Machine Learning Accelerates 27 Al NMR Chemical Shift Predictions in Zeolites
Researchers from the Department have successfully deployed machine learning-based methods to predict 27Al chemical shifts in zeolite MFI, a complex industrially relevant material. This breakthrough enables the comprehensive exploration of conditions relevant to catalysis, including water loading, temperature, and aluminium pair positions. The study demonstrates the capabilities of machine learning approaches in providing reliable predictions of spectroscopic observables under realistic conditions.
