MAISE package: Materials prediction accelerated with neural network potentials

ORAL

Abstract

Our recently released Module for Ab Initio Structure Evolution (MAISE) features an evolutionary algorithm for structure prediction and a neural network formalism for modeling interatomic interactions [1]. The open-source code has a simple interface for parallelized local optimization of crystalline or nanosized structures using a library of neural network or traditional classical potentials. Unique capabilities include a symbiotic evolutionary optimization of nanoparticles and a stratified construction of neural network models for multicomponent systems [2]. This presentation will review confirmed MAISE predictions and illustrate the acceleration of global structure searches with neural network models.

[1] https://github.com/maise-guide/maise
[2] S. Hajinazar, J. Shao, and A.N. Kolmogorov, Phys. Rev. B 95, 014114 (2017)

–

Presenters

  • Aleksey Kolmogorov

    Binghamton University, Department of Physics, Applied Physics and Astronomy, Binghamton University, Physics, Applied Physics and Astronomy, Binghamton University

Authors

  • Aleksey Kolmogorov

    Binghamton University, Department of Physics, Applied Physics and Astronomy, Binghamton University, Physics, Applied Physics and Astronomy, Binghamton University

  • Samad Hajinazar

    Binghamton University, Physics, Applied Physics and Astronomy, Binghamton University

  • Ernesto D. Sandoval

    Binghamton University, Physics, Applied Physics and Astronomy, Binghamton University