In this paper, the possibility of applying graph neural networks (NN) to study the structure of copper centers of zeolites is considered. The dataset used for NN training was prepared using the FDMNES software based on the finite difference method and included more than 2100 Cu K-XANES spectra for Cu-MOR. The performed study demonstrated the capability of graph neural networks to reproduce the Cu K-XANES spectrum corresponding to a particular model of the copper center in the zeolite framework.
Keywords: zeolite, mordenite, atomic structure, XANES, machine learning, graph neural networks
Today, catalysts based on zeolites containing transition metal ions are being intensively developed, ensuring the selectivity of the reaction of direct oxidation of methane to methanol. In current work, the X-ray absorption spectroscopy complimented with the structural models obtained in frames of the density functional theory were used to study the dependence of the local atomic structure of copper centers in mordenite type zeolites synthesized by solid-phase ion exchange using CuCl and H-MOR, upon the annealing temperature at different stages of synthesis. The typical Cu – O interatomic distances and the corresponding coordination numbers are determined. The dependence of the fraction of copper ions on the zeolite on the annealing temperature was established.
Keywords: EXAFS, DFT, zeolites, solid-phase synthesis, methanol synthesis