Document Type
Article
Publication Date
11-21-2025
Department
Department of Mechanical and Aerospace Engineering
Abstract
We propose machine learning (ML) models to predict the electron density — the fundamental unknown of a material’s ground state — across the composition space of concentrated alloys. From this, other physical properties can be inferred, enabling accelerated exploration. A significant challenge is that the number of descriptors and sampled compositions required for accurate prediction grows rapidly with species. To address this, we employ Bayesian Active Learning (AL), which minimizes training data requirements by leveraging uncertainty quantification capabilities of Bayesian Neural Networks. Compared to the strategic tessellation of the composition space, Bayesian-AL reduces the number of training data points by a factor of 2.5 for ternary (SiGeSn) and 1.7 for quaternary (CrFeCoNi) systems. We also introduce easy-to-optimize, body-attached-frame descriptors, which respect physical symmetries while keeping descriptor-vector size nearly constant as alloy complexity increases. Our ML models demonstrate high accuracy and generalizability in predicting both electron density and energy across composition space.
Publication Title
Npj Computational Materials
Recommended Citation
Pathrudkar, S.,
Taylor, S.,
Keripale, A.,
Gangan, A.,
Thiagarajan, P.,
Agarwal, S.,
Marian, J.,
Ghosh, S.,
&
Banerjee, A.
(2025).
Electronic structure prediction of medium and high entropy alloys across composition space.
Npj Computational Materials,
11(1).
http://doi.org/10.1038/s41524-025-01856-3
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p2/2212
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Version
Publisher's PDF
Publisher's Statement
© The Author(s) 2025. Publisher’s version of record: https://doi.org/10.1038/s41524-025-01856-3