Simulations of disordered matter in 3D with the morphological autoregressive protocol (MAP) and convolutional neural networks.

Autor: Madanchi A; Department of Physics, McGill University, 3600 University St., Montreal, Quebec H3A 2T8, Canada., Kilgour M; Department of Chemistry, McGill University, 801 Sherbrooke St. W, Montreal, Quebec H3A 0B8, Canada., Zysk F; Dynamics of Condensed Matter and Center for Sustainable Systems Design, Chair of Theoretical Chemistry, University of Paderborn, Paderborn 33098, Germany., Kühne TD; Dynamics of Condensed Matter and Center for Sustainable Systems Design, Chair of Theoretical Chemistry, University of Paderborn, Paderborn 33098, Germany., Simine L; Department of Chemistry, McGill University, 801 Sherbrooke St. W, Montreal, Quebec H3A 0B8, Canada.
Jazyk: angličtina
Zdroj: The Journal of chemical physics [J Chem Phys] 2024 Jan 14; Vol. 160 (2).
DOI: 10.1063/5.0174615
Abstrakt: Disordered molecular systems, such as amorphous catalysts, organic thin films, electrolyte solutions, and water, are at the cutting edge of computational exploration at present. Traditional simulations of such systems at length scales relevant to experiments in practice require a compromise between model accuracy and quality of sampling. To address this problem, we have developed an approach based on generative machine learning called the Morphological Autoregressive Protocol (MAP), which provides computational access to mesoscale disordered molecular configurations at linear cost at generation for materials in which structural correlations decay sufficiently rapidly. The algorithm is implemented using an augmented PixelCNN deep learning architecture that, as we previously demonstrated, produces excellent results in 2 dimensions (2D) for mono-elemental molecular systems. Here, we extend our implementation to multi-elemental 3D and demonstrate performance using water as our test system in two scenarios: (1) liquid water and (2) samples conditioned on the presence of pre-selected motifs. We trained the model on small-scale samples of liquid water produced using path-integral molecular dynamics simulations, including nuclear quantum effects under ambient conditions. MAP-generated water configurations are shown to accurately reproduce the properties of the training set and to produce stable trajectories when used as initial conditions in quantum dynamics simulations. We expect our approach to perform equally well on other disordered molecular systems in which structural correlations decay sufficiently fast while offering unique advantages in situations when the disorder is quenched rather than equilibrated.
(© 2024 Author(s). Published under an exclusive license by AIP Publishing.)
Databáze: MEDLINE