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

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.