Machine-Learning Interatomic Potentials for Materials Science

By Yuri Mishin. Social Science Research Network, 2021

341 citations recorded by the source corpus.

Large-scale atomistic computer simulations of materials rely on interatomic potentials providing computationally efficient predictions of energy and Newtonian forces. Traditional potentials have served in this capacity for over three decades. Recently, a new class of potentials has emerged, which is based on a radically different philosophy. The new potentials are constructed using machine-learning (ML) methods and a massive reference database generated by quantum-mechanical calculations. While the traditional potentials are derived from physical insights into the nature of chemical bonding, the ML potentials utilize a high-dimensional mathematical regression to interpolate between the reference energies. We review the current status of the interatomic potential field, comparing the strengths and weaknesses of the traditional and ML potentials. A third class of potentials is introduced, in which an ML model is coupled with a physics-based potential to improve the transferability to unknown atomic environments. The discussion is focused on potentials intended for materials science applications. Possible future directions in this field are outlined.

Subfields: Computational Theory and Mathematics, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/f2394f1565acc1d0da3de5b16e25ecd21d9a4fd3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Han Wang
2. Linfeng Zhang
3. W. E
4. Jesús María Sanz-Serna
5. Eric Vanden-Eijnden
6. E. Weinan

In Materials Chemistry

1. Linfeng Zhang
2. David J. Srolovitz
3. W. E
4. T. Wen
5. Han Wang
6. Risi Kondor
7. Nicholas K.-R. Kevlahan

Citations in the corpus

• Deep Potentials for Materials Science (2022, background): “The concept of “ML potentials guided by the physics in the empirical potentials” is also an exciting area; e.g., see the recent work of Mishin, et al. [29, 214] .”