Modelling amorphous materials with machine-learning-driven interatomic potentials

Volker Deringer

Department of Engineering, University of Cambridge, CB2 1PZ, UK

Abstract

Understanding the links between atomic structure, bonding, and properties in materials is a formidable task. Quantum-mechanical atomistic simulations, prominently based on density-functional theory (DFT), have played important roles in this – but they are computationally expensive, and can describe complex materials only in small model systems. Novel interatomic potentials based on machine learning (ML) have recently garnered a lot of attention in the computational materials-science community: they achieve close-to DFT accuracy but at only a fraction of the cost.

In this talk, I will argue that ML-based interatomic potentials are particularly useful for studying materials with complex structures, such as amorphous (non-crystalline) solids. I will first describe an ML potential for amorphous carbon [1], with a special view on what is needed to generate and validate ML potentials for the amorphous state. I will then present an application to porous and partly "graphitised" carbon structures, which are relevant for applications in batteries and supercapacitors [2]; this includes a new ML methodology for simulating the movement of Li ions in such materials [3]. Finally, I will present recent work on amorphous silicon (a-Si), another prototypical non-crystalline material – where ML-driven simulations allowed us to unlock long simulation times and accurate atomistic structures [4], and “machine-learned” atomic energies were shown to permit a chemical interpretation, suggesting a more general approach to modelling and understanding the intricate liquid and amorphous phases of silicon [5].

[1] V. L. Deringer, G. Csányi, Phys. Rev. B 95, 094203 (2017).

[2] V. L. Deringer, C. Merlet, Y. Hu, T. H. Lee, J. A. Kattirtzi, O. Pecher, G. Csányi, S. R. Elliott, C. P. Grey, Chem. Commun. 54, 5988 (2018).

[3] S. Fujikake, V. L. Deringer, T. H. Lee, M. Krynski, S. R. Elliott, G. Csányi, J. Chem. Phys. 148, 241714 (2018).

[4] V. L. Deringer, N. Bernstein, A. P. Bartók, R. N. Kerber, L. E. Marbella, C. P. Grey, S. R. Elliott, G. Csányi, J. Phys. Chem. Lett. 9, 2879 (2018).

[5] N. Bernstein, B. Bhattarai, G. Csányi, D. A. Drabold, S. R. Elliott, V. L. Deringer, Angew. Chem. Int. Ed., in press, DOI: 10.1002/anie.201902625 (2019).