Gaussian Process Regression for Materials and Molecules

By Volker L. Deringer, A. P. Bart'ok, Noam Bernstein, David M. Wilkins, Michele Ceriotti, Gábor Csányi. Chemical Reviews, 2021

1,025 citations recorded by the source corpus.

We provide an introduction to Gaussian process regression (GPR) machine-learning methods in computational materials science and chemistry. The focus of the present review is on the regression of atomistic properties: in particular, on the construction of interatomic potentials, or force fields, in the Gaussian Approximation Potential (GAP) framework; beyond this, we also discuss the fitting of arbitrary scalar, vectorial, and tensorial quantities. Methodological aspects of reference data generation, representation, and regression, as well as the question of how a data-driven model may be validated, are reviewed and critically discussed. A survey of applications to a variety of research questions in chemistry and materials science illustrates the rapid growth in the field. A vision is outlined for the development of the methodology in the years to come.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/b8c0e3cf66357d1a297515c6fe18a3805507759d

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. Ilyes Batatia
2. Christoph Ortner
3. Han Wang
4. Linfeng Zhang
5. D. Kov'acs
6. W. E
7. Gábor Csányi
8. Gregor N. C. Simm

In Materials Chemistry

1. Linfeng Zhang
2. Han Wang
3. David J. Srolovitz
4. W. E
5. T. Wen
6. Ilyes Batatia
7. Christoph Ortner
8. D. Kov'acs

In Molecular Biology

1. Han Wang
2. Linfeng Zhang
3. Ilyes Batatia
4. Christoph Ortner
5. D. Kov'acs
6. W. E
7. Gábor Csányi
8. Gregor N. C. Simm

Citations in the corpus

• Deep Potentials for Materials Science (2022, background): “Apart from NNP and SchNet, several other types of ML potentials were introduced; Gaussian approximation potentials (GAP) [30– 33], moment tensor potentials (MTP) [34–36], spectral neighbour analysis potentials (SNAP) [37–39], gradient-domain machine learning (GDML) [40, 41], et al [42].”
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields (2022, background): “Models that are significantly faster to train are better suited for applications of active learning, which is typically how databases for materials science applications are built [13–15].”
• A foundation model for atomistic materials chemistry. (2023, neutral): “Yet , such custom-trained potentials require significant computational and human effort for the generation of DFT reference data, as well as model training and validation ( 18 ).”