Application of K-means Clustering Algorithm in Rice Production of Tamil Nadu, India

Abstract

Aim: (i) To Cluster the Rice data using K-Means clustering algorithm. (ii) To helps the study of crop yield prediction. Study Design: K-Means clustering technique is one of the most common exploratory data analysis used to get an intuition about the structure of the data. Place and Duration of Study: Time Series crop data were collected from the season and crop report, Directorate of Economics and Statistics, Chennai for the period of 2015-2020. Methodology: The machine learning algorithm of big data analytics method such as K-means clustering algorithm helps to predict the paddy yield accurately in Tamil Nadu. The performance of the technique is examined through the determinable value of k by Elbow method and Silhouette method which helps in the crop yield prediction. Results: The observed results show that there is a positive relationship between area, production, area under irrigation, minimum temperature, and relative humidity and a close negative relationship with moisture and wind speed. Additionally, two clusters were identified with cluster 2 having the highest mean value, followed by 1. The identification of the highest mean clusters will guide farmers on where best to concentrate on when planting their crops in ordered to improve productivity and crop yield. Conclusion: This study reveals a scalable, simple, and reduced method for correctly assessing rice production over a large area using publicly released multi-source data, which may have been used to calculate crop production in areas with rarely observed data and all around the world.