Machine learning-assisted crystal engineering of a zeolite

Abstract

It is shown that Machine Learning (ML) algorithms can usefully capture the effect of crystallization composition and conditions (inputs) on key microstructural characteristics (outputs) of faujasite type zeolites (structure types FAU, EMT, and their intergrowths), which are widely used zeolite catalysts and adsorbents. The utility of ML (in particular, Geometric Harmonics) toward learning input-output relationships of interest is demonstrated, and a comparison with Neural Networks and Gaussian Process Regression, as alternative approaches, is provided. Through ML, synthesis conditions were identified to enhance the Si/Al ratio of high purity FAU zeolite to the hitherto highest level (i.e., Si/Al = 3.5) achieved via direct (not seeded), and organic structure-directing-agent-free synthesis from sodium aluminosilicate sols. The analysis of the ML algorithms’ results offers the insight that reduced Na2O content is key to formulating FAU materials with high Si/Al ratio. An acid catalyst prepared by partial ion exchange of the high-Si/Al-ratio FAU (Si/Al = 3.5) exhibits improved proton reactivity (as well as specific activity, per unit mass of catalyst) in propane cracking and dehydrogenation compared to the catalyst prepared from the previously reported highest Si/Al ratio (Si/Al = 2.8).

Restructuring Surface Lewis Pairs of FAU Zeolite through N Doping for Boosting the Toluene Side-Chain Alkylation Performance

“…As can be seen in the 29 Si MAS NMR spectra (Figure 3a), both CsX-P and CsX-BN-600 samples exhibit four main resonances, corresponding Q 4 Si species coordinated with n OAl bonds (where n = 0, 1, 2, and 3). 19,20 Notably, the characteristic band of Q 4 (3Al) in CsX-BN-600 becomes more intense than CsX-P, which might be due to the introduction of N species into the framework of X zeolite. 21 In the 27 Al MAS NMR, all samples show one dominant peak (∼62 ppm), which is attributed to tetrahedral coordinated aluminum species, indicating all of the Al atoms are incorporated in the framework of zeolite (Figure 3b).…”

The Current Understanding of Mechanistic Pathways in Zeolite Crystallization

“…The ongoing development and employment of computational modeling, data mining, and machine learning − will be a critical aspect of zeolite design in the coming decades . Mining and analysis of large data sets has helped investigate relationships between synthesis parameters and product properties. − Computational modeling and machine learning have also been used to predict optimal OSDAs, leading to more economical synthesis approaches and crystals with enhanced morphologies and properties (e.g., intergrowths). , Thermodynamic calculations of zeolite structures have predicted the potential limits for synthesizing new crystal structures and controlling framework composition.…”

Machine Learning Prediction of Transition-State Energies in Small-Pore Zeolites Combining Acidity and Topology Descriptors

“…Machine learning (ML) techniques have attracted increasing interest to predict structures, energies, and properties in zeolite catalysis using various electronic and structural features or descriptors. − It has been demonstrated that the adsorption strength and the reaction energies can be predicted in metal-exchanged zeolites using different descriptor-based ML approaches. − The prediction of TS energies, on the other hand, is particularly desirable using limited computational data to circumvent the costly TS calculations. It already becomes possible by combining ML models and a set of (topology-based) descriptors across a series of metal or oxide surfaces. − …”