A systematic approach to generating accurate neural network potentials: the case of carbon

• Published in: npj computational materials Vol. 7; no. 1; pp. 1 - 13
• Main Authors: Shaidu, Yusuf, Küçükbenli, Emine, Lot, Ruggero, Pellegrini, Franco, Kaxiras, Efthimios, de Gironcoli, Stefano
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 14.04.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/1034/1035; 639/301/1034/1037; 639/301/119/1002; 639/766/119/1002; Artificial neural networks; Carbon; Characterization and Evaluation of Materials; Chemistry and Materials Science; Computational Intelligence; Construction; Crystal structure; Data analysis; Diamonds; Elastic properties; First principles; Graphene; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Neural networks; Potential energy; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-021-00508-6

Availability of affordable and widely applicable interatomic potentials is the key needed to unlock the riches of modern materials modeling. Artificial neural network-based approaches for generating potentials are promising; however, neural network training requires large amounts of data, sampled adequately from an often unknown potential energy surface. Here we propose a self-consistent approach that is based on crystal structure prediction formalism and is guided by unsupervised data analysis, to construct an accurate, inexpensive, and transferable artificial neural network potential. Using this approach, we construct an interatomic potential for carbon and demonstrate its ability to reproduce first principles results on elastic and vibrational properties for diamond, graphite, and graphene, as well as energy ordering and structural properties of a wide range of crystalline and amorphous phases.