Explainability and extrapolation of machine learning models for predicting the glass transition temperature of polymers (in EN)
Abstract
Machine learning (ML) offers promising tools to develop surrogate models for polymers' structure–property relations. Surrogate models can be built upon existing polymer data and are useful for rapidly predicting the properties of unknown polymers. The accuracy of such ML models appears to depend on the feature space representation of polymers, the range of training data, and learning algorithms. Here, we establish connections between these factors for predicting the glass transition temperature (Tg) of polymers. Our analysis suggests linear models with fewer fitting parameters are as accurate as nonlinear models with many hidden and unexplainable parameters. Also, the performance of a monomer topology‐based ML model is found to be qualitatively identical to that of a physicochemical descriptor‐based ML model. We find that the ML models's performance in the extrapolative region is enhanced as the property range of the training data increases. Moreover, we establish newTg– polymer chemistry correlations via ML. Our work illustrates how ML can advance the fundamental understanding of polymer structure–property correlations and its efficacy for extrapolation problems.
- Research Organization:
- Argonne National Laboratory (ANL), Argonne, IL (United States). Argonne Leadership Computing Facility (ALCF)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC02-06CH11357
- OSTI ID:
- 2580641
- Journal Information:
- Journal of Polymer Science, Journal Name: Journal of Polymer Science Journal Issue: 6 Vol. 62; ISSN 2642-4150
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- EN
Similar Records
Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning