Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning
Name
s41524-022-00736-4.pdf
Description
Published version
Size
21.75 MB
Format
Adobe PDF
Checksum (MD5)
8b4dd702dcafb9d161fa76db8c11d861
Author(s)
Damewood, James
Schwalbe-Koda, Daniel
Gómez-Bombarelli, Rafael
Date Issued
December 2022
Journal
npj Computational Materials
Publisher
Springer Science and Business Media LLC
Citation
Damewood, James, Schwalbe-Koda, Daniel and Gómez-Bombarelli, Rafael. 2022. "Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning." npj Computational Materials, 8 (1).
Version
Final published version
Abstract
AbstractCalculating thermodynamic potentials and observables efficiently and accurately is key for the application of statistical mechanics simulations to materials science. However, naive Monte Carlo approaches, on which such calculations are often dependent, struggle to scale to complex materials in many state-of-the-art disciplines such as the design of high entropy alloys or multi-component catalysts. To address this issue, we adapt sampling tools built upon machine learning-based generative modeling to the materials space by transforming them into the semi-grand canonical ensemble. Furthermore, we show that the resulting models are transferable across wide ranges of thermodynamic conditions and can be implemented with any internal energy model U, allowing integration into many existing materials workflows. We demonstrate the applicability of this approach to the simulation of benchmark systems (AgPd, CuAu) that exhibit diverse thermodynamic behavior in their phase diagrams. Finally, we discuss remaining challenges in model development and promising research directions for future improvements.
MIT Department
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Terms of Use
Creative Commons Attribution 4.0 International License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/s41524-022-00736-4
