EGU General Assembly 2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Using convolutional neural networks to detect giant landslides in the Patagonian Andean foreland

Elisabeth Schönfeldt1, Tomáš Pánek2, Diego Winocur3, and Oliver Korup1,4
Elisabeth Schönfeldt et al.
  • 1University of Potsdam, Institute of Geoscience, Potsdam, Germany (
  • 2University of Ostrava, Department of Physical Geography and Geoecology, Czech Republic
  • 3Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Departamento de Ciencias Geologicas, Argentina
  • 4University of Potsdam, Institute of Environmental Science and Geography, Germany

The Andean foreland of Patagonia features dozens of basaltic plateaus that are spread out from the Argentinean province of Neuquén south to Tierra del Fuego. The plateau margins are undermined by numerous giant slope failures that mostly involved a combination of lateral spreading and rotational sliding, running out up to several kilometres along the plateau margins. However, the overall extent of plateau margins affected by landsliding is still unknown, because manual mapping of such a large area (~500.000 km²) is time-consuming. Therefore, our goal is to test methods that support manual mapping by an automatic and objective detection of giant landslides. All of these landslides share very similar topographic features such as subparallel compression ridges and elongate depressions, distinguishing them in terms of their topographic and optical appearance from surrounding areas (e.g. plains or plateau tops). Using a catalogue of these features, we tested an image classification scheme using convolutional neural networks (CNNs). Our input data consist of Sentinel-2 optical data (20-m resolution) and topographic factors (surface roughness and curvature) acquired from TanDEM-X data (12-m resolution). We applied transfer learning, modifying the pre-existing CNN alexnet to test how well it is able to distinguish different geomorphic features such as unstable terrain from plateau tops or plains. Over 4000 training images were extracted from the Meseta Somuncurá, while the trained algorithm was tested at the Sierra Cuadrada. Both plateaus are part of the Northern Patagonia Massif. Preliminary results show that the modified algorithms performs reasonable and is able to distinguish between giant landslides and other geomorphic features. However, performance strongly depends on the training options of the stochastic gradient descent within the CNN and image quality of the training images, especially the quantity of images and their extracted location with respect to the plateau margin.

How to cite: Schönfeldt, E., Pánek, T., Winocur, D., and Korup, O.: Using convolutional neural networks to detect giant landslides in the Patagonian Andean foreland, EGU General Assembly 2021, online, 19–30 Apr 2021, EGU21-2728,, 2021.


Display file

Comments on the display

to access the discussion