Study of the Relationship between Synthesis Descriptors and the Type of Zeolite Phase Formed in ZSM‐43 Synthesis by Using Machine Learning

Abstract

Small-pore zeolites possess pores that are constructed of eight tetrahedral atoms. ZSM-43 is a small-pore zeolite with twodimensional eight-ring channels. The preparation of ZSM-43 is influenced by the molar concentration of hydroxide ions, choline based organic structure-directing agents (OSDA) and inorganic structure-directing agents (ISDA) such as sodium, potassium and cesium. The synthetic conditions yield a range of products such as ZSM-43, amorphous, UZM-15, and other zeolites. There is a significant challenge in relating synthetic descriptors to their implications in zeolite phase formation. As a proof-of-concept study, we correlated the type of product formed with the gel molar composition in complex ZSM-43 synthesis using machine learning algorithms. Seven different supervised machine learning algorithms have demonstrated an accuracy of > 95 percent and an F1 score of > 95 percent. The decision tree algorithm (DT) demonstrates the relationship between what type of phase is produced by what concentration of ISDA and hydroxide ions, as well as the effects of changing these parameters on phase transformation. DT provides structural and physicochemical insights into zeolite chemistry. From the experimental data of ZSM-43, it is difficult to obtain detailed information regarding the chemistry of all phase formations. However, machine learning algorithms aid in recognizing hidden patterns in the data, facilitating deeper understanding of zeolite chemistry and phase transformations.

Efficient Removal of Greenhouse Gases: Machine Learning-Assisted Exploration of Metal–Organic Framework Space

“…For adsorbents that capture GHGs, various features can be calculated or measured to optimize the synthesis of component materials. 127 Temperature, pH, pressure, reaction time, and reactant amount are commonly used experimental characteristics. Conformational and compositional characteristics (including pore size, volume, surface area, and topological shape) were frequently used when exploring adsorbent materials with optimal structures and compositions.…”

“…Therefore, materials and computer scientists can collaborate to identify the most promising characteristics for the input of the model. For adsorbents that capture GHGs, various features can be calculated or measured to optimize the synthesis of component materials . Temperature, pH, pressure, reaction time, and reactant amount are commonly used experimental characteristics.…”

Machine Learning in the Development of Adsorbents for Clean Energy Application and Greenhouse Gas Capture

“…[ 28 , 31 , 36 ] For example, experimental features (temperature, pH value, pressure, reaction time, and the amount of the reactants) would be used to construct models for synthesis optimization of adsorbent materials. [ 58 ] Topographical features (pore size, volume, surface area, topological shape) and compositional features are frequently used when searching for adsorbent materials with the best texture and composition for gas uptake. [ 59 ] Atomic features (e.g., atomic radii, mass, number of valence electrons) and electronic features (e.g., electronegativity, ionization energy, polarizability) are frequently used for selection of the coordinating metals of MOFs.…”