Moiré patterns made of two-dimensional (2D) materials represent highly tunable electronic Hamiltonians, allowing a wide range of quantum phases to emerge in a single material. Current modeling techniques for moiré electrons require significant technical work specific to each material, impeding large-scale searches for useful moiré materials. In order to address this difficulty, we have developed a material-Agnostic machine learning approach and test it here on prototypical one-dimensional (1D) moiré tight-binding models. We utilize the stacking dependence of the local density of states (SD-LDOS) to convert information about electronic band structure into physically relevant images. We then train a neural network that successfully predicts moiré electronic structure from the easily computed SD-LDOS of aligned bilayers. This network can satisfactorily predict moiré electronic structures, even for materials that are not included in its training data.
|Original language||English (US)|
|Journal||Physical Review Research|
|State||Published - Oct 2022|
Bibliographical noteFunding Information:
The calculations in this work were performed using computational resources and services at the Center for Computation and Visualization (CCV) at Brown University and the Minnesota Supercomputing Institute (MSI) at the University of Minnesota. D.L. was supported in part by NSF DMREF Award No. 1922165. M.L. was supported in part by NSF DMREF Award No. 1922165 and Simons Targeted Grant Award No. 896630. S.C. was supported by the National Science Foundation under Grant No. OIA-1921199.
© 2022 authors. Published by the American Physical Society.