Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials

Johnathan D Georgaras, Akash Ramdas, Chung Hsuan Shan, Elena Halsted, Berwyn Berwyn, Tianshu Li, Felipe H da Jornada · 2026

Read Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials by Johnathan D Georgaras, Akash Ramdas, Chung Hsuan Shan, Elena Halsted, Berwyn Berwyn, Tianshu Li, Felipe H da Jornada (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13526791.txt.

Description

Georgaras and colleagues present a 2026 machine learning approach for predicting the atomic structure of twisted layered materials. When two thin sheets are stacked with a slight twist, they form moiré patterns, meaning large repeating patterns with unusual electronic behavior. Standard learned atom models struggle to capture these structures accurately.

Their split model treats forces inside each layer separately from forces between layers, and it improved energy and force predictions about tenfold over standard models. The team also built a new accuracy check based on how stacking arrangements are distributed across a whole moiré pattern, rather than on small test cells alone. Tests on hafnium and gallium sulfide bilayers showed the better structures also gave trustworthy electronic predictions.

Catalog record

CREATORJohnathan D Georgaras, Akash Ramdas, Chung Hsuan Shan, Elena Halsted, Berwyn Berwyn, Tianshu Li, Felipe H da Jornada
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE65 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13526791

Browse the full library · About the Tower of Babel