district of Telangana using data mining approach

Methods

Results

Conclusion