Erik Loebel

CR Cryospheric Sciences

The 2021 Virtual Outstanding Student and PhD candidate Presentation (vOSPP) Award is awarded to Erik Loebel for the poster/PICO entitled:

Automated extraction of calving front locations from multi-spectral satellite imagery using deep learning: methodology and application to Greenland outlet glaciers (Loebel, E.; Schreinert, M.; Christmann, J.; Heidler, K.; Horwath, M.; Humbert, A.)

Click here to download the poster/PICO file.

Erik Loebel is a PhD student at Technische Universität Dresden under the supervision of Prof. Dr. Martin Horwath and Dr. Mirko Scheinert. As part of the “Artificial Intelligence for Cold Regions” (AI-CORE) project, his research aims at applying AI methods in earth observation and thereby breaking new ground for researching the cryosphere. In particular, he focuses on calving front detection and change pattern identification of outlet glaciers in Greenland.

His contribution at the virtual EGU General Assembly 2021 presented an automated workflow for extracting glacier calving front positions from optical Landsat-8 imagery utilizing deep learning methods. The workflow is based on semantic image segmentation using a Convolutional Neural Network as well as a unique set of multi-spectral, textural and topographic input features. Jointly with discussing the proposed methodology, he presents an exceedingly dense dataset for 20 of the most important Greenlandic outlet glaciers for the period from 2013 to 2021.