Force Field-Agnostic Phase Classification of Zeolitic Imidazolate Framework Polymorphs

TL;DR

This study develops neural network classifiers to automatically identify phases of Zeolitic Imidazolate Frameworks during molecular dynamics simulations, improving understanding of phase transitions and reducing force field bias.

Contribution

It introduces a force field-agnostic neural network approach for classifying ZIF phases, enhancing accuracy and applicability in molecular simulations.

Findings

Low-dimensional descriptors achieve high classification accuracy.

High-dimensional descriptors improve performance further.

Training across different force fields reduces bias and increases generality.

Abstract

Zeolitic Imidazolate Frameworks (ZIFs) are a family of metal--organic frameworks that feature metal centers tetrahedrally linked to imidazole-based ligands and adopt zeolite-like topologies. ZIFs formed by Zinc cations and imidazolate linkers exhibit a remarkable degree of polymorphism, which can be modulated by varying synthesis parameters or thermodynamic conditions (i.e., temperature and pressure). Computer simulations provide a unique way of studying these materials and their phase transitions from the microscopic standpoint, revealing their underlying molecular mechanisms. However, studying these mechanisms requires to be able to classify the phase of each molecular entity in an agnostic and automatic fashion, which is particularly challenging when the two phases involved are structurally very similar. In this work, we systematically study neural network classifiers to classify ZIF phases on-the-fly during molecular dynamics simulations. We test a variety of input features, differing both in the dimensionality and nature of the descriptors and in the kind of force field used for building the training/testing database. We reveal that even with low-dimensional descriptors the classification is highly accurate, while the use of high-dimensional descriptors leads to an even better performance. Training the classifier with configurations coming from different force fields we can remove force field bias and enhance the classifier performance and general applicability. Finally, we apply our classifiers to reveal mechanistic details of the ZIF-4-cp $\xrightarrow{}$ ZIF-4-cp-II phase transition.