Speciation of Nanocatalysts Using X-ray Absorption Spectroscopy Assisted by Machine Learning
Prahlad K. Routh, Nicholas Marcella, Anatoly I. Frenkel
Abstract
The structure and morphology of supported nanoparticle catalysts play important roles in many industrial reactions. Recent progress has identified key aspects of structure–activity relationships at the nanoscale and novel methods to study the local environment of the active sites. X-ray absorption fine structure (XAFS) spectroscopy, despite being a leading technique for this purpose, is hampered significantly by its ensemble-averaging nature which often leads to a bias toward a single “representative” structure. Learning heterogeneous distributions of nanostructures at the inter- and intraparticle levels from the average XAFS spectrum is a formidable challenge that can be overcome in some cases described in this Perspective. We also discuss emerging machine learning techniques for extracting the information about the heterogeneity of metal species from XAFS data.