Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials
- 1Department of Materials Science and Engineering, Stanford University, Stanford, CA, USA
- 2Department of Materials Science and Engineering, Stanford University, Stanford, CA, USA. [email protected]
- 3Stanford Institute for Materials and Energy Sciences, SLAC National Accelerator Laboratory, Menlo Park, CA, USA. [email protected]
Abstract
Twisted layered van der Waals materials often exhibit unique electronic and optical properties absent in their non-twisted counterparts. Unfortunately, predicting such properties is hindered by the difficulty in determining the atomic structure in materials displaying large moiré domains. Here, we introduce a split machine-learned interatomic potential (MLIP) and dataset curation approach that separates intralayer and interlayer interactions and significantly improves model accuracy, yielding roughly a tenfold improvement in energy and force predictions relative to conventional models. We further demonstrate that traditional MLIP validation metrics – force and energy errors – are inadequate for moiré structures and develop a holistic, physically-motivated metric based on the distribution of stacking configurations. This metric effectively compares the entirety of large-scale moiré domains between two structures instead of relying on conventional measures evaluated on smaller commensurate cells. Finally, we establish that one-dimensional, rather than two-dimensional, moiré structures can serve as efficient surrogate systems for validating MLIPs, permitting validation protocols against explicit DFT calculations. Applying our framework to HfS2/GaS bilayers reveals that accurate structural predictions directly translate into reliable electronic properties. Our model-agnostic approach integrates with various intralayer and interlayer interaction models, enabling computationally tractable relaxation of moiré materials, from bilayer to complex multilayers, with rigorously validated accuracy. Machine learning interatomic potentials (MLIPs) struggle with twisted 2D materials due to varying energy scales and hard-to-validate moiré domains. Here, the authors propose a split MLIP and surrogate 1D systems to build accurate, verifiable models.
Related
- Orbital-Free Surrogate Functionals Yield Transferable Interatomic Potentials and Electron Densities
- Accurate and Rapid Vibrational Spectra of Molecular Crystals from Machine-Learned Interatomic Potentials
- How accurate are foundational machine learning interatomic potentials for heterogeneous catalysis?
- FACTO: fast atom-centered tensor operator for accurate and efficient foundational machine-learned interatomic potentials
- Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
BibTeX
@article{georgaras2026accurate,
title = {{Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials}},
author = {Johnathan D. Georgaras and Akash Ramdas and Chung Hsuan Shan and Elena Halsted and Berwyn and Tianshu Li and Felipe H. da Jornada},
journal = {Nature Communications},
year = {2026},
month = jul,
doi = {10.1038/s41467-026-74482-2},
url = {https://doi.org/10.1038/s41467-026-74482-2},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials
AU - Johnathan D. Georgaras
AU - Akash Ramdas
AU - Chung Hsuan Shan
AU - Elena Halsted
AU - Berwyn
AU - Tianshu Li
AU - Felipe H. da Jornada
PY - 2026
DA - 2026/07/31
JO - Nature Communications
DO - 10.1038/s41467-026-74482-2
UR - https://doi.org/10.1038/s41467-026-74482-2
AB - Twisted layered van der Waals materials often exhibit unique electronic and optical properties absent in their non-twisted counterparts. Unfortunately, predicting such properties is hindered by the difficulty in determining the atomic structure in materials displaying large moiré domains. Here, we introduce a split machine-learned interatomic potential (MLIP) and dataset curation approach that separates intralayer and interlayer interactions and significantly improves model accuracy, yielding roughly a tenfold improvement in energy and force predictions relative to conventional models. We further demonstrate that traditional MLIP validation metrics – force and energy errors – are inadequate for moiré structures and develop a holistic, physically-motivated metric based on the distribution of stacking configurations. This metric effectively compares the entirety of large-scale moiré domains between two structures instead of relying on conventional measures evaluated on smaller commensurate cells. Finally, we establish that one-dimensional, rather than two-dimensional, moiré structures can serve as efficient surrogate systems for validating MLIPs, permitting validation protocols against explicit DFT calculations. Applying our framework to HfS2/GaS bilayers reveals that accurate structural predictions directly translate into reliable electronic properties. Our model-agnostic approach integrates with various intralayer and interlayer interaction models, enabling computationally tractable relaxation of moiré materials, from bilayer to complex multilayers, with rigorously validated accuracy. Machine learning interatomic potentials (MLIPs) struggle with twisted 2D materials due to varying energy scales and hard-to-validate moiré domains. Here, the authors propose a split MLIP and surrogate 1D systems to build accurate, verifiable models.
SN - 2041-1723
ER -