Skip to main content

Deep Potential: A General Representation of a Many-Body Potential Energy Surface

Author(s): Han, Jiequn; Zhang, Linfeng; Car, Roberto; E, Weinan

To refer to this page use:
Abstract: We present a simple, yet general, end-to-end deep neural network representation of the potential energy surface for atomic and molecular systems. This methodology, which we call Deep Potential, is "first-principle" based, in the sense that no ad hoc approximations or empirical fitting functions are required. The neural network structure naturally respects the underlying symmetries of the systems. When tested on a wide variety of examples, Deep Potential is able to reproduce the original model, whether empirical or quantum mechanics based, within chemical accuracy. The computational cost of this new model is not substantially larger than that of empirical force fields. In addition, the method has promising scalability properties. This brings us one step closer to being able to carry out molecular simulations with accuracy comparable to that of quantum mechanics models and computational cost comparable to that of empirical potentials.
Publication Date: 1-Jan-2018
Citation: Han, Jiequn, Zhang, Linfeng, Car, Roberto, E, Weinan. (2018). Deep Potential: A General Representation of a Many-Body Potential Energy Surface. Communications in Computational Physics, 23 (3), 10.4208/cicp.oa-2017-0213
DOI: doi:10.4208/cicp.oa-2017-0213
ISSN: 1815-2406
Type of Material: Journal Article
Journal/Proceeding Title: Communications in Computational Physics
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.