Dresden 2020 – wissenschaftliches Programm
Die DPG-Frühjahrstagung in Dresden findet nicht statt! Lesen Sie mehr ...
O 42: Focus Session: Innovation in Machine learning PRocEsses for Surface Science (IMPRESS)
Dienstag, 17. März 2020, 10:30–13:15, TRE Phy
Self-learning and -improving algorithms, more-commonly referred to known as *machine learning*, are being increasingly used for various applications in surface science, both in theory and experiment. On the experimental side, they hold great promise to automate tedious, repetitive tasks (for example in image recognition) or allow to determine automated procedures to manipulate interfaces with STM tips. Computationally, machine learning algorithms provide the means to significantly speed up calculations without (significant) loss of accuracy or even to extract the physics determining specific processes (such as structure formations) from comparatively small data sets. The aim of this session is to provide a focussed overview over the recent applications and development of machine learning algorithms for surface science applications.
Organizers: Oliver Hoffmann (TU Graz), Patrick Rinke (Aalto University), Milica Todorović (Aaalto University)
|10:30||O 42.1||Hauptvortrag: Exploring the Design Space of Organic Semiconductors with Machine Learning — •Harald Oberhofer|
|11:00||O 42.2||Hauptvortrag: Machine learning for molecular nanorobotics — •Christian Wagner|
|11:30||O 42.3||The search of new catalysts for an OCM reaction based on CO2 adsorption properties using data mining technique — •Aliaksei Mazheika, Frank Rosowski, and Ralph Kraehnert|
|11:45||O 42.4||Symmetry-adapted neural network representations of electronic friction to simulate nonadiabatic dynamics at metal surfaces — •Reinhard J Maurer, Yaolong Zhang, and Bin Jiang|
|12:00||O 42.5||SAMPLE: Surface structure search enabled by coarse graining and statistical learning — •Lukas Hörmann, Andreas Jeindl, Alexander T. Egger, and Oliver T. Hofmann|
|12:15||O 42.6||(Re)interpreting TCNE adsorption on Cu(111) with machine learning — Alexander Egger, Lukas Hörmann, Andreas Jeindl, Milica Todorovic, Patrick Rinke, and •Oliver T. Hofmann|
|12:30||O 42.7||Chemicaly reasonable models for automatic interpretation of AFM images — •Prokop Hapala, Niko Oinonen, Fedor Urtev, Benjamin Alldritt, Ondrej Krejci, Filippo F. Canova, Fabian Schulz, Juho Kannala, Peter Liljeroth, and Adam S. Foster|
|12:45||O 42.8||Hauptvortrag: Theory-informed Machine Learning for Interface Structure Reconstruction from Experimental Data — Eric Schwenker, Chaitanya Kolluru, Spencer Hills, Arun Mannodi Kanakkithodi, Fatih Sen, Michael Sternberg, and •Maria Chan|