Predictability of Storms in an Idealized Climate Revealed by Machine Learning

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 with 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. Quantitatively, jet meandering over the storm center and eastern regions is associated with a doubling of the predicted uncertainty sensitivity in storm growth to the jet structure. These findings highlight the potential of machine learning for advancing understanding of predictability and its governing mechanisms.