Spatiotemporal Cluster Analysis of Gridded Temperature Data -- A Comparison Between K-means and MiSTIC

TL;DR

This study compares K-means and MiSTIC clustering methods on gridded temperature data to analyze spatiotemporal climate patterns, revealing how geographic features influence clustering results and dataset groupings.

Contribution

It provides a comparative analysis of K-means and MiSTIC clustering techniques on climate data, highlighting their behavior and sensitivity to geographic and dataset variations.

Findings

K-means boundaries align with topography.

MiSTIC clusters are influenced by physiographic features.

Dataset differences significantly affect cluster counts.

Abstract

The Earth is a system of numerous interconnected spheres, such as the climate. Climate's global and regional influence requires understanding its evolution in space and time to improve knowledge and forecasts. Analyzing and studying decades of climate data is a data mining challenge. Cluster analysis minimizes data volumes and analyzes behavior by cluster. Understanding invariant behavior is as crucial as understanding variable behavior. Gridded data from two sources: Grided IMD data and CMIP5 HadCM3 decadal experiments, are studied using K-Means and MiSTIC clustering techniques to explore spatiotemporal clustering of maximum and minimum temperatures. The boundaries of k-means clustering correspond with topography. The Indian subcontinent's physiographic, climatic, and topographical characteristics affect MiSTIC's core areas. Both techniques yield overlapping clusters. The datasets' MiSTIC cluster counts varied significantly. The impact of data on this technique is shown in how the datasets group the Himalayas.