EGU22-1445
https://doi.org/10.5194/egusphere-egu22-1445
EGU General Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Machine learning for boulder detection in acoustic data

Peter Feldens1, Svenja Papenmeier1, Sören Themann2, Agata Feldens2, and Patrick Westfeld3
Peter Feldens et al.
  • 1IOW, Marine Geology, Warnemünde, Germany
  • 2Subsea Europe Services, Halstenbek, Germany
  • 3Federal Maritime and Hydrographic Agency (BSH), Rostock, Germany

Sublittoral hard substrates, for example formed by blocks and boulders, are hotspots for marine biodiversity, especially for benthic communities. Knowledge on boulder occurrence is also important for marine and coastal management, including offshore wind parks and safety of navigation. The occurrence of boulders have to be reported by member states to the European Union. Typically, boulders are located by acoustic surveys with multibeam echo sounders and side scan sonars. The manual interpretation of these data is subjective and time consuming. This presentation reports on recent work concerned with the detection of boulders in different acoustic datasets by convolutional neural networks, highlighting current approaches, challenges and future opportunities.

How to cite: Feldens, P., Papenmeier, S., Themann, S., Feldens, A., and Westfeld, P.: Machine learning for boulder detection in acoustic data, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-1445, https://doi.org/10.5194/egusphere-egu22-1445, 2022.

Comments on the display material

to access the discussion