Enhancing Surface Analysis and Data Collection Efficiency using GE-XANES and Machine Learning: A Synchrotron-Based Study

Abstract

Addressing global challenges such as corrosion requires the development of new materials and a deeper understanding of their surface properties. Compositionally complex alloys (CCAs) have emerged as a promising class of materials for various applications, including aerospace and energy industries, due to their exceptional structural properties. However, their complex atomic interactions and behavior under extreme conditions remain understudied, particularly in the context of corrosion. Surface-sensitive techniques, including grazing exit X-ray absorption near-edge structure spectroscopy (GE-XANES), play a pivotal role in understanding the physical and chemical properties of material surfaces. This study presents the development of a new GE-XANES setup using a pnCCD detector, which offers several advantages over other detector types, such as a small pixel area and improved signal discrimination. This enables a more detailed analysis of the layer structure and composition of CCAs, contributing to our understanding of surface degradation phenomena [1]. Moreover, we explore machine learning-driven data acquisition, specifically Bayesian optimization (BO), to improve the data collection process in GE-XANES experiments at synchrotron facilities. The integration of machine learning / active learning techniques aims to optimize data acquisition, reduce the experimental time, and increase research productivity in photon-hungry experiments such as GEXANES. By enhancing the efficiency of beamtime at synchrotron facilities, our approach holds significant potential for advancing the study of CCAs and other materials in various fields. To sum up, this study integrates sophisticated surface analysis methods and data gathering techniques powered by machine learning to tackle the crucial problem of corrosion and surface degradation in compositionally complex alloys. The suggested approach not only improves comprehension of material surfaces but also provides a more streamlined and potent method for materials research and development. Reference Cakir, C. T.; Piotrowiak, T.; Reinholz, U.; Ludwig, A.; Emmerling, F.; Streli, C.; Guilherme Buzanich, A.; Radtke, M. Exploring the Depths of Corrosion: A Novel GE-XANES Technique for Investigating Compositionally Complex Alloys. Analytical Chemistry 2023, 95, 4810—4818.