Towards exact molecular dynamics simulations with machine-learned force fields

By Stefan Chmiela, Huziel E. Sauceda, K. Müller, Alexandre Tkatchenko. 2018

743 citations recorded by the source corpus.

Molecular dynamics (MD) simulations employing classical force fields constitute the cornerstone of contemporary atomistic modeling in chemistry, biology, and materials science. However, the predictive power of these simulations is only as good as the underlying interatomic potential. Classical potentials often fail to faithfully capture key quantum effects in molecules and materials. Here we enable the direct construction of flexible molecular force fields from high-level ab initio calculations by incorporating spatial and temporal physical symmetries into a gradient-domain machine learning (sGDML) model in an automatic data-driven way. The developed sGDML approach faithfully reproduces global force fields at quantum-chemical CCSD(T) level of accuracy and allows converged molecular dynamics simulations with fully quantized electrons and nuclei. We present MD simulations, for flexible molecules with up to a few dozen atoms and provide insights into the dynamical behavior of these molecules. Our approach provides the key missing ingredient for achieving spectroscopic accuracy in molecular simulations. Simultaneous accurate and efficient prediction of molecular properties relies on combined quantum mechanics and machine learning approaches. Here the authors develop a flexible machine-learning force-field with high-level accuracy for molecular dynamics simulations.

Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry, Computational Chemistry & Drug Discovery, AI for Physical Sciences

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

1. Yuri Mishin
2. Rohit Batra
3. G. P. P. Pun
4. Rampi Ramprasad
5. K. Müller
6. Grgoire Montavon
7. Wojciech Samek
8. Shyue Ping Ong

In Materials Chemistry

1. Tess E. Smidt
2. Yuri Mishin
3. Shyue Ping Ong
4. Chi Chen
5. Mario Geiger
6. Rohit Batra
7. Rampi Ramprasad
8. Simon L. Batzner

In Computational Chemistry & Drug Discovery

1. Tess E. Smidt
2. Mario Geiger
3. Shyue Ping Ong
4. Chi Chen
5. Grgoire Montavon
6. Rampi Ramprasad
7. Stephan Günnemann
8. Johannes Klicpera

In AI for Physical Sciences

1. Tess E. Smidt
2. Wojciech Samek
3. Grgoire Montavon
4. Stephan Günnemann
5. Johannes Klicpera
6. Rampi Ramprasad
7. Shyue Ping Ong
8. Chi Chen

Citations in the corpus

• Directional Message Passing for Molecular Graphs (2020, background): “, 2019), and symmetrized gradient-domain machine learning (sGDML) (Chmiela et al., 2018).”
• Unmasking Clever Hans predictors and assessing what machines really learn (2019, background): “Commonly discussed ingredients to make learning machines act more human-like are, e.g. compositionality, causality, learning to learn 39 – 41 , and also an ef fi cient usage of prior knowledge or invariance structure (see e.g. 44 ).”
• Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning (2019, background): “Previous studies have trained on high-quality QM data for small molecules at equilibrium conformations 46,47 and for non-equilibrium conformations of a single molecule 48 .”