Accelerating Surface Composition Characterization of Thin-Film Materials Libraries using Multi-Output Gaussian Process Regression

Abstract

Efficient characterization of surface compositions across high-dimensional materials spaces is critical for accelerating the discovery of surface-dominated functional materials. While X-ray photoelectron spectroscopy allows detailed surface composition investigation, it remains a time-intensive technique. In this work, it is demonstrated that Gaussian process regression can be used to accurately predict surface compositions from rapidly acquired volume composition data obtained by energy-dispersive X-ray spectroscopy, drastically reducing the number of required surface measurements. As a proof of principle, an exemplary system, the oxide Mg-Mn-Al-O, is synthesized as a composition-spread thin-film materials library and analyzed by high-throughput methods. We show that the surface composition of the entire library can be predicted with an accuracy of 96% with only 13 measurements, reducing the total measurement time by 277 h. This is a scalable and data-efficient solution for integrating surface analysis into materials discovery workflows.