edoc

A reactive, scalable, and transferable model for molecular energies from a neural network approach based on local information

Unke, Oliver T. and Meuwly, Markus. (2018) A reactive, scalable, and transferable model for molecular energies from a neural network approach based on local information. Journal of Chemical Physics, 148 (24). p. 241708.

[img] PDF - Published Version
2233Kb

Official URL: https://edoc.unibas.ch/94219/

Downloads: Statistics Overview

Abstract

Despite the ever-increasing computer power, accurate ab initio calculations for large systems (thousands to millions of atoms) remain infeasible. Instead, approximate empirical energy functions are used. Most current approaches are either transferable between different chemical systems, but not particularly accurate, or they are fine-tuned to a specific application. In this work, a data-driven method to construct a potential energy surface based on neural networks is presented. Since the total energy is decomposed into local atomic contributions, the evaluation is easily parallelizable and scales linearly with system size. With prediction errors below 0.5 kcal mol −1 for both unknown molecules and configurations, the method is accurate across chemical and configurational space, which is demonstrated by applying it to datasets from nonreactive and reactive molecular dynamics simulations and a diverse database of equilibrium structures. The possibility to use small molecules as reference data to predict larger structures is also explored. Since the descriptor only uses local information, high-level ab initio methods, which are computationally too expensive for large molecules, become feasible for generating the necessary reference data used to train the neural network.
Faculties and Departments:05 Faculty of Science > Departement Chemie > Chemie > Physikalische Chemie (Meuwly)
UniBasel Contributors:Meuwly, Markus
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:AIP Publishing
ISSN:0021-9606
e-ISSN:1089-7690
Note:Publication type according to Uni Basel Research Database: Journal article
Language:English
Identification Number:
edoc DOI:
Last Modified:03 Apr 2023 11:38
Deposited On:03 Apr 2023 07:17

Repository Staff Only: item control page