Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Machine Learning Study of the Heulandite Family of Zeolites

Published

Author(s)

Shujiang Yang, Mohammed Lach-hab, Estela Blaisten-Barojas, Xiang Li, Vicky L. Karen

Abstract

Heulandite and clinoptilolite form the most abundant family of natural zeolite crystals. The topology of both of them is characterized by the framework type HEU. Despite many studies on these crystals, the mineral assignment to a zeolite as heulandite or clinoptilolite is still controversial and unresolved today. Based on a machine learning clustering analysis of crystallographic data of zeolite crystals, we show that zeolites belonging to the HEU framework type are divided into three groups of minerals instead of two. Two of the groups, HEU-h and HEU-c, contain crystals with names heulandite and clinoptilolite, respectively. The third newly proposed group HEU-m is composed of mixed zeolites named under both traditional names. The grouping is based on the EM algorithm and a set of descriptors built from data collected in the Inorganic Crystal Structure Database. Verification of the division of the HEU family into three groups is provided based on a battery of machine learning tests.
Citation
Microporous and Mesoporous Materials
Volume
130
Issue
3

Keywords

Zeolite, Heulandite, Clinoptilolite, Data Mining Clustering, Machine learning

Citation

Yang, S. , Lach-hab, M. , Blaisten-Barojas, E. , Li, X. and Karen, V. (2010), Machine Learning Study of the Heulandite Family of Zeolites, Microporous and Mesoporous Materials, [online], https://doi.org/10.1016/j.micromeso.2009.11.027 (Accessed April 20, 2024)
Created April 30, 2010, Updated October 12, 2021