AI-Guided Design and Property Prediction for Zeolites and Nanoporous Materials

11 Machine Learning-Aided Discovery of Nanoporous Materials for Energy- and Environmental-Related Applications

Archit Datar¹, Qiang Lyu², and Li-Chiang Lin^1,3

¹ William G. Lowrie Department of Chemical and Biomolecular Engineering, The Ohio State University, Columbus, Ohio, USA ² School of Materials Science and Engineering, China University of Petroleum (East China), Qingdao, Shandong, China³ Department of Chemical Engineering, National Taiwan University, Taipei, Taiwan

11.1 Introduction

11.1.1 Nanoporous Materials

Nanoporous materials are materials with pore sizes similar to that of common gas molecules (i.e., <2 nm) [1]. They can be classified as crystalline or non-crystalline, where non-crystalline materials include activated carbons, single-walled carbon nanotubes (SWCNTs), etc., while crystalline materials include metal-organic frameworks (MOFs), covalent organic frameworks (COFs), zeolites, etc. Crystalline materials have particularly drawn attention over the past decade. According to the data from Web of Science, the number of publications on zeolites, MOFs, and COFs has been increasing every year over the past decade (Figure 11.1). An interesting feature of these materials is that they can be synthesized with a large porosity and a high internal surface area, with the highest reported to date being DUT-60 having a surface area of 7800 m²/g [2]. The porosities and surface areas of these materials have substantially increased in the last few decades [3]. Another interesting ...