EGU22-6995, updated on 28 Mar 2022
EGU General Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

AI-based hydromorphological assessment of river restoration using UAV-remote sensing

Felix Dacheneder, Karen Schulz, and Andre Niemann
Felix Dacheneder et al.
  • Universität Duisburg-Essen, Institute of Hydraulic Engineering and Water Resources Management, Essen, Germany (

Many hydromorphological restoration measures have been applied on German water courses since 2000 the European water framework directive has been induced. The measures aim to improve the diversity of habitat alteration. Often a positive effect on aquatic biota can’t be detected, therefore implementation and the hydromorphological development of such measures can be questioned. But also the common monitoring and assessment methods for physical river habitat mapping can be questioned as they are limited in spatial scale and objectiveness of the mapper itself.

In the last decade, Unmaned Areal Vehicle (UAV) in combination with high-resolution sensors open new opportunities in a spatial and temporal scales. This research shows a case study of the river Lippe for the detection of hydromorphological habitat structures using Structure from Motion (SfM) and Deep learning based classification methods. In detail, this work discusses the difficulties of creating digital surface and orthomosaics from field survey data, but also shows results from a case study using a deep learning classification approach to identify physical river habitat structures.

How to cite: Dacheneder, F., Schulz, K., and Niemann, A.: AI-based hydromorphological assessment of river restoration using UAV-remote sensing, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-6995,, 2022.