Dresden 2020 – scientific programme
The DPG Spring Meeting in Dresden had to be cancelled! Read more ...
Parts | Days | Selection | Search | Updates | Downloads | Help
O: Fachverband Oberflächenphysik
O 42: Focus Session: Innovation in Machine learning PRocEsses for Surface Science (IMPRESS)
O 42.8: Invited Talk
Tuesday, March 17, 2020, 12:45–13:15, TRE Phy
Theory-informed Machine Learning for Interface Structure Reconstruction from Experimental Data — Eric Schwenker1, 2, Chaitanya Kolluru1, Spencer Hills1, Arun Mannodi Kanakkithodi1, Fatih Sen1, Michael Sternberg1, and •Maria Chan1 — 1Center for Nanoscale Materials, Argonne National Laboratory, Lemont IL, USA — 2Materials Science and Engineering, Northwestern University, Evanston IL, USA
Determining atomistic structure at interfaces is challenging because metastable interfaces are likely accessible under realistic conditions, rendering energy-only searches insufficient, and experimental data often give incomplete information. Therefore, neither theory nor experimental data alone is sufficient to determine these structures. In this talk, we will discuss how we use machine learning to combine experimental and theory-based data to determine interfacial structures.