Predictability of Storms in an Idealized Climate Revealed by Machine Learning

TL;DR

This study employs machine learning to analyze storm predictability in an idealized climate, revealing key factors like jet meanders and baroclinicity that influence forecast accuracy and uncertainty.

Contribution

It introduces a CNN-based approach to quantify storm predictability and identifies specific atmospheric features affecting forecast skill in a controlled climate model.

Findings

Storm intensity less predictable than trajectory

Jet meanders significantly degrade forecast skill

Baroclinicity accelerates storm intensification

Abstract

The midlatitude climate and weather are shaped by storms, yet the factors governing their predictability remain insufficiently understood. Here, we use a Convolutional Neural Network (CNN) to predict and quantify uncertainty in the intensity growth and trajectory of over 200,000 storms simulated in a 200-year aquaplanet GCM. This idealized framework provides a controlled climate background for isolating factors that govern predictability. Results show that storm intensity is less predictable than trajectory. Strong baroclinicity accelerates storm intensification and reduces its predictability, consistent with theory. Crucially, enhanced jet meanders further degrade forecast skill, revealing a synoptic source of uncertainty. Using sensitivity maps from explainable AI, we find that the error growth rate is nearly doubled by the more meandering structure. These findings highlight the potential of machine learning for advancing understanding of predictability and its governing mechanisms.