Regensburg 2025 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

MM: Fachverband Metall- und Materialphysik

MM 31: Data-driven Materials Science: Big Data and Worksflows

MM 31.4: Vortrag

Donnerstag, 20. März 2025, 15:45–16:00, H10

Advancing chemical shielding predictions in organic solids — •Matthias Kellner and Michele Ceriotti — École Polytech- nique Fédérale de Lausanne, 1015 Lausanne, Switzerland

In this presentation, we showcase our recent advancements in machine learning for predicting chemical shieldings in organic solids. Leveraging symmetry-adapted machine learning models, our updated infrastructure facilitates the accurate prediction of chemical shielding anisotropy and enables structure optimization driven by chemical shielding gradients. We will highlight how integrating machine learning potentials with property prediction models provides unique insights into atomistic processes, offering a powerful framework for exploring the complex behavior of organic materials.

Keywords: NMR; Machine Learning