Physics-informed automated surface reconstructing via low-energy electron diffraction based on Bayesian optimization
Abstract
Low-energy electron diffraction (LEED) is a cornerstone technique for determining surface atomic structures[heldStructureDeterminationLowenergy2025], yet the quantitative analysis of electron diffraction intensity as a function of incident electron energy -- that is, LEED-\textit{I(V)} analysis -- remains a complex inverse problem. In this work, we tackle quantitative LEED-\textit{I(V)} analysis based on physics-informed Bayesian optimization (BO). By embedding multiple scattering LEED forward models directly into a trust-region BO loop, our approach simultaneously optimizes both structural and experimental parameters, adaptively adjusting trust regions for efficient exploration of complex non-convex parameter spaces without manual intervention. The robustness and scalability of the approach are demonstrated using the Ag(100)-(11) and Fe\textsubscript{2}O\textsubscript{3}(102)-(11) surfaces as examples. Our work establishes a general framework for solving inverse problems in various characterization techniques, unlocking a physics-informed efficient, reproducible, and autonomous paradigm.
Cite
@article{arxiv.2604.04578,
title = {Physics-informed automated surface reconstructing via low-energy electron diffraction based on Bayesian optimization},
author = {Xiankang Tang and Ruiwen Xie and Jan P. Hofmann and Hongbin Zhang},
journal= {arXiv preprint arXiv:2604.04578},
year = {2026}
}