First-principles NMR of oxide glasses boosted by machine learning

Abstract

Solid-State NMR has established itself as a cutting-egde spectroscopy for elucidating the structure of oxide glasses thanks to several decades of methodological and instrumental progresses. First-principles calculations of NMR properties combined with molecular dynamics (MD) simulations provides a powerful complementing approach for the interpretation of the NMR data although they still suffer from limitations in terms of size, time and high consumption of computational resources. We address this challenge by developing a machine-learning framework to boost predictive modelling of NMR spectra. We use kernel ridge regression techniques (least-square support vector regression and linear ridge regression) combined with the smooth overlap of atomic position (SOAP) atom-centered descriptors to efficiently predict NMR interactions: isotropic magnetic shielding and the electric field gradient (EFG) tensor. As illustrated in this work, this approach enables the simulation of MAS and MQMAS NMR spectra of very large models (more than 10000 atoms) and an efficient averaging of NMR properties over MD trajectories of nanoseconds for incorporating finite temperature effects, at computational cost of classical MD simulation. We illustrate these advances on sodium silicate glasses (SiO2-Na2O). NMR parameters (isotropic chemical shift and electric field gradient) could be predicted with an accuracy of 1 to 2% in terms of the total span of the NMR parameter values. To include vibrational effects, an approach is proposed by scaling the EFG tensor in NMR simulations with a factor obtained from the time auto-correlation functions computed on MD trajectory.