Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials

Gao, Ang; Remsing, Richard C.

doi:10.48550/arxiv.2109.13074

Cited by 1 publication

(2 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these cases, the assumption made here that the environmental dependence of the Wannier centroids is not affected by size should be revisited, and one should envision a self-consistent condition for the centroids under the action of the long-range electrostatic field along lines similar to those developed in Ref. 53 .…”

Section: Discussionmentioning

confidence: 93%

“…While preparing this manuscript, we became aware of a recent preprint by Gao and Remsing 53 , in which the electronic structure information encoded in the Wannier centers is used to construct a ML model of the PES including long-range electrostatics. This model, called self-consistent field neural network (SCFNN), differs from DPLR because the separation between short-and long-range contributions is not done in the way in which the training data are handled, but in the way in which they are generated.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A deep potential model with long-range electrostatic interactions

Zhang,

Wang,

Muniz

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning models for the potential energy of multi-atomic systems, such as the deep potential (DP) model, make possible molecular simulations with the accuracy of quantum mechanical density functional theory, at a cost only moderately higher than that of empirical force fields. However, the majority of these models lack explicit long-range interactions and fail to describe properties that derive from the Coulombic tail of the forces. To overcome this limitation we extend the DP model by approximating the long-range electrostatic interaction between ions (nu-clei+core electrons) and valence electrons with that of distributions of spherical Gaussian charges located at ionic and electronic sites. The latter are rigorously defined in terms of the centers of the maximally localized Wannier distributions, whose dependence on the local atomic environment is modeled accurately by a deep neural network. In the deep potential long-range (DPLR) model, the electrostatic energy of the Gaussian charge system is added to short-range interactions that are represented as in the standard DP model. The resulting potential energy surface is smooth and possesses analytical forces and virial. Missing effects in the standard DP scheme are recovered, improving on accuracy and predictive power. By including long-range electrostatics, DPLR correctly extrapolates to large systems the potential energy surface learned from quantum mechanical calculations on smaller systems. We illustrate the approach with three examples, the potential energy profile of the water dimer, the free energy of interaction of a water molecule with a liquid water slab, and the phonon dispersion curves of the NaCl crystal.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%