Work

Physics-informed automated surface reconstruction via low-energy electron diffraction based on Bayesian optimization

Year: 2026

Type: article

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- I(V) analysis---remains a complex inverse problem. In this work, we tackle quantitative LEED- 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)-(1×1) and Fe\textsubscript{2}O\textsubscript{3}(1$(\overline{1})$02)-(1×1) 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.

Source: npj Computational Materials

DOI: 10.1038/s41524-026-02297-2

Authors: Xiankang Tang, Ruiwen Xie, Jan P. Hofmann, Hongbin Zhang

Institution: Technische Universität Darmstadt

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,490

Funders: China Scholarship Council, Technische Universität Darmstadt