Integrating Solution Physical Properties into Zeolite Synthesis Prediction via Causal Machine Learning.
TL;DR
A data-driven framework that integrates state-of-the-art synthesis parameters with solution physical properties derived from molecular simulations to predict zeolite crystallization outcomes is developed, showing that framework selection is encoded not only in chemical composition but also in emergent solution properties.
Abstract
Zeolites are essential crystalline materials for catalysis and molecular separations, yet their targeted synthesis remains challenging because framework selection is governed by coupled solution chemistry, organic structure-directing agents, solvent environments, and crystallization conditions. Here we develop a data-driven framework that integrates state-of-the-art synthesis parameters with solution physical properties derived from molecular simulations to predict zeolite crystallization outcomes. Across 366 literature syntheses, the model achieves 96.4% accuracy in classifying 20 zeolite frameworks and 87.7% accuracy in distinguishing four structural aperture classes, outperforming composition-only baselines. Model interpretation reveals that solution density and dielectric constant provide independent information, with opposite effects on the formation of small- and large-aperture zeolites. These findings show that framework selection is encoded not only in chemical composition but also in emergent solution properties, offering a physically informed strategy for predictive zeolite synthesis.