Repository logo

Hyperactive learning for data-driven interatomic potentials

Published version

Repository DOI

Change log


van der Oord, C 
Sachs, M 
Kovács, DP 
Ortner, C 


jats:titleAbstract</jats:title>jats:pData-driven interatomic potentials have emerged as a powerful tool for approximating ab initio potential energy surfaces. The most time-consuming step in creating these interatomic potentials is typically the generation of a suitable training database. To aid this process hyperactive learning (HAL), an accelerated active learning scheme, is presented as a method for rapid automated training database assembly. HAL adds a biasing term to a physically motivated sampler (e.g. molecular dynamics) driving atomic structures towards uncertainty in turn generating unseen or valuable training configurations. The proposed HAL framework is used to develop atomic cluster expansion (ACE) interatomic potentials for the AlSi10 alloy and polyethylene glycol (PEG) polymer starting from roughly a dozen initial configurations. The HAL generated ACE potentials are shown to be able to determine macroscopic properties, such as melting temperature and density, with close to experimental accuracy.</jats:p>


Funder: Dassault Systèmes


40 Engineering, 34 Chemical Sciences, 3406 Physical Chemistry

Journal Title

npj Computational Materials

Conference Name

Journal ISSN


Volume Title



Springer Science and Business Media LLC
Engineering and Physical Sciences Research Council (1971218)
Engineering and Physical Sciences Research Council (EP/K014560/1)