EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated River Substrate Mapping From Sonar Imagery With Machine Learning

C. S. Bodine, D. Buscombe, T. D. Hocking

Journal of Geophysical Research: Machine Learning and Computation · 2024-09 · 1 (3)

DOI: 10.1029/2024jh000135 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Geophysical Research: Machine Learning and Computation, online erschienen am 09.07.2024. Verfasst von C. S. Bodine und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Fish and Wildlife Service.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge of the variation and distribution of substrates at large spatial extents in aquatic systems, particularly rivers, is severely lacking, impeding species conservation and ecosystem restoration efforts. Recreation‐grade side‐scan sonar (SSS) instruments have demonstrated their unparalleled value as a low‐cost scientific instrument capable of efficient and rapid imaging of the benthic environment. However, existing methods for generating georeferenced data sets from these instruments, especially substrate maps, remain a barrier of adoption for scientific inquiry due to the high degree of human intervention and required expertise. To address this shortcoming, we introduced PING‐Mapper, an open‐source and freely available Python‐based software for automatically generating geospatial benthic data sets from popular Humminbird ® instruments reproducibly. The previously released Version 1.0 of the software provided automated workflows for exporting georeferenced sonar imagery. This study extends functionality with version 2.0 by incorporating semantic segmentation with deep neural networks to reproducibly map substrates at large spatial extents. We present a novel approach for generating label‐ready sonar data sets, creating label‐image training sets, and model training with transfer learning; all with open‐source tools. The six‐class substrate model achieves an overall accuracy of 78% and the best performing class achieves 91%. Grouping substrates into three classes further improves the overall accuracy (87%) and best performing class accuracy (94%). Additional workflows enable masking sonar shadows, calculating independent bed picks and correcting attenuation effects in the imagery to improve interpretability. This software provides an improved mechanism for automatically mapping substrate distribution from recreation‐grade SSS systems, thereby lowering the barrier for inclusion in wider aquatic research.

Förderung

  • U.S. Fish and Wildlife Service

Zitieren

APA

Bodine, C. S., Buscombe, D., & Hocking, T. D. (2024). Automated River Substrate Mapping From Sonar Imagery With Machine Learning. Journal of Geophysical Research: Machine Learning and Computation, 1(3). https://doi.org/10.1029/2024jh000135

Vancouver

Bodine CS, Buscombe D, Hocking TD. Automated River Substrate Mapping From Sonar Imagery With Machine Learning. Journal of Geophysical Research: Machine Learning and Computation. 2024;1(3). doi:10.1029/2024jh000135

BibTeX
@article{Bodine2024,
  author = {Bodine, C. S. and Buscombe, D. and Hocking, T. D.},
  title = {Automated River Substrate Mapping From Sonar Imagery With Machine Learning},
  journal = {Journal of Geophysical Research: Machine Learning and Computation},
  year = {2024},
  volume = {1},
  number = {3},
  doi = {10.1029/2024jh000135}
}
Kostenlos starten →