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

MM: Fachverband Metall- und Materialphysik

MM 3: Data-driven Materials Science: Big Data and Worksflows

MM 3.10: Vortrag

Montag, 17. März 2025, 12:45–13:00, H10

Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Stable Oxides for Catalytic Applications — •Akhil S. Nair, Lucas Foppa, and Matthias Scheffler — The NOMAD Laboratory at the FHI of the Max Planck Society, Berlin, Germany

AI-driven workflows will accelerate materials discovery by efficiently guiding experiments or simulations towards materials with desired properties. However, probabilistic AI approaches commonly used in these workflows are limited by the relatively small size of high-quality datasets and they rely on typically unknown, low-dimensional representations. Herein, we discuss the recent advancements in applying symbolic regression based on the sure-independence screening and sparsifying operator (SISSO) approach within iterative frameworks for materials discovery. This involves an ensemble approach for the uncertainty quantification of SISSO models as well as the development of optimization strategies to efficiently explore promising regions of the materials space. These developments present an opportunity to integrate SISSO into sequential-learning workflows for materials discovery. Importantly, SISSO provides materials-property maps covering the entire materials space, further reducing the risk that the workflow misses promising materials that were overlooked in the initial dataset. We demonstrate the effectiveness of the SISSO-guided workflows by identifying stable oxides for catalytic applications.

Keywords: Materials Discovery; Symbolic regression; SISSO; Uncertainty quantification