Data-driven Material Models for Atomistic Simulation

Abstract

The central approximation made in classical molecular dynamics simulation of materials is the interatomic potential used to calculate the forces on the atoms. Great effort and ingenuity is required to construct viable functional forms and find accurate parameterizations for potentials using traditional approaches. Machine-learning has emerged as an effective alternative approach to develop accurate and robust interatomic potentials. Starting with a very general model form, the potential is learned directly from a database of electronic structure calculations and therefore can be viewed as a multiscale link between quantum and classical atomistic simulations. Risk of inaccurate extrapolation exists outside the narrow range of time- and length-scales where the two methods can be directly compared. In this work, we use the Spectral Neighbor Analysis Potential (SNAP) and show how a fit can be produced with minimal interpolation errors which is also robust in extrapolating beyond training. To demonstrate the method, we have developed a new tungsten-beryllium potential suitable for the full range of binary compositions. Subsequently, large-scale molecular dynamics simulations were performed of high energy Be atom implantation onto the (001) surface of solid tungsten. The new machine learned W-Be potential generates a population of implantation structures consistent with quantum calculations of defect formation energies. A very shallow (<2nm) average Be implantation depth is predicted which may explain ITER diverter degradation in the presence of beryllium.

5 Figures, 2 Tables

References in corpus (16)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• The SIESTA method for ab initio order-N materials simulation
• Efficient index handling of multidimensional periodic boundary conditions
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Active learning of linearly parametrized interatomic potentials
• Machine learning a general purpose interatomic potential for silicon
• Hierarchical modeling of molecular energies using a deep neural network
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Quantum-Accurate Spectral Neighbor Analysis Potential Models for Ni-Mo Binary Alloys and FCC Metals
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Reflection and implantation of low energy helium with tungsten surfaces

Cited by in corpus (13)

• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Gaussian approximation potentials for body-centered-cubic transition metals
• Predicting electronic structures at any length scale with machine learning
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• Quantum-accurate magneto-elastic predictions with classical spin-lattice dynamics
• Machine Learned Interatomic Potential for Dispersion Strengthened Plasma Facing Components
• Training-free hyperparameter optimization of neural networks for electronic structures in matter
• Machine learning the electronic structure of matter across temperatures
• Embedding quantum statistical excitations in a classical force field
• Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo
• Nanoindentation simulations for copper and tungsten with adaptive-precision potentials