Efficient Autoencoder Pipeline for Discovering High Entropy Alloys with Molecular Dynamics Data

Amirhossein Naghdi Dorabati, Grzegorz Kaszuba, Stefanos Papanikolaou, Andrzej Jaszkiewicz, Piotr Sankowski

Submission Track: Full Paper

Submission Category: AI-Guided Design

Keywords: generative diffusion models, Multi-component materials, materials discovery

TL;DR: We use generative diffusion models and a local search algorithm to discover new multi-component alloys.

Abstract:

In this work, we utilize computationally efficient Molecular Dynamics (MD)
simulations to create a machine learning pipeline for discovery of crystalline multi-
component alloys. We employ high-quality interatomic potentials to create a
dataset of NiFeCr structures and apply Crystal Diffusion Variational Autoencoder
(CDVAE) to maximize their mechanical properties, i.e. bulk modulus. As part of
the experiment, we utilize local search coupled with classical interatomic potentials
to explore the local structure space and show that utilization of this procedure
greatly improves optimization capability of the neural model. We also expand the
model with an extra submodule, which attains 42% improvement on modeling the
crystalline phase of the structures. Ultimately, we verify the global stability of the
created structures with quantum mechanical calculation methods.

AI4Mat Journal Track: Yes

Submission Number: 31