Representations and descriptors unifying the study of molecular and bulk systems. Issue 8 (27th December 2019)

• Record Type: Journal Article
• Authors: Rossi, Kevin; Cumby, James
• Is Part Of: International journal of quantum chemistry. Volume 120:Issue 8(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-12-27
• Subjects: atom density -- connectivity -- data driven -- descriptors -- machine learning -- symmetry distortions; Quantum chemistry -- Periodicals; 541.28
• DOI: 10.1002/qua.26151
• Languages: English
• ISSNs: 0020-7608

Abstract

Abstract: Establishing a unified framework for describing the structures of molecular and periodic systems is a long‐standing challenge in physics, chemistry, and material science. With the rise of machine learning methods in these fields, there is a growing need for such a method. This perspective aims to discuss the development and use of three promising approaches—topological, atom‐density, and symmetry‐based—for the prediction and rationalization of physical, chemical, and mechanical properties of atomistic systems across different scales and compositions. Abstract : Machine learning based on atomic structure is a rapidly growing area, but a key limitation is finding suitable ways to represent the structure (descriptors). A number of methods have been developed, but tend to focus on either molecular materials or extended solids. This perspective discusses a range of methods with the potential to unify these two areas, which would enable a greater range of machine learning problems to be explored.