Machine learning prediction for classification of outcomes in local minimisation
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Das, R
Wales, DJ
Abstract
Machine learning schemes are employed to predict which local minimum will result from local energy minimisation of random starting configurations for a triatomic cluster. The input data consists of structural information at one or more of the configurations in optimisation sequences that converge to one of four distinct local minima. The ability to make reliable predictions, in terms of the energy or other properties of interest, could save significant computational resources in sampling procedures that involve systematic geometry optimisation. Results are compared for two energy minimisation schemes, and for neural network and quadratic functions of the inputs.
Description
Keywords
34 Chemical Sciences, 51 Physical Sciences
Journal Title
Chemical Physics Letters
Conference Name
Journal ISSN
0009-2614
1873-4448
1873-4448
Volume Title
667
Publisher
Elsevier