Machine Learning Identification of Zeolite Framework Types
نویسندگان
چکیده
The characteristic framework types of zeolite crystals are routinely determined by calculating coordination sequences and vertex symbols of the 3D crystal structures. This method has limitations and tends to fail when the synthesized crystals are not close to perfect and present some types of crystallographic disorder. A machine learning based Zeolite-Structure-Predictor (ZSP) model is developed to predict framework types for both near perfect and moderately disordered zeolite crystals. The ZSP uses various attributes, including topological descriptors based on a computational geometry approach and relevant physical, chemical properties of the crystals. Trained with 41 framework types, the ZSP can correctly classify zeolite crystals with over 98% accuracy. Additionally, it is shown that the ZSP model is able to predict the framework types for strongly disordered zeolite crystals with reliable success rate.
منابع مشابه
Identifying Zeolite Frameworks with a Machine Learning Approach
Zeolites are microporous crystalline materials with highly regular framework structures consisting of molecularsized pores and channels. The characteristic framework type of a zeolite is conventionally defined by combining information on its coordination sequences, vertex symbols, tiling, and transitivity information. Here we present a novel knowledge-based approach for zeolite framework type c...
متن کاملMachine Learning Approach for Classification of Zeolite Crystals
—A machine learning approach is applied to classify zeolite crystals according to their framework type. The Zeolite-Structure-Predictor is introduced based on the Random Forest algorithm. Zeolites structural data from the Inorganic Crystal Structure Database (ICSD) are used to train the model. The ZSP uses sixteen attributes including topological descriptors obtained with statistical geometry a...
متن کاملA Cheminformatics Approach for Zeolite Framework Determination
Knowledge of the framework topology of zeolites is essential for multiple applications. Framework type determination relying on the combined information of coordination sequences and vertex symbols is appropriate for crystals with no defects. In this work we present an alternative machine learning model to classify zeolite crystals according to their framework types. The model is based on an ei...
متن کاملMachine learning approach for structure-based zeolite classification
Please cite this article in press as: D.A. Ca Application of knowledge discovery methods to crystal structure databases is an emerging research area of materials science that is playing an important role in facilitating data analysis. This study is aimed at combining computational geometry methods with machine learning algorithms for classification of inorganic solid materials of known structur...
متن کاملNovel Approach for Clustering Zeolite Crystal Structures.
Informatics approaches play an increasingly important role in the design of new materials. In this work we apply unsupervised statistical learning for identifying four framework-type attractors of zeolite crystals in which several of the zeolite framework types are grouped together. Zeolites belonging to these super-classes manifest important topological, chemical and physical similarities. The...
متن کامل