Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials

Abstract

The universal mathematical form of machine-learning potentials (MLPs) shifts the core of development of interatomic potentials to collecting proper training data. Ideally, the training set should encompass diverse local atomic environments but the conventional approach is prone to sampling similar configurations repeatedly, mainly due to the Boltzmann statistics. As such, practitioners handpick a large pool of distinct configurations manually, stretching the development period significantly. Herein, we suggest a novel sampling method optimized for gathering diverse yet relevant configurations semi-automatically. This is achieved by applying the metadynamics with the descriptor for the local atomic environment as a collective variable. As a result, the simulation is automatically steered toward unvisited local environment space such that each atom experiences diverse chemical environments without redundancy. We apply the proposed metadynamics sampling to H:Pt(111), GeTe, and Si systems. Throughout the examples, a small number of metadynamics trajectories can provide reference structures necessary for training high-fidelity MLPs. By proposing a semi-automatic sampling method tuned for MLPs, the present work paves the way to wider applications of MLPs to many challenging applications.

References in corpus (21)

• Escaping free-energy minima
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Improved initial guess for minimum energy path calculations
• Metadynamics with adaptive Gaussians
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• An Accurate and Transferable Machine Learning Potential for Carbon
• A neural network interatomic potential for the phase change material GeTe
• 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
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• Energetics and Vibrational States for Hydrogen on Pt(111)
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Breakdown of Stokes-Einstein relation in the supercooled liquid state of phase change materials
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Atomic energy mapping of neural network potential
• Training machine-learning potentials for crystal structure prediction using disordered structures

Cited by in corpus (4)

• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Accelerated identification of equilibrium structures of multicomponent inorganic crystals using machine learning potentials
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials