Inter-Research > MEPS > v681 > p197-210  
MEPS
Marine Ecology Progress Series

via Mailchimp

MEPS 681:197-210 (2022)  -  DOI: https://doi.org/10.3354/meps13912

Machine learning analysis reveals relationship between pomacentrid calls and environmental cues

Jill E. Munger1,8,*, Daniel P. Herrera2, Samara M. Haver1,3, Lynn Waterhouse4, Megan F. McKenna5,9, Robert P. Dziak6, Jason Gedamke7, Scott A. Heppell3, Joseph H. Haxel1,10

1Cooperative Institute for Marine Ecosystem and Resources Studies, NOAA Pacific Marine Environmental Laboratory and Oregon State University, Hatfield Marine Science Center, Newport, OR 97365, USA
2Portland, OR 97218, USA
3Department of Fisheries, Wildlife, and Conservation Sciences, Oregon State University, Corvallis, OR 97333, USA
4Daniel P. Haerther Center for Conservation and Research, John G. Shedd Aquarium, Chicago, IL 60605, USA
5Natural Sounds and Night Skies Division, National Park Service, Fort Collins, CO 80525, USA
6NOAA, Pacific Marine Environmental Laboratory, Newport, OR 97365, USA
7Office of Science and Technology, NOAA Fisheries, Silver Spring, MD 20910, USA
8Present address: Department of Fisheries, Wildlife, and Conservation Sciences, Oregon State University, Corvallis, OR 97333, USA
9Present address: Hopkins Marine Station, Stanford University, Pacific Grove, CA 93950, USA
10Present address: Pacific Northwest National Laboratory, Sequim, WA 98382, USA
*Corresponding author:

ABSTRACT: Sound production rates of fishes can be used as an indicator for coral reef health, providing an opportunity to utilize long-term acoustic recordings to assess environmental change. As acoustic datasets become more common, computational techniques need to be developed to facilitate analysis of the massive data files produced by long-term monitoring. Machine learning techniques demonstrate an advantage in the identification of fish sounds over manual sampling approaches. Here we evaluated the ability of convolutional neural networks to identify and monitor call patterns for pomacentrids (damselfishes) in a tropical reef region of the western Pacific. A stationary hydrophone was deployed for 39 mo (2014-2018) in the National Park of American Samoa to continuously record the local marine acoustic environment. A neural network was trained—achieving 94% identification accuracy of pomacentrids—to demonstrate the applicability of machine learning in fish acoustics and ecology. The distribution of sound production was found to vary on diel and interannual timescales. Additionally, the distribution of sound production was correlated with wind speed, water temperature, tidal amplitude, and sound pressure level. This research has broad implications for state-of-the-art acoustic analysis and promises to be an efficient, scalable asset for ecological research, environmental monitoring, and conservation planning.


KEY WORDS: Convolutional neural network · Passive acoustic monitoring · Fish acoustics · Damselfishes · American Samoa


Full text in pdf format
Supplementary material 
Cite this article as: Munger JE, Herrera DP, Haver SM, Waterhouse L and others (2022) Machine learning analysis reveals relationship between pomacentrid calls and environmental cues. Mar Ecol Prog Ser 681:197-210. https://doi.org/10.3354/meps13912

Export citation
Mail this link - Contents Mailing Lists - RSS
Facebook - - linkedIn