Physics-constrained polynomial chaos expansion for scientific machine learning and uncertainty quantification

TL;DR

This paper introduces a physics-constrained polynomial chaos expansion method that integrates scientific machine learning and uncertainty quantification, enabling physically realistic predictions with limited data and efficient uncertainty estimation.

Contribution

It develops a novel surrogate modeling approach that incorporates physical constraints and combines SciML with UQ, improving accuracy and efficiency in complex physical systems.

Findings

Effectively models PDEs with physical constraints.

Reduces computational costs for surrogate training.

Provides accurate uncertainty estimates in stochastic systems.

Abstract

We present a novel physics-constrained polynomial chaos expansion as a surrogate modeling method capable of performing both scientific machine learning (SciML) and uncertainty quantification (UQ) tasks. The proposed method possesses a unique capability: it seamlessly integrates SciML into UQ and vice versa, which allows it to quantify the uncertainties in SciML tasks effectively and leverage SciML for improved uncertainty assessment during UQ-related tasks. The proposed surrogate model can effectively incorporate a variety of physical constraints, such as governing partial differential equations (PDEs) with associated initial and boundary conditions constraints, inequality-type constraints (e.g., monotonicity, convexity, non-negativity, among others), and additional a priori information in the training process to supplement limited data. This ensures physically realistic predictions and significantly reduces the need for expensive computational model evaluations to train the surrogate model. Furthermore, the proposed method has a built-in uncertainty quantification (UQ) feature to efficiently estimate output uncertainties. To demonstrate the effectiveness of the proposed method, we apply it to a diverse set of problems, including linear/non-linear PDEs with deterministic and stochastic parameters, data-driven surrogate modeling of a complex physical system, and UQ of a stochastic system with parameters modeled as random fields.