Rapid Neural Network Prediction of Linear Block Copolymer Free Energies

TL;DR

This paper introduces a machine learning approach that accurately predicts free energies of linear diblock copolymer systems from simulation data, significantly reducing computational effort compared to traditional methods like BAR.

Contribution

The authors develop a neural network framework trained on simulation-derived energetic descriptors to rapidly estimate free energies, outperforming traditional methods in efficiency and reliability.

Findings

Neural network models accurately predict free energies across various polymer parameters.

Models remain reliable even where traditional BAR estimates fail due to poor phase-space overlap.

The approach accelerates thermodynamic analysis of polymer systems with minimal loss of accuracy.

Abstract

Free energies are fundamental quantities governing phase behavior and thermodynamic stability in polymer systems, yet their accurate computation often requires extensive simulations and post-processing techniques such as the Bennett Acceptance Ratio (BAR). While BAR provides reliable estimates when applied between closely related thermodynamic states, evaluating free energies across large changes in interaction strength typically requires a sequence of intermediate simulations to maintain sufficient phase-space overlap, substantially increasing computational cost. In this work we develop a machine learning framework for rapidly predicting excess free energies of linear diblock copolymer systems from simulation-derived energetic descriptors. Using dissipative particle dynamics simulations of freely-jointed chain polymers, we construct a dataset of per-chain energetic statistics, including heterogeneous interaction energies, homogeneous interaction energies, and bonded spring energies, and train feed-forward neural networks to learn the relationship between these descriptors and free energies computed using a stratified BAR procedure. The resulting models accurately reproduce the reference free energies across a range of chain lengths, compositions, and densities, including polymer architectures held out from training. In regimes where direct, brute-force BAR estimates become unreliable due to poor phase-space overlap, the neural network predictions remain consistent with the reference values. These results demonstrate that physically informed machine learning models can serve as efficient surrogates for expensive free-energy calculations and provide a promising approach for accelerating thermodynamic analysis of polymer systems.