Active learning accelerates ab initio molecular dynamics on reactive energy surfaces

Active learning accelerates ab initio molecular dynamics on reactive energy surfaces

© 2020 Elsevier Inc. Through autonomous data acquisition and machine learning, we demonstrate that our neural-network-based reactive force fields allow us to study the dynamical effects of several pericyclic reactions and to predict solvent effects on periselectivity. Our method is over 2,000 times...

Full description

Bibliographic Details
Main Authors: Ang, Shi Jun (Author), Wang, Wujie (Author), Schwalbe-Koda, Daniel (Author), Axelrod, Simon (Author), Gómez-Bombarelli, Rafael (Author)
Format: Article
Language:English
Published: Elsevier BV, 2022-05-12T19:25:22Z.
Subjects:
Article
Online Access:Get fulltext
Description
Summary:© 2020 Elsevier Inc. Through autonomous data acquisition and machine learning, we demonstrate that our neural-network-based reactive force fields allow us to study the dynamical effects of several pericyclic reactions and to predict solvent effects on periselectivity. Our method is over 2,000 times faster than the traditional density functional theory approach, and its accuracy matches the parent quantum mechanical method. Given the efficiency of our machine learning framework, we envisage its applicability in studying larger reactive systems with a higher complexity.

Similar Items