Permutation invariant polynomial neural network approach to fitting potential energy surfaces. IV. Coupled diabatic potential energy matrices

Changjian Xie, Xiaolei Zhu, David R. Yarkony, Hua Guo

The Journal of Chemical Physics 2018 article cited by 90

Source Open-access PDF More in Physics & Astronomy

importance 4/10 solved Advanced Chemical Physics Studies computational chemistry stage: research

Problem

Accurately representing coupled diabatic potential energy matrices of molecules, needed to model non-adiabatic photodissociation dynamics.

Why it matters

High-fidelity potential energy matrices underpin reliable simulations of molecular photochemical processes.

What the AI did

A permutation invariant polynomial-neural network (PIP-NN) machine learning method, extended with a symmetry multiplicative factor, fitted diabatic PEM elements with high fidelity.

Results

Small fitting errors; reproduced absorption spectra and product branching ratios for H2O(X̃/B̃) and NH3(X̃/Ã) photodissociation.

Impact

Evidence supports accurate ML-based fitting of diabatic PEMs for the demonstrated molecular systems.

Record

Venue	The Journal of Chemical Physics
Published	2018
Work type	article
Authors	Changjian Xie, Xiaolei Zhu, David R. Yarkony, Hua Guo
Citations	90 (OpenAlex, at import time)
References	82
Model or method	PIP-NN (permutation invariant polynomial-neural network)
Organization	not stated in source
Primary source	https://doi.org/10.1063/1.5054310
Open access	green
Keywords	neural networks, potential energy surfaces, diabatic matrices, photodissociation, machine learning

Importance rating

4 / 10

real but narrower advance

High-fidelity diabatic PEM fitting underpins reliable photochemical simulations, demonstrated on H2O and NH3; a real but narrow methodological advance in computational chemistry.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7