Work

Machine Learning Lattice Parameters of M2AX Phases

Year: 2025

Type: article

Abstract: High Resolution Image Download MS PowerPoint Slide MAX phases, with a general composition of M n +1 AX n, are layered materials with hexagonal symmetry that have increasingly captivated a lot of attention because of their unique way of combining ceramic and metallic properties into a homogeneous bulk material. We developed a machine learning approach to predict the lattice parameters a and c of M 2 AX phases. This approach consists of training an ensemble model on a data set collecting all experimentally synthesized M 2 AX phases’ lattice parameters. Our approach combines a data augmentation scheme with state-of-the-art regression models and hyperparameter optimization tools. We tested our model on newly synthesized compositionally complex high-entropy M 2 AX phases with positive results. Finally, we also show that our machine learning predictions of lattice parameters are useful as initial values for variable-cell relaxations of M 2 AX structures with the density functional theory.

Source: The Journal of Physical Chemistry C

DOI: 10.1021/acs.jpcc.4c08730

Authors: Cesare Roncaglia, Fábio Lopes, Nick Goossens, Michael Stuer, Daniele Passerone

Institution: Swiss Federal Laboratories for Materials Science and Technology

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,500

Funder: National Supercomputing Center, Korea Institute of Science and Technology Information