A Neural Network Approach for Characterization of Metal Nanostructures

Anatoly I. Frenkel

Department of Materials Science and Chemical Engineering, Stony Brook University
Stony Brook, NY

Monday 25 March 2019
Time: 1pm
Venue: A1/3 Physics, UCL
Contact: Alex Shluger
Tel: +44 (0)20 7679 1312

Tracking the structure of nanocatalysts (and other functional nanomaterials) under operating conditions is a challenge due to the paucity of experimental techniques that can provide atomic-level information for active metal species. I will demonstrate the use of X-ray absorption spectroscopy (XAS) and supervised machine learning (SML) for determining the three-dimensional geometry of metal catalysts at the sub-nanometer size scale. Artificial neural network is used to unravel the hidden relationship between the XAS features and catalyst geometry. In other words, we trained computer to learn how to ‘invert” the unknown spectrum and obtain the underlying structural descriptors. This method is demonstrated by reconstructing the average size, shape and morphology of nanoparticles with narrow size and composition distributions from the coordination numbers and interatomic distances obtained using the SML approach. First applications of this method to the determination of nanomaterial structure in operando conditions, such as studies of synthesis, nucleation, growth and reactivity of metal catalysts will be demonstrated.


[1] J. Timoshenko, C. J. Wrasman, M. Luneau, T. Shirman, M. Cargnello, S.  R. Bare, J. Aizenberg,  C. M. Friend, A. I. Frenkel Nano Letters 19, 520-529 (2019)

[2] J. Timoshenko, A. Halder, B. Yang, S. Seifert, M. Pellin, S. Vajda, A. I. Frenkel J. Phys. Chem. C 122, 21686-21693 (2018)

[3] J. Timoshenko, A. Anspoks, A. Cintins, A. Kuzmin, J. Purans, A. I. Frenkel Phys. Rev. Lett. 120, 225502 (2018)

[4] J. Timoshenko, D. Lu, Y. Lin, A. I. Frenkel J. Phys. Chem. Lett., 8, 5091-5098 (2017)

  • Anatoly Frenkel.jpg

Follow @tyc_london for updates from the Thomas Young Centre.