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

TL;DR

This paper introduces a physics-informed Bayesian optimization method for automated surface structure reconstruction using LEED I(V) analysis, effectively solving complex inverse problems in surface characterization.

Contribution

It embeds multiple scattering LEED models into a trust-region Bayesian optimization loop for autonomous, efficient, and scalable surface structure determination.

Findings

Successfully applied to Ag(100) surface

Demonstrated robustness on Fe2O3 surface

Enables physics-informed, reproducible inverse analysis

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)-(1$\time$1) and Fe\textsubscript{2}O\textsubscript{3}(1$\overline{1}$02)-(1$\time$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.