Leveraging Theory for Enhanced Machine Learning

Published

August 26, 2022

Author(s)

Debra Audus, Austin McDannald, Brian DeCost

Abstract

The application of machine learning to the materials domain has traditionally struggled with two major challenges: a lack of large, curated data sets and the need to understand the physics behind the machine-learning prediction. The former problem is particularly acute in the polymers domain. Here we aim to simultaneously tackle these challenges through the incorporation of scientific knowledge, thus, providing improved predictions for smaller data sets, both under interpolation and extrapolation, and a degree of explainability. We focus on imperfect theories, as they are often readily available and easier to interpret. Using a system of a polymer in different solvent qualities, we explore numerous methods for incorporating theory into machine learning using different machine-learning models, including Gaussian process regression. Ultimately, we find that encoding the functional form of the theory performs best followed by an encoding of the numeric values of the theory.

Citation

ACS Macro Letters

Volume

11

Pub Type

Journals

Download Paper

https://doi.org/10.1021/acsmacrolett.2c00369

Local Download

Keywords

polymers, machine learning, transfer learning, theory

Citation

Audus, D. , McDannald, A. and DeCost, B. (2022), Leveraging Theory for Enhanced Machine Learning, ACS Macro Letters, [online], https://doi.org/10.1021/acsmacrolett.2c00369, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=934090 (Accessed November 20, 2024)