Deep Clustering for Climate: Analyzing Teleconnections through Learned Categorical States

TL;DR

This paper introduces a self-supervised discretization method using Masked Siamese Networks to identify meaningful climate regimes from temperature data, aiding analysis and prediction of climate variability.

Contribution

The work demonstrates that learned categorical states from climate data can reflect meaningful climate regimes and relate to phenomena like El Niño, advancing climate data analysis techniques.

Findings

Clusters reflect meaningful climate states

Enables sampling of climate scenarios

Associates with El Niño events

Abstract

Understanding and representing complex climate variability is essential for both scientific analysis and predictive modeling. However, identifying meaningful climate regimes from raw variables is challenging, as they exhibit high noise and nonlinear dependencies. In this work, we explore the use of Masked Siamese Networks to discretize climate time series into semantically rich clusters. Focusing on daily minimum and maximum temperature, we show that the resulting representations: (i) yield clusters that reflect meaningful climate states under our modeling assumptions, offering a simplified representation for downstream use; (ii) enable sampling and analysis of specific climate scenarios; and (iii) exhibit statistical associations with El Ni\~no events, underscoring their scientific relevance. Our findings highlight the potential of self-supervised discretization as a tool for climate data analysis and open avenues for incorporating richer climate indicators in future work.