Qualitative Regionalization of Bay of Bengal

Abstract

Clustering is an essential statistical technique to find subgroups within a dataset. Clustering helps to uncover hidden relationships among the observational variables in the data. Many researchers have applied clustering techniques across a number of knowledge domains with success. Here we focus on application to ocean science, more particularly to the north region of the Indian Ocean, i.e., the Bay of Bengal. In this article, Regionalization is carried out for the Bay of Bengal to group the regions with similar characteristics using a graph-based clustering technique called SKATER (Spatial ‘K’luster Analysis by Tree Edge Removal). These subgroups are consistent with observations that characterize the near-surface features of the Bay of Bengal.