Extreme Event Aware ($\eta$-) Learning

TL;DR

This paper introduces $\\eta$-learning, a novel method for predicting rare and extreme events in complex systems without requiring their presence in training data, by enforcing extreme event statistics during model training.

Contribution

The paper proposes a new regularization-based approach, $\\eta$-learning, that improves extreme event prediction without relying on observed extremes in training data.

Findings

Enforces extreme event statistics during training.

Produces models capable of generating unprecedented extreme events.

Validated on real-world precipitation downscaling problems.

Abstract

Quantifying and predicting rare and extreme events persists as a crucial yet challenging task in understanding complex dynamical systems. Many practical challenges arise from the infrequency and severity of these events, including the considerable variance of simple sampling methods and the substantial computational cost of high-fidelity numerical simulations. Numerous data-driven methods have recently been developed to tackle these challenges. However, a typical assumption for the success of these methods is the occurrence of multiple extreme events, either within the training dataset or during the sampling process. This leads to accurate models in regions of quiescent events but with high epistemic uncertainty in regions associated with extremes. To overcome this limitation, we introduce Extreme Event Aware (e2a or eta) or $\eta$-learning which does not assume the existence of extreme events in the available data. $\eta$-learning reduces the uncertainty even in `uncharted' extreme event regions, by enforcing the extreme event statistics of an observable indicative of extremeness during training, which can be available through qualitative arguments or estimated with unlabeled data. This type of statistical regularization results in models that fit the observed data, while enforcing consistency with the prescribed observable statistics, enabling the generation of unprecedented extreme events even when the training data lack extremes therein. Theoretical results based on optimal transport offer a rigorous justification and highlight the optimality of the introduced method. Additionally, extensive numerical experiments illustrate the favorable properties of the $\eta$-learning framework on several prototype problems and real-world precipitation downscaling problems.