Modeling the ultrafast
photoinduced dynamics and reactivity of
adsorbates on metals requires including the effect of the laser-excited
electrons and, in many cases, also the effect of the highly excited
surface lattice. Although the recent ab initio molecular dynamics
with electronic friction and thermostats, (
T
e
,
T
l
)-AIMDEF [
Alducin
M.
Alducin
M.
246802
31922860
Phys. Rev. Lett.
2019
123
, enables such complex
modeling, its computational cost may limit its applicability. Here,
we use the new embedded atom neural network (EANN) method [
Zhang
Y.
Zhang
Y.
31397157
J. Phys. Chem. Lett.
2019
10
4962
] to develop an accurate and extremely
complex potential energy surface (PES) that allows us a detailed and
reliable description of the photoinduced desorption of CO from the
Pd(111) surface with a coverage of 0.75 monolayer. Molecular dynamics
simulations performed on this EANN-PES reproduce the (
T
e
,
T
l
)-AIMDEF results with
a remarkable level of accuracy. This demonstrates the outstanding
performance of the obtained EANN-PES that is able to reproduce available
density functional theory (DFT) data for an extensive range of surface
temperatures (90–1000 K); a large number of degrees of freedom,
those corresponding to six CO adsorbates and 24 moving surface atoms;
and the varying CO coverage caused by the abundant desorption events.