Understanding Extreme Precipitation Changes through Unsupervised Machine Learning

TL;DR

This paper introduces an unsupervised machine learning framework to analyze how storm dynamics influence changes in extreme precipitation patterns under climate warming, emphasizing spatial shifts over intensity changes.

Contribution

The study develops a novel unsupervised learning approach to analyze storm-scale climate model outputs, revealing dominant spatial shifts in storm regimes affecting precipitation extremes.

Findings

Spatial patterns of extreme precipitation are dominated by shifts in storm regimes.

Unsupervised learning helps uncover physical mechanisms behind precipitation changes.

Framework can improve understanding of climate change impacts on extreme weather.

Abstract

Despite the importance of quantifying how the spatial patterns of extreme precipitation will change with warming, we lack tools to objectively analyze the storm-scale outputs of modern climate models. To address this gap, we develop an unsupervised machine learning framework to quantify how storm dynamics affect changes in precipitation extremes, without sacrificing spatial information. For the upper precipitation quantiles (above the 80th percentile), we find that the spatial patterns of extreme precipitation changes are dominated by spatial shifts in storm dynamical regimes rather than changes in how these storm regimes produce precipitation. Our study shows how unsupervised machine learning, paired with domain knowledge, may allow us to better understand the physics of the atmosphere and anticipate the changes associated with a warming world.