Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids

• Published in: npj computational materials 2022-08, Vol.8 (1), p.1-10, Article 183
• Main Authors: Jørgensen, Peter Bjørn, Bhowmik, Arghya
• Format: Article
• Language: English
• Subjects: 639/301/1034/1037; 639/301/1034/1038; 639/638/563; 639/766/119/995; Accuracy; Apexes; Cathodes; Characterization and Evaluation of Materials; Chemistry and Materials Science; Computational Intelligence; Datasets; Density functional theory; Electrolytes; Electron density; Electrons; Energy; Functional materials; Graph neural networks; Graph representations; Graph theory; Lithium; Lithium-ion batteries; Machine learning; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Message passing; Neural networks; Rechargeable batteries; Simulation; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-022-00863-y

Electron density ρ ( r → ) is the fundamental variable in the calculation of ground state energy with density functional theory (DFT). Beyond total energy, features and changes in ρ ( r → ) distributions are often used to capture critical physicochemical phenomena in functional materials. We present a machine learning framework for the prediction of ρ ( r → ) . The model is based on equivariant graph neural networks and the electron density is predicted at special query point vertices that are part of the message-passing graph, but only receive messages. The model is tested across multiple datasets of molecules (QM9), liquid ethylene carbonate electrolyte (EC) and LixNiyMnzCo(1-y-z)O2 lithium ion battery cathodes (NMC). For QM9 molecules, the accuracy of the proposed model exceeds typical variability in ρ ( r → ) obtained from DFT done with different exchange-correlation functionals. The accuracy on all three datasets is beyond state of the art and the computation time is orders of magnitude faster than DFT.