A symmetry-preserving and transferable representation for learning the Kohn–Sham density matrix

Digital Discovery 2026 Open access

Read full text
Authors: Liwei Zhang, Patrizia Mazzeo, Michele Nottoli, Edoardo Cignoni, Lorenzo Cupellini, Benjamin Stamm
DOI: 10.1039/d5dd00230c
Cited by: 1
References: 67

Abstract

We present a parameterized representation for learning the mapping from a molecular configuration to its corresponding density matrix using the atomic cluster expansion (ACE) framework, which preserves the physical symmetries of the mapping.

Fields of Study & Subjects

Machine Learning in Materials Science Inorganic Chemistry and Materials Advanced Chemical Physics Studies

Publication details

Journal / source
Digital Discovery
Publisher
Royal Society of Chemistry (RSC)
Volume
5
Issue
4
Pages
1868–1880
Publication date
1 January 2026
Language
EN