***Note: This event has been rescheduled to Wednesday, February 4.***
Join us for a Lunch & Learn with Daniel Boscu as he discusses his research developing an AI-based atmospheric model to forecast extreme climate events.
Lunch is provided.
Abstract
Extreme climate events like sudden stratospheric warmings (SSWs) are rare yet impactful, posing significant modeling challenges due to their infrequent occurrence in historical data. AI-based emulators offer a fast and data-efficient alternative to traditional numerical models, so long as they can reliably represent rare transitions and internal variability. In this study, we develop a deep learning architecture tailored to emulate the stochastic Holton-Mass stratospheric model and investigate its latent space. The Holton-Mass model is capable of simulating both a standard polar vortex state and a disrupted vortex, warm stratosphere state, as well as rare transitions between the two states. The architecture we use is a ResNet-inspired Conditional Variational Autoencoder (CVAE) with 6-layer encoder/decoder stacks and state conditioning. The model is trained on 300,000k days of simulated real and imaginary streamfunction (ψ) fields, with the goal of forecasting ψ and mean zonal wind (U) at the next time step. To handle the system’s inherent stochasticity, we use a KL-annealed training procedure and a specially weighted loss function that balances reconstruction and latent regularization. The emulator we build faithfully represents model dynamics, including distributions of state variables, transition statistics, committor function, and lead time distribution. To interpret the learned representation, we apply Principal Component Analysis (PCA) to the latent space and discover a striking result: the encoded representations self-organize into well-separated clusters corresponding to four physical regimes (standard or warm stratosphere and stable or about to transition). This degree of unsupervised regime separation in latent space is rare for deep generative models, particularly in high-dimensional, stochastic systems. This work contributes a scalable, interpretable emulator architecture for stochastic climate dynamics and introduces a latent space probing framework for diagnosing what AI models internalize about rare events. Our findings suggest that effectively designed deep emulators can not only accelerate simulation but may also uncover physically meaningful manifolds of variability through latent space interrogation. Future directions include incorporating rare-event sampling and developing disentangled latent models to further enhance interpretability and control.
