Скачать или смотреть Machine learning-assisted analysis of XANES and EXAFS: XAS Journal Club, Anatoly Frenkel

Title: Machine learning-assisted analysis of material structure using XANES and EXAFS
Speaker: Prof. Anatoly Frenkel (Stony Brook University)
Abstract: Tracking the structure of functional nanomaterials (e.g., metal catalysts) remains a challenge due to the paucity of experimental techniques that can provide atomic-level information for metal species in harsh conditions, often required for studying chemical transformations. 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 monometallic and alloy nanoparticles [1]. Artificial neural network (NN) is used to unravel the hidden relationship between the XANES features and material’s geometry [2]. In the case of EXAFS, NN is used to obtained the partial radial distribution function (PRDF) directly from the spectra [3]. In other words, we trained computer to learn how to ‘invert” the unknown spectrum and obtain the underlying structural descriptors. Training of the NN was performed by using theoretical spectroscopy codes. These applications are demonstrated by reconstructing the compositional distributions of nanocatalysts from the coordination numbers obtained by NN-XANES, or from the PRDF obtained by NN-EXAFS. First applications of these method to the determination of structure of nanocatalysts in reaction conditions will be demonstrated [4-6].
Reading: [1] J. Timoshenko, A. I. Frenkel. “Inverting” X-ray Absorption Spectra of Catalysts by Machine Learning in Search of Activity Descriptors. ACS Catalysis (Perspective) 9, 10192-10211 (2019).
https://pubs.acs.org/doi/10.1021/acsc...
[2] J. Timoshenko, D. Lu, Y. Lin, A. I. Frenkel. Supervised machine learning-based determination of three-dimensional structure of metallic nanoparticles. J. Phys. Chem. Lett., 8, 5091-5098 (2017).
https://pubs.acs.org/doi/abs/10.1021/...
[3] J. Timoshenko, et al. Artificial neural network approach for characterizing structural transformations by X-ray Absorption Fine Structure spectroscopy. Phys. Rev. Lett. 120, 225502 (2018).
https://journals.aps.org/prl/abstract...
[4] N. Marcella, Y. Liu,et al Neural network assisted analysis of bimetallic nanocatalysts using X-ray absorption near edge structure spectroscopy. Phys. Chem. Chem. Phys. (2020) Early view.
https://pubs.rsc.org/en/content/artic...
[5] J. Timoshenko, et al . Probing atomic distributions in mono- and bimetallic nanoparticles by supervised machine learning. Nano Letters 19, 520-529 (2019).
https://pubs.acs.org/doi/10.1021/acs....
[6] Y. Liu,et al . Mapping XANES spectra on structural descriptors of copper oxide clusters using supervised machine learning. J. Chem. Phys. 151, 164201 (2019).
https://aip.scitation.org/doi/full/10...