Structural Investigation and Enriched Catalysis of Cu-complex Encapsulated Microporous Catalyst with Pragmatic Modelling for Prediction of Activity by Using Machine Learning
Authors :- R Prajapati, J Chaudhari, P Paredi, K Shah, R Bandyopadhyay, M Bandyopadhyay at el.
Publication :- ChemPhysChem 2025, e202400950
Silicoaluminophosphates (SAPOs) are structurally diverse materials widely used in separation, catalysis, and environmental applications. In this study, a simple post-synthetic method is used to create a hybrid porous material by immobilizing a copper(II) complex onto base-functionalized SAPO molecular sieves. The copper complex, synthesized using 2,9-dimethyl-1,10-phenanthroline and copper nitrate, is structurally confirmed through single-crystal X-ray diffraction. The effective activity in ring-opening reaction of epoxide is achieved when this complex is anchored on amine-functionalized SAPO materials. Characterization techniques such as powder X-ray diffraction, N2 adsorption-desorption, Fourier transform infrared spectroscopy, nuclear magnetic resonance, scanning electron microscope, and thermogravimetric analysis confirm the structural integrity, surface properties, and thermal stability of the materials. High conversion efficiencies of 90% and 88% are achieved using copper-complex-immobilized SAPO-34 and SAPO-5, respectively. To enhance industrial applicability, machine learning techniques are applied to predict product conversion and selectivity. Methods such as linear regression, support vector machine (SVM), and k-nearest neighbors (kNN) are evaluated, with SVM and kNN showing strong predictive performance. Error metrics like mean-squared error, mean absolute percentage error, and R score validate the model accuracy. This work highlights the effective integration of functionalized SAPOs with ML tools for catalytic optimization and industrial-scale applications.