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

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.

References in corpus (10)

• XGBoost: A Scalable Tree Boosting System
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• On representing chemical environments
• On the Completeness of Atomic Structure Representations
• Graph similarity drives zeolite diffusionless transformations and intergrowth
• Accurate large-scale simulations of siliceous zeolites by neural network potentials
• A New Kind of Atlas of Zeolite Building Blocks
• Ranking the Synthesizability of Hypothetical Zeolites with the Sorting Hat
• Pointwise Distance Distributions for detecting near-duplicates in large materials databases

Cited by in corpus (3)

• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Geographic-style maps with a local novelty distance help navigate the materials space
• Guided Synthesis of EMT Zeolites by Machine Learning