Permutation invariant potential energy surfaces for polyatomic reactions using atomistic neural networks

被引：50

作者：

Kolb, Brian ^{[1
,2
]}

Zhao, Bin ^{[1
]}

Li, Jun ^{[3
]}

Jiang, Bin ^{[4
]}

Guo, Hua ^{[1
]}

机构：

[1] Univ New Mexico, Dept Chem & Chem Biol, Albuquerque, NM 87131 USA

[2] MIT, Dept Mech Engn, Cambridge, MA 02139 USA

[3] Chongqing Univ, Sch Chem & Chem Engn, Chongqing 401331, Peoples R China

[4] Univ Sci & Technol China, Dept Chem Phys, Hefei 230026, Anhui, Peoples R China

来源：

JOURNAL OF CHEMICAL PHYSICS | 2016年 / 144卷 / 22期

基金：

中国国家自然科学基金; 美国国家科学基金会;

关键词：

QUANTUM DYNAMICS; WATER CLUSTERS; SIMULATIONS; MOLECULES; PROTEINS; KINETICS; SPECTRUM;

D O I：

10.1063/1.4953560

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

The applicability and accuracy of the Behler-Parrinello atomistic neural network method for fitting reactive potential energy surfaces is critically examined in three systems, H + H-2 -> H-2 + H, H + H2O -> H-2 + OH, and H + CH4 -> H-2 + CH3. A pragmatic Monte Carlo method is proposed to make efficient choice of the atom-centered mapping functions. The accuracy of the potential energy surfaces is not only tested by fitting errors but also validated by direct comparison in dynamically important regions and by quantum scattering calculations. Our results suggest this method is both accurate and efficient in representing multidimensional potential energy surfaces even when dissociation continua are involved. Published by AIP Publishing.

引用

页数：7

共 50 条

[21] POTENTIAL-ENERGY SURFACES FOR POLYATOMIC REACTION DYNAMICS
TRUHLAR, DG
STECKLER, R
GORDON, MS
CHEMICAL REVIEWS, 1987, 87 (01) : 217 - 236
[22] Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
Koner, Debasish
Meuwly, Markus
JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2020, 16 (09) : 5474 - 5484
[23] The fitting of potential energy surfaces using neural networks. Application to the study of the photodissociation processes
Prudente, FV
Neto, JJS
CHEMICAL PHYSICS LETTERS, 1998, 287 (5-6) : 585 - 589
[24] INTERSECTION OF POTENTIAL-ENERGY SURFACES IN POLYATOMIC-MOLECULES
LONGUETHIGGINS, HC
PROCEEDINGS OF THE ROYAL SOCIETY OF LONDON SERIES A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 1975, 344 (1637): : 147 - 156
[25] On the representation of potential energy surfaces of polyatomic molecules in normal coordinates
Carter, S
Handy, NC
CHEMICAL PHYSICS LETTERS, 2002, 352 (1-2) : 1 - 7
[26] Using neural networks to represent potential surfaces as sums of products
Manzhos, Sergei
Carrington, Tucker, Jr.
JOURNAL OF CHEMICAL PHYSICS, 2006, 125 (19):
[27] Quantification using permutation-invariant networks based on histograms
Olaya Pérez-Mon
Alejandro Moreo
Juan José del Coz
Pablo González
Neural Computing and Applications, 2025, 37 (5) : 3505 - 3520
[28] GENERAL POTENTIAL SURFACES AND NEURAL NETWORKS
DEMBO, A
ZEITOUNI, O
PHYSICAL REVIEW A, 1988, 37 (06) : 2134 - 2143
[29] The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning
Tang, Yujin
Ha, David
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
[30] Fitting potential energy surfaces to sum-of-products form with neural networks using exponential neurons
Brown, Alex
Pradhan, E.
JOURNAL OF THEORETICAL & COMPUTATIONAL CHEMISTRY, 2017, 16 (05):

← 1 2 3 4 5 →