Líffræðifélag Íslands - biologia.is
Líffræðiráðstefnan 2023
Höfundar / Authors: Lieke Ponsioen (1), Kalina H. Kapralova (2), Fredrik Holm (1), Benjamin D. Hennig (1)
Starfsvettvangur / Affiliations: (1) University of Iceland, (2) Institute for Experimental pathology at Keldur
Kynnir / Presenter: Lieke Ponsioen
Salmonids are especially vulnerable during their embryonic development, but monitoring of
their spawning grounds is rare and often relies on manual counting of their nests (redds).
This method, however, is prone to sampling errors resulting in over- or underestimations of
redd counts. Salmonid spawning habitat in shallow water areas can be distinguished by
their visible reflection which makes the use of standard unmanned aerial vehicles (UAV) a
viable option for their mapping. Here, we aimed to develop a standardised approach to
detect salmonid spawning habitat that is easy and low-cost. We used a semi-automated
approach by applying supervised classification techniques to UAV derived RGB imagery
from two contrasting lakes in Iceland. For both lakes six endmember classes were obtained
with high accuracies. Most importantly, producer’s and user’s accuracy for classifying
spawning redds was >90% after applying post-classification improvements for both study
areas. What we are proposing here is an entirely new approach for monitoring spawning
habitats which will address some the major shortcomings of the widely used redd count
method e.g. collecting and analysing large amounts of data cost and time efficiently, limiting
observer bias, and allowing for precise quantification over different temporal and spatial
scales.