Zeolites are porous, aluminosilicate materials with many industrial and “green” applications. Despite their industrial relevance, many aspects of zeolite synthesis remain poorly understood requiring costly trial and error synthesis. In this paper, we create natural language processing techniques and text markup parsing tools to automatically extract synthesis information and trends from zeolite journal articles. We further engineer a data set of germanium-containing zeolites to test the accuracy of the extracted data and to discover potential opportunities for zeolites containing germanium. We also create a regression model for a zeolite’s framework density from the synthesis conditions. This model has a cross-validated root mean squared error of 0.98 T/1000 Å3, and many of the model decision boundaries correspond to known synthesis heuristics in germanium-containing zeolites. We propose that this automatic data extraction can be applied to many different problems in zeolite synthesis and enable novel zeolite morphologies.
Selectivity control in zeolite synthesis: Zeolites are widely used in many industrial applications, but despite decades of research, their synthesis still relies on trial-and-error approaches. Complex nucleation mechanisms and topological diversity lead to strong phase competition, complicating the issue of rational design of zeolite synthesis. Using atomistic simulations, literature mining, human-computer interaction, synthesis, and characterization, Schwalbe-Koda et al . developed a computational strategy that enables a priori control of phase selectivity in zeolite synthesis (see the Perspective by Chaikittisilp and Okubo). This approach uses several metrics for designing organic structure–directing agents to crystallize target zeolites with controlled phase competition and intergrowth. These results may have profound implications for the materials science community if this method is shown to be successful in the synthesis of practically useful uncommon zeolites. —YS
Zeolites are crystalline microporous materials with diverse topologies used ubiquitously in catalysis and separations. However, the targeted synthesis of specific frameworks remains limited by the complexity of crystallization and competition among phases. Here, we introduce a data-driven strategy that integrates high-throughput simulations and SHapley Additive exPlanations (SHAP) analysis to design both organic and inorganic structure-directing agents (OSDA and ISDAs, respectively) for synthesizing small-pore zeolites containing lta-cages. Guided by this framework, we identified 4,7,13,16,21,24-hexaoxa-1,10-diazabicyclo[8.8.8]hexacosane as an optimal OSDA, and tailored alkali/alkaline-earth metal cations to stabilize specific composite building units. We achieved the phase-selective crystallization of RHO, KFI, LTA, and UFI zeolites with record-high Si/Al ratios under hydroxide-mediated conditions without the use of fluoride. The resulting high-silica materials exhibit exceptional hydrothermal stability, outperforming that of conventional analogues. Our results establish a generalizable framework for computational SDA selection and rational synthesis of zeolites with targeted structure and composition.