Portal de Periódicos da CAPES

The MLIP package: moment tensor potentials with MPI and active learning

2020; IOP Publishing; Volume: 2; Issue: 2 Linguagem: Inglês

10.1088/2632-2153/abc9fe

2632-2153

Ivan S. Novikov, Konstantin Gubaev, Evgeny V. Podryabinkin, Alexander V. Shapeev,

Nuclear Physics and Applications

The subject of this paper is the technology (the 'how') of constructing machine-learning interatomic potentials, rather than science (the 'what' and 'why') of atomistic simulations using machine-learning potentials. Namely, we illustrate how to construct moment tensor potentials using active learning as implemented in the MLIP package, focusing on the efficient ways to automatically sample configurations for the training set, how expanding the training set changes the error of predictions, how to set up ab initio calculations in a cost-effective manner, etc. The MLIP package (short for Machine-Learning Interatomic Potentials) is available at https://mlip.skoltech.ru/download/.