Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances

TL;DR

This study employs machine learning and crystallographic distances to map inorganic synthesis conditions in zeolites, enabling prediction and interpretation of synthesis parameters for known and hypothetical frameworks.

Contribution

It introduces a novel distance metric and ML approach to relate zeolite structures with inorganic synthesis conditions without relying on templates or labels.

Findings

Distances correlate with synthesis conditions from literature.

Neighboring zeolites share similar synthesis parameters.

Models predict synthesis conditions for hypothetical frameworks.

Abstract

Zeolites are inorganic materials known for their diversity of applications, synthesis conditions, and resulting polymorphs. Although their synthesis is controlled both by inorganic and organic synthesis conditions, computational studies of zeolite synthesis have focused mostly on organic template design. In this work, we use a strong distance metric between crystal structures and machine learning (ML) to create inorganic synthesis maps in zeolites. Starting with 253 known zeolites, we show how the continuous distances between frameworks reproduce inorganic synthesis conditions from the literature without using labels such as building units. An unsupervised learning analysis shows that neighboring zeolites according to our metric often share similar inorganic synthesis conditions, even in template-based routes. In combination with ML classifiers, we find synthesis-structure relationships for 14 common inorganic conditions in zeolites, namely Al, B, Be, Ca, Co, F, Ga, Ge, K, Mg, Na, P, Si, and Zn. By explaining the model predictions, we demonstrate how (dis)similarities towards known structures can be used as features for the synthesis space. Finally, we show how these methods can be used to predict inorganic synthesis conditions for unrealized frameworks in hypothetical databases and interpret the outcomes by extracting local structural patterns from zeolites. In combination with template design, this work can accelerate the exploration of the space of synthesis conditions for zeolites.