Reconstructing the Hamiltonian from the local density of states using neural networks
Journal of Physics: Condensed Matter · 03.07.2026 · 38 (26) · 265502
DOI: 10.1088/1361-648x/ae7d75 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Physics: Condensed Matter, online erschienen am 03.07.2026. Verfasst von Nisarga Paul und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Reconstructing a quantum system’s Hamiltonian from limited yet experimentally observable information is interesting both as a practical task and from a fundamental standpoint. We investigate the inverse problem of reconstructing a Hamiltonian from a spatial map of the local density of states (LDOS) near a fixed energy. We demonstrate high-quality recovery of Hamiltonians from the LDOS using supervised learning. In particular, we generate synthetic data from single-particle Hamiltonians in 1D and 2D, train convolutional neural networks, and obtain models that solve the inverse problem with remarkably high accuracy. Moreover, we are able to generalize beyond the training distribution and develop models with strong robustness to noise. Finally, we comment on possible experimental applications to scanning tunneling microscopy, where we propose that maps of the electronic LDOS might be used to reveal a sample’s unknown underlying energy landscape.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America.
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America.
ORCID-Profile: Nisarga Paul, Andrew Ma
Zitieren
APA
Paul, N., Ma, A., & Nuckolls, K. P. (2026). Reconstructing the Hamiltonian from the local density of states using neural networks. Journal of Physics: Condensed Matter, 38(26), 265502. https://doi.org/10.1088/1361-648x/ae7d75
Vancouver
Paul N, Ma A, Nuckolls KP. Reconstructing the Hamiltonian from the local density of states using neural networks. Journal of Physics: Condensed Matter. 2026;38(26):265502. doi:10.1088/1361-648x/ae7d75
BibTeX
@article{Paul2026,
author = {Paul, Nisarga and Ma, Andrew and Nuckolls, Kevin P},
title = {Reconstructing the Hamiltonian from the local density of states using neural networks},
journal = {Journal of Physics: Condensed Matter},
year = {2026},
volume = {38},
number = {26},
pages = {265502},
doi = {10.1088/1361-648x/ae7d75}
}
EUVIMED