On-the-Fly Machine-Learned Force Fields for High-Fidelity Polymer Glass Transition Simulations

TL;DR

This paper introduces an on-the-fly machine-learned force field approach that enables high-accuracy, large-scale polymer glass transition simulations at a fraction of the traditional computational cost.

Contribution

The authors develop an adaptive, on-the-fly MLFF method that combines AIMD with machine learning to predict polymer Tg with quantum accuracy efficiently.

Findings

Accurately predicts Tg for twelve diverse polymers.

Reduces computational cost by about six orders of magnitude.

Demonstrates generalizability across various polymer chemistries.

Abstract

Predicting polymer glass transition temperatures (Tg) with first-principles fidelity has long remained out of reach, as cooling multi-thousand-atom systems over a broad temperature range at acceptable rates exceeds the computational limits of ab initio molecular dynamics (AIMD). Here we employ a hybrid scheme that merges AIMD with accelerated on-the-fly (OTF) machine-learned force-field (MLFF) construction, enabling Tg prediction at quantum-mechanical accuracy with near-classical computational cost. The OTF protocol to construct MLFFs adaptively triggers first-principles calculations only when newly encountered configurations lie outside the current model's domain of confidence, allowing robust, parameter-free MLFFs to be built from merely 1000 AIMD-sampled configurations per polymer. These MLFFs are then utilized to perform long-time cooling simulations on amorphous supercells containing several thousand atoms. Applied across twelve polymers spanning aromatic, aliphatic, heteroatomic, and branched chemistries, the method yields predictions in excellent accord with experiment while reducing computational cost by approximately six orders of magnitude relative to AIMD. This work establishes a new paradigm for predictive polymer modeling, demonstrating that OTF-MLFFs provide a generalizable, accurate, and scalable route to simulating the thermophysical behavior of complex disordered materials at quantum-mechanical fidelity.