Open Access Open Access  Restricted Access Subscription or Fee Access

Identifying Rainfall Diversity through Clustering

Vikas Singh, Mukesh Kumar

Abstract



The uneven distribution of rainfall at different regions is an important issue now days. Particularly the places of low rainfall are of serious concerns. These places are lacking in drinking water and lot of other related problems like unsatisfactory irrigation, sanitation, etc. The rainfall diversity in India through clusters (similar regions) has been observed under this study. The rainfall distribution in India is varied over seasons, and high-rainfall observed under monsoon season. In this paper, we have analyzed rainfall data in the context of India through divisive clustering technique K-means and model based probability clustering. The techniques are used over rainfall data given by the Indian Meteorology Department (IMD), and a comparative finding has been reported. The annual and seasonal rainfalls data for the year 2016-17 has been taken for this study. Optimal numbers of clusters are obtained by using the Elbow method in case of K-means clustering and Bayesian Information Criterion (BIC) is used for model based clustering. Moreover, the results obtained through K-means and model based cluster analysis have been reported in terms of spatial distribution. The main advantage of splitting the states of rainfall into homogenous groups based on similar features is that it eliminates the necessity to carry out a detailed drought characteristic analysis for any location of interest. Therefore detection of rainfall pattern in a spatial domain is very important and useful for policy makers, climatologists, government, hydrologists and local and regional planners and managers.

Keywords


Clustering, K-means, Model based clustering, EM-algorithm, BIC, rainfall.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.