A Robust Learning Methodology for Uncertainty-aware Scientific Machine Learning models

TL;DR

This paper introduces a comprehensive methodology for evaluating and enhancing the robustness of Scientific Machine Learning models by considering multiple sources of uncertainty, validated through a polymerization reactor case study.

Contribution

It proposes a novel, all-encompassing uncertainty evaluation framework for SciML models, addressing theory absence, data imperfections, and computational challenges.

Findings

Models are robust against uncertainties in the case study.

The methodology effectively identifies and quantifies multiple uncertainty sources.

Validated approach improves reliability of SciML models in practical applications.

Abstract

Robust learning is an important issue in Scientific Machine Learning (SciML). There are several works in the literature addressing this topic. However, there is an increasing demand for methods that can simultaneously consider all the different uncertainty components involved in SciML model identification. Hence, this work proposes a comprehensive methodology for uncertainty evaluation of the SciML that also considers several possible sources of uncertainties involved in the identification process. The uncertainties considered in the proposed method are the absence of theory and causal models, the sensitiveness to data corruption or imperfection, and the computational effort. Therefore, it was possible to provide an overall strategy for the uncertainty-aware models in the SciML field. The methodology is validated through a case study, developing a Soft Sensor for a polymerization reactor. The results demonstrated that the identified Soft Sensor are robust for uncertainties, corroborating with the consistency of the proposed approach.