full
search.png

Search

close.png

Cancel

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

Jiequn Han, Linfeng Zhang, Roberto Car & Weinan E

DOI: 10.4208/cicp.OA-2017-0213

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

Published online: 2018-03

[An open-access article; the PDF is free to any online user.]

Preview Full PDF 5463 84574

Cited by

google scholar semantic scholar
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
  • BibTex
  • RIS
  • TXT
@Article{CiCP-23-629, author = {Jiequn Han, Linfeng Zhang, Roberto Car and Weinan E}, 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} }
TY - JOUR T1 - Deep Potential: A General Representation of a Many-Body Potential Energy Surface AU - Jiequn Han, Linfeng Zhang, Roberto Car & Weinan E JO - Communications in Computational Physics VL - 3 SP - 629 EP - 639 PY - 2018 DA - 2018/03 SN - 23 DO - http://doi.org/10.4208/cicp.OA-2017-0213 UR - https://global-sci.org/intro/article_detail/cicp/10541.html KW - Potential energy surface, deep learning, molecular simulation. AB -

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.

Jiequn Han, Linfeng Zhang, Roberto Car and Weinan E. (2018). Deep Potential: A General Representation of a Many-Body Potential Energy Surface. Communications in Computational Physics. 23 (3). 629-639. doi:10.4208/cicp.OA-2017-0213
Copy to clipboard
BibteX RIS TXT
The citation has been copied to your clipboard