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

14 Machine Learning and Digital Manufacturing Approaches for Solid-State Materials Development

Lawson T. Glasby¹, Emily H. Whaites¹, and Peyman Z. Moghadam^1,2

¹ Department of Chemical and Biological Engineering, University of Sheffield, Sheffield, United Kingdom² Department of Chemical Engineering, University College London (UCL), London, United Kingdom

14.1 Introduction

Solid state chemistry, often referred to as materials chemistry, is a field of chemistry concerned with studying the synthesis, structure, and properties of materials in the solid phase. These solids are often classified as crystalline, amorphous, organic, inorganic, or nano-materials, depending on the type, and the arrangements of their constituent atoms. Some notable examples include zeolites, covalent organic frameworks (COFs), metal–organic cages (MOCs), and metal–organic nano-sheets (MONs).

One intensely studied class of solid state materials, and the primary example used throughout this chapter, are metal–organic frameworks (MOFs), crystalline structures synthesized from organic and inorganic building blocks to form an extended framework material. The building-block approach creates the opportunity for the synthesis of tens of thousands of combinations where they can be tailored to achieve particular properties for a multitude of applications, and since the start of the 1990s, thousands of MOF materials have been synthesized at laboratory scale [1–6]. However, despite their great promise for a wide range ...