Accelerating NMR Shielding Calculations Through Machine Learning Methods: Application to Magnesium Sodium Silicate Glasses
ChemPhysChem · 18.11.2024 · 25 (22)
DOI: 10.1002/cphc.202300782 ↗Kurz gefasst
Fachartikel in der Zeitschrift ChemPhysChem, online erschienen am 22.09.2024. Verfasst von Marco Bertani und 3 weiteren Autor:innen. Beteiligte Einrichtung: University of Modena and Reggio Emilia, Department of Chemical and Geological Sciences, via Campi 103, Modena, Italy. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PNRR MUR project, NVIDIA.
Abstract (Originalsprache)
In this work, we have applied the Kernel Ridge Regression (KRR) method using a Least Square Support Vector Regression (LSSVR) approach for the prediction of the NMR isotropic magnetic shielding (σ iso ) of active nuclei ( 17 O, 23 Na, 25 Mg, and 29 Si) in a series of (Mg, Na)–silicate glasses. The Machine Learning (ML) algorithm has been trained by mapping the local environment of each atom described by the Smooth Overlap of Atomic Position (SOAP) descriptor with isotropic chemical shielding values computed with DFT using the Gauge‐Included‐Projector‐Augmented‐Wave (GIPAW) approach. The influence of different training datasets generated through molecular dynamics simulations at various temperatures and with different inter‐atomic potentials has been tested and we demonstrate the importance of a wide exploration of the configurational space to enhance the transferability of the ML‐regressor. Finally, the trained ML‐regressor has been used to simulate the 29 Si MAS NMR spectra of systems containing up to 20000 atoms by averaging hundreds of configurations extracted from classical MD simulations to account for thermal vibrations. This ML approach is a powerful tool for the interpretation of NMR spectra using relatively large systems at a fraction of the computational time required by quantum mechanical calculations which are of high computational cost.
Autor:innen und Institutionen
- University of Modena and Reggio Emilia, Department of Chemical and Geological Sciences, via Campi 103, Modena, Italy.
- Université Paris-Saclay, CEA, CNRS, NIMBE, 91191, Gif-sur-Yvette, France.
ORCID-Profile: Marco Bertani, Francesco Faglioni, Thibault Charpentier
Förderung
- PNRR MUR project
- NVIDIA
Zitieren
APA
Bertani, M., Pedone, A., Faglioni, F., & Charpentier, T. (2024). Accelerating NMR Shielding Calculations Through Machine Learning Methods: Application to Magnesium Sodium Silicate Glasses. ChemPhysChem, 25(22). https://doi.org/10.1002/cphc.202300782
Vancouver
Bertani M, Pedone A, Faglioni F, Charpentier T. Accelerating NMR Shielding Calculations Through Machine Learning Methods: Application to Magnesium Sodium Silicate Glasses. ChemPhysChem. 2024;25(22). doi:10.1002/cphc.202300782
BibTeX
@article{Bertani2024,
author = {Bertani, Marco and Pedone, Alfonso and Faglioni, Francesco and Charpentier, Thibault},
title = {Accelerating NMR Shielding Calculations Through Machine Learning Methods: Application to Magnesium Sodium Silicate Glasses},
journal = {ChemPhysChem},
year = {2024},
volume = {25},
number = {22},
doi = {10.1002/cphc.202300782}
}
EUVIMED