Automated discovery of a robust interatomic potential for aluminum

Abstract

Accuracy of molecular dynamics simulations depends crucially on the interatomic potential used to generate forces. The gold standard would be first-principles quantum mechanics (QM) calculations, but these become prohibitively expensive at large simulation scales. Machine learning (ML) based potentials aim for faithful emulation of QM at drastically reduced computational cost. The accuracy and robustness of an ML potential is primarily limited by the quality and diversity of the training dataset. Using the principles of active learning (AL), we present a highly automated approach to dataset construction. The strategy is to use the ML potential under development to sample new atomic configurations and, whenever a configuration is reached for which the ML uncertainty is sufficiently large, collect new QM data. Here, we seek to push the limits of automation, removing as much expert knowledge from the AL process as possible. All sampling is performed using MD simulations starting from an initially disordered configuration, and undergoing non-equilibrium dynamics as driven by time-varying applied temperatures. We demonstrate this approach by building an ML potential for aluminum (ANI-Al). After many AL iterations, ANI-Al teaches itself to predict properties like the radial distribution function in melt, liquid-solid coexistence curve, and crystal properties such as defect energies and barriers. To demonstrate transferability, we perform a 1.3M atom shock simulation, and show that ANI-Al predictions agree very well with DFT calculations on local atomic environments sampled from the nonequilibrium dynamics. Interestingly, the configurations appearing in shock appear to have been well sampled in the AL training dataset, in a way that we illustrate visually.

References in corpus (22)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• 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
• Less is more: sampling chemical space with active learning
• Interatomic potentials for atomistic simulations of the Ti-Al system
• Active learning of linearly parametrized interatomic potentials
• Machine-learning based interatomic potential for amorphous carbon
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Physically-informed artificial neural networks for atomistic modeling of materials
• Hierarchical modeling of molecular energies using a deep neural network
• De novo exploration and self-guided learning of potential-energy surfaces
• Data-driven learning of total and local energies in elemental boron
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Machine learning of molecular properties: locality and active learning
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• Bulk Aluminum at High Pressure: A First-Principles Study
• Machine learning for molecular dynamics with strongly correlated electrons

Cited by in corpus (13)

• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• Systematic Atomic Structure Datasets for Machine Learning Potentials: Application to Defects in Magnesium
• Deep Coarse-grained Potentials via Relative Entropy Minimization
• Modeling nanoconfinement effects using active learning
• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations
• Data efficiency and extrapolation trends in neural network interatomic potentials
• A "Magnetic" Machine Learning Interatomic Potential for Nickel
• Machine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles
• Supervised and Unsupervised Machine Learning of Structural Phases of Polymers Adsorbed to Nanowires
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• Nanoindentation simulations for copper and tungsten with adaptive-precision potentials
• Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure