De novo exploration and self-guided learning of potential-energy surfaces
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Abstract
Interatomic potential models based on machine learning (ML) are rapidly developing as tools for materials simulations. However, because of their flexibility, they require large fitting databases that are normally created with substantial manual selection and tuning of reference configurations. Here, we show that ML potentials can be built in a largely automated fashion, exploring and fitting potential-energy surfaces from the beginning (de novo) within one and the same protocol. The key enabling step is the use of a configuration-averaged kernel metric that allows one to select the few most relevant structures at each step. The resulting potentials are accurate and robust for the wide range of configurations that occur during structure searching, despite only requiring a relatively small number of single-point DFT calculations on small unit cells. We apply the method to materials with diverse chemical nature and coordination environments, marking a milestone toward the more routine application of ML potentials in physics, chemistry, and materials science.
Description
Keywords
Journal Title
Conference Name
Journal ISSN
2057-3960
Volume Title
Publisher
Publisher DOI
Rights
Sponsorship
Leverhulme Trust (ECF-2017-278)
Engineering and Physical Sciences Research Council (EP/L014742/1)
Engineering and Physical Sciences Research Council (EP/P022596/1)