Accelerated Scheme to Predict Ring-Opening Polymerization Enthalpy: Simulation-Experimental Data Fusion and Multitask Machine Learning

Aubrey Toland; Huan Tran; Lihua Chen; Yinghao Li; Chao Zhang; Will Gutekunst; Rampi Ramprasad

doi:10.1021/acs.jpca.3c05870

Accelerated Scheme to Predict Ring-Opening Polymerization Enthalpy: Simulation-Experimental Data Fusion and Multitask Machine Learning

J Phys Chem A. 2023 Dec 21;127(50):10709-10716. doi: 10.1021/acs.jpca.3c05870. Epub 2023 Dec 6.

Authors

Aubrey Toland¹, Huan Tran¹, Lihua Chen¹, Yinghao Li², Chao Zhang², Will Gutekunst³, Rampi Ramprasad¹

Affiliations

¹ School of Materials Science & Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
² School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
³ School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.

Abstract

Ring-opening enthalpy (ΔH^ROP) is a fundamental thermodynamic quantity controlling the polymerization and depolymerization of an important class of recyclable polymers, namely, those created from ring-opening polymerization (ROP). Highly accurate first-principles-based computational methods to compute ΔH^ROP are computationally too demanding to efficiently guide the design of depolymerizable polymers. In this work, we develop a generalizable machine-learning model that was trained on experimental measurements and reliably computed simulation results of ΔH^ROP (the latter provides a pathway to systematically increase the chemical diversity of the data). Predictions of ΔH^ROP using this machine-learning model require essentially no time while the prediction accuracy is about ∼8 kJ/mol, approaching the well-known chemical accuracy. We hope that this effort will contribute to the future development of new depolymerizable polymers.