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 - <p style="text-align: justify;">We present a simple, yet general, deep neural network representation of the
potential energy surface for atomic and molecular systems. It is &quot;first-principle&quot; 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.</p>