Uncertainty Quantification for Reduced-Order Surrogate Models Applied to Cloud Microphysics

TL;DR

This paper presents a flexible, model-agnostic framework for uncertainty quantification in reduced-order models, demonstrated on cloud microphysics, enabling reliable prediction intervals without altering the original model training.

Contribution

Introduces a post hoc, model-agnostic uncertainty quantification method for latent space ROMs using conformal prediction, applicable without modifying existing models.

Findings

Accurately predicts droplet-size evolution in cloud microphysics

Provides reliable uncertainty estimates across the ROM pipeline

Works without changing the original model architecture or training process

Abstract

Reduced-order models (ROMs) can efficiently simulate high-dimensional physical systems but lack robust uncertainty quantification methods. Existing approaches are frequently architecture- or training-specific, which limits flexibility and generalization. We introduce a post hoc, model-agnostic framework for predictive uncertainty quantification in latent space ROMs that requires no modification to the underlying architecture or training procedure. Using conformal prediction, our approach estimates statistical prediction intervals for multiple components of the ROM pipeline: latent dynamics, reconstruction, and end-to-end predictions. We demonstrate the method on a latent space dynamical model for cloud microphysics, where it accurately predicts the evolution of droplet-size distributions and quantifies uncertainty across the ROM pipeline.