Skip to main content

Research Repository

Advanced Search

Active learning in Gaussian process interpolation of potential energy surfaces

Uteva, Elena; Graham, Richard S.; Wilkinson, Richard D.; Wheatley, Richard J.


Daphne Jackson Fellowship

Professor of Applied Mathematics

Professor of Applied Mathematics

Profile Image

Associate Professor & Reader in Theoretical Chemistry


© 2018 Author(s). Three active learning schemes are used to generate training data for Gaussian process interpolation of intermolecular potential energy surfaces. These schemes aim to achieve the lowest predictive error using the fewest points and therefore act as an alternative to the status quo methods involving grid-based sampling or space-filling designs like Latin hypercubes (LHC). Results are presented for three molecular systems: CO2-Ne, CO2-H2, and Ar3. For each system, two of the active learning schemes proposed notably outperform LHC designs of comparable size, and in two of the systems, produce an error value an order of magnitude lower than the one produced by the LHC method. The procedures can be used to select a subset of points from a large pre-existing data set, to select points to generate data de novo, or to supplement an existing data set to improve accuracy.


Uteva, E., Graham, R. S., Wilkinson, R. D., & Wheatley, R. J. (2018). Active learning in Gaussian process interpolation of potential energy surfaces. Journal of Chemical Physics, 149(17), 174114.

Journal Article Type Article
Acceptance Date Oct 19, 2018
Online Publication Date Nov 7, 2018
Publication Date Nov 7, 2018
Deposit Date Oct 25, 2018
Publicly Available Date Oct 25, 2018
Journal Journal of Chemical Physics
Print ISSN 0021-9606
Electronic ISSN 1089-7690
Publisher AIP Publishing
Peer Reviewed Peer Reviewed
Volume 149
Issue 17
Article Number 174114
Pages 174114
Public URL
Publisher URL
Additional Information Received: 2018-08-12; Accepted: 2018-10-19; Published: 2018-11-07


You might also like

Downloadable Citations