Calibrated Physics-Informed Uncertainty Quantification

TL;DR

This paper presents a physics-informed conformal prediction framework that provides guaranteed, data-free uncertainty quantification for neural PDE models, enabling reliable predictions in complex physical simulations without labeled data.

Contribution

It introduces a model-agnostic, physics-based conformal prediction method that calibrates uncertainty estimates using physics residuals, applicable across various PDEs without requiring labeled data.

Findings

Provides guaranteed uncertainty calibration for neural PDEs.

Enables data-free uncertainty quantification with coverage guarantees.

Validated on plasma modeling and fusion reactor design tasks.

Abstract

Simulating complex physical systems is crucial for understanding and predicting phenomena across diverse fields, such as fluid dynamics and heat transfer, as well as plasma physics and structural mechanics. Traditional approaches rely on solving partial differential equations (PDEs) using numerical methods, which are computationally expensive and often prohibitively slow for real-time applications or large-scale simulations. Neural PDEs have emerged as efficient alternatives to these costly numerical solvers, offering significant computational speed-ups. However, their lack of robust uncertainty quantification (UQ) limits deployment in critical applications. We introduce a model-agnostic, physics-informed conformal prediction (CP) framework that provides guaranteed uncertainty estimates without requiring labelled data. By utilising a physics-based approach, we can quantify and calibrate the model's inconsistencies with the physics rather than the uncertainty arising from the data. Our approach utilises convolutional layers as finite-difference stencils and leverages physics residual errors as nonconformity scores, enabling data-free UQ with marginal and joint coverage guarantees across prediction domains for a range of complex PDEs. We further validate the efficacy of our method on neural PDE models for plasma modelling and shot design in fusion reactors.