Learning predictable and informative dynamical drivers of extreme precipitation using variational autoencoders

<p><br></p><p><strong>Citation:</strong> Spuler, F. R., Kretschmer, M., Balmaseda, M. A., Kovalchuk, Y., &amp; Shepherd, T. G. (2025). Learning predictable and informative dynamical drivers of extreme precipitation using variational autoencoders. <em>Weather and Climate Dynamics</em>, 6, 995–1014. https://doi.org/10.5194/wcd-6-995-2025</p><p><strong>Main Takeaways:</strong></p><ul><li><strong>Innovative Machine Learning Approach:</strong> The study introduces the Categorical Mixture Model Variational Autoencoder (CMM-VAE), a novel generative machine learning method designed to identify probabilistic atmospheric circulation regimes by combining targeted dimensionality reduction and probabilistic clustering into a single model.</li><li><strong>Resolving a Major Forecasting Trade-off:</strong> Traditionally, atmospheric regimes are either highly predictable globally but locally uninformative, or highly informative for local impacts but lacking in subseasonal predictability. CMM-VAE resolves this trade-off, successfully identifying patterns that predict local extremes without sacrificing forecast skill at subseasonal lead times.</li><li><strong>Targeted Application for Moroccan Rainfall:</strong> When applied to extreme winter precipitation in Morocco, the CMM-VAE method successfully disentangled a distinct, highly impactful weather pattern—a Scandinavian blocking coupled with a localized cut-off low—that traditional linear clustering methods failed to isolate.</li><li><strong>Linkages to Global Climate Drivers:</strong> The weather regimes identified by the model remain physically interpretable and show clear, predictable teleconnections to large-scale, low-frequency climate drivers, notably the Madden-Julian Oscillation (MJO) and the Stratospheric Polar Vortex (SPV).</li><li><strong>Enhancing Early Warning Systems:</strong> By providing a better representation of regional dynamical drivers, this framework offers significant potential to improve subseasonal-to-seasonal (S2S) forecasts, statistical downscaling, and early-warning systems for severe, localized weather impacts.</li></ul>