Volume 23, Issue 3
Deep Potential: A General Representation of a Many-Body Potential Energy Surface

Jiequn Han, Linfeng Zhang, Roberto Car & Weinan E

Commun. Comput. Phys., 23 (2018), pp. 629-639.

Published online: 2018-03

Preview Full PDF 35 2496
Export citation
  • Abstract

We present a simple, yet general, deep neural network representation of the potential energy surface for atomic and molecular systems. It is “first-principle” based, in the sense that no ad hoc approximations or empirical fitting functions are required. When tested on a wide variety of examples, it reproduces the original model within chemical accuracy. This brings us one step closer to carrying out molecular simulations with quantum mechanics accuracy at empirical potential computational cost.

  • Keywords

Potential energy surface, deep learning, molecular simulation.

  • AMS Subject Headings

81V55, 92E10, 68T99

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • References
  • Hide All
    View All

@Article{CiCP-23-629, author = {}, title = {Deep Potential: A General Representation of a Many-Body Potential Energy Surface}, journal = {Communications in Computational Physics}, year = {2018}, volume = {23}, number = {3}, pages = {629--639}, abstract = {

We present a simple, yet general, deep neural network representation of the potential energy surface for atomic and molecular systems. It is “first-principle” based, in the sense that no ad hoc approximations or empirical fitting functions are required. When tested on a wide variety of examples, it reproduces the original model within chemical accuracy. This brings us one step closer to carrying out molecular simulations with quantum mechanics accuracy at empirical potential computational cost.

}, issn = {1991-7120}, doi = {https://doi.org/10.4208/cicp.OA-2017-0213}, url = {http://global-sci.org/intro/article_detail/cicp/10541.html} }
Copy to clipboard
The citation has been copied to your clipboard