Accelerating crystal structure prediction and liquid electrolyte simulations using actively-trained moment tensor potentials

Nikita Rybin, Evgeny Moerman, Mikhail Polovinkin, Ivan Novikov, Alexander Shapeev

Keywords: machine-learning potentials, moment tensor potential, crystal structure prediction, electrolytes

TL;DR: In this work, we show how machine-learned Moment Tensor Potentials can be used as accurate interatomic potential models for applications such as crystal structure prediction and liquid electrolyte simulation.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 227