Incorporating long-range physics in atomic-scale machine learning
Top Cited Papers
- 26 November 2019
- journal article
- conference paper
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 151 (20) , 204105
Abstract
The most successful and popular machine learning models of atomic-scale properties derive their transferability from a locality ansatz. The properties of a large molecule or a bulk material are written as a sum over contributions that depend on the configurations within finite atom-centered environments. The obvious downside of this approach is that it cannot capture nonlocal, nonadditive effects such as those arising due to long-range electrostatics or quantum interference. We propose a solution to this problem by introducing nonlocal representations of the system, which are remapped as feature vectors that are defined locally and are equivariant in O(3). We consider, in particular, one form that has the same asymptotic behavior as the electrostatic potential. We demonstrate that this framework can capture nonlocal, long-range physics by building a model for the electrostatic energy of randomly distributed point-charges, for the unrelaxed binding curves of charged organic molecular dimers, and for the electronic dielectric response of liquid water. By combining a representation of the system that is sensitive to long-range correlations with the transferability of an atom-centered additive model, this method outperforms current state-of-the-art machine-learning schemes and provides a conceptual framework to incorporate nonlocal physics into atomistic machine learning.Keywords
All Related Versions
Funding Information
- MPG-EPFL Centre for Molecular Nanoscience
- H2020 European Research Council (677013-HBMAP)
- National Center of Competence in Research Materials’ Revolution: Computational Design and Discovery of Novel Materials
This publication has 42 references indexed in Scilit:
- Atomistic Modeling of the Electrode–Electrolyte Interface in Li-Ion Energy Storage Systems: Electrolyte StructuringThe Journal of Physical Chemistry C, 2013
- High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxidePhysical Review B, 2011
- Long range interactions in nanoscale scienceReviews of Modern Physics, 2010
- Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the ElectronsPhysical Review Letters, 2010
- Electrical polarization and orbital magnetization: the modern theoriesJournal of Physics: Condensed Matter, 2010
- Ab initio molecular simulations with numeric atom-centered orbitalsComputer Physics Communications, 2009
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995
- Macroscopic polarization in crystalline dielectrics: the geometric phase approachReviews of Modern Physics, 1994
- Die Berechnung optischer und elektrostatischer GitterpotentialeAnnalen der Physik, 1921