A Neural Network Approach for Characterization of Metal Nanostructures
Anatoly I. Frenkel
Stony Brook University & Brookhaven National Laboratory
Tracking the structure of functional nanomaterials (e.g., metal catalysts) under operando conditions remains a challenge due to the paucity of experimental techniques that can provide atomic-level information for active metal species. Here we report on the use of X-ray absorption spectroscopy (XANES and EXAFS) and supervised machine learning (SML) for determining the three-dimensional geometry of metal catalysts. Artificial neural network (NN) is used to unravel the hidden relationship between the XANES features and catalyst geometry. In the case of EXAFS, NN is used to obtain the partial radial distribution function directly from the spectra. Our approach allows one to solve the structure of a mono- or heterometallic nanoparticle or a size-selected cluster from its experimental XANES or EXAFS spectra. These applications are demonstrated by reconstructing the average size, shape and morphology of well-defined platinum nanoparticles1 and monitoring structural changes in bulk Fe during its structural phase transition from BCC to FCC upon heating. This method is applicable to the determination of nanomaterial structure in operando studies. It also allows on-the-fly analysis, and is a promising approach for high-throughput and time-dependent studies.
- 10:30 Refreshments
- 10:45–12:00 Talk