Active Learning of a Neural Network Potential for Large-Scale Atomistic Simulations of Polymer Electrolyte Membranes

Abstract

Machine learning interatomic potentials (MLIPs) can achieve near density-functional-theory (DFT) accuracy at force-field computational cost; however, long-time, large-scale molecular dynamics (MD) simulations often fail when trajectories sample local atomic environments that are underrepresented in the training set. Here, we employ an active-learning workflow to develop a robust neural network potential (NNP) for perfluorinated ionomer membranes (Nafion) across a wide range of hydration levels ($\lambda$). A reliable deep potential (DP) model is constructed through iterative dataset expansion within active-learning loops. Specifically, off-equilibrium configurations are generated via non-equilibrium DPMD simulations and selected using an ensemble force-deviation criterion combined with a three-dimensional structural feature space augmented by minimum interatomic distances, which significantly enhances the DP model's robustness. The trained DP model enables stable MD simulations of large Nafion systems containing approximately 10,000-20,000 atoms for an extended duration of 31 ns. Our DPMD simulations reproduce the qualitative hydration dependence of density and yield self-diffusion coefficients of hydrogen atoms and hydronium ions in quantitative agreement with experimental values. Compared with previous ab initio MD and MLIP-MD studies, our simulations show improved agreement with experimental transport properties and remain predictive up to $\lambda =24$, well beyond the training range ($\lambda \le 13$). This work provides an efficient and scalable approach for achieving stable, large-scale NNP-MD simulations of heterogeneous polymer electrolyte membranes and related disordered materials.

53 pages, 14 figures

References in corpus (26)

• Advanced capabilities for materials modelling with Quantum ESPRESSO
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum ESPRESSO toward the exascale
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• Machine learning for molecular simulation
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine-learning based interatomic potential for amorphous carbon
• DeePMD-kit v2: A software package for Deep Potential models
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• How van der Waals interactions determine the unique properties of water
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• RadonPy: Automated Physical Property Calculation using All-atom Classical Molecular Dynamics Simulations for Polymer Informatics
• Local Segmental Dynamics and Stresses in Polystyrene - C${}_{60}$ Mixtures
• Phase stability of Au-Li binary systems studied using neural network potential
• Developing machine-learned potentials to simultaneously capture the dynamics of excess protons and hydroxide ions in classical and path integral simulations
• Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations
• Transferability of the chemical bond-based machine learning model for dipole moment: the GHz to THz dielectric properties of liquid propylene glycol and polypropylene glycol