Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Machine learning analysis reveals relationship between pomacentrid calls and environmental cues

Journal Article · · Marine Ecology - Progress Series
DOI: https://doi.org/10.3354/meps13912 · OSTI ID:1907052
 [1];  [2];  [1];  [3];  [4];  [5];  [6];  [7];  [8]
  1. National Oceanic and Atmospheric Administration (NOAA), Newport, OR (United States). Pacific Marine Environmental Laboratory; Oregon State Univ., Corvallis, OR (United States)
  2. Independent Researcher, Portland, OR (United States)
  3. John G. Shedd Aquarium, Chicago, IL (United States)
  4. National Park Service, Fort Collins, CO (United States); Stanford University, Pacific Grove, CA (United States)
  5. National Oceanic and Atmospheric Administration (NOAA), Newport, OR (United States). Pacific Marine Environmental Laboratory
  6. National Oceanic and Atmospheric Administration (NOAA), Silver Spring, MD (United States). Office of Science and Technology
  7. Oregon State Univ., Corvallis, OR (United States)
  8. National Oceanic and Atmospheric Administration (NOAA), Newport, OR (United States). Pacific Marine Environmental Laboratory; Oregon State Univ., Newport, OR (United States); Pacific Northwest National Lab. (PNNL), Sequim, WA (United States)
+ Show Author Affiliations

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.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE; National Park Service; National Oceanic and Atmospheric Administration (NOAA)
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
1907052
Report Number(s):
PNNL-SA-159507
Journal Information:
Marine Ecology - Progress Series, Journal Name: Marine Ecology - Progress Series Vol. 681; ISSN 0171-8630
Publisher:
Inter-Research Science PublisherCopyright Statement
Country of Publication:
United States
Language:
English

References (44)

Diel, lunar and seasonal rhythms in the reproduction of two tropical damselfishes: Pomacentrus flavicauda and P. wardi journal January 1983
Diel and lunar patterns of reproduction in the Caribbean and Pacific sergeant major damselfishes Abudefduf saxatilis and A. troschelii journal August 1987
A re-evaluation of the diel feeding hypothesis for marine herbivorous fishes journal September 2002
Directional orientation of pomacentrid larvae to ambient reef sound journal March 2004
Relationships between structural complexity, coral traits, and reef fish assemblages journal January 2017
ImageNet Large Scale Visual Recognition Challenge journal April 2015
Basic principles of ROC analysis journal October 1978
Identification of fish vocalizations from ocean acoustic data journal September 2016
Monitoring long-term soundscape trends in U.S. Waters: The NOAA/NPS Ocean Noise Reference Station Network journal April 2018
Acoustic behavior of the damselfish Dascyllus albisella: behavioral and geographic variation journal December 1998
ORCA-SPOT: An Automatic Killer Whale Sound Detection Toolkit Using Deep Learning journal July 2019
Deep Machine Learning Techniques for the Detection and Classification of Sperm Whale Bioacoustics journal August 2019
Deep neural networks for automated detection of marine mammal species journal January 2020
Territorial vocalization in sympatric damselfish: acoustic characteristics and intruder discrimination journal February 2017
Evidence of the Lombard effect in fishes journal April 2014
Deep Residual Learning for Image Recognition conference June 2016
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups journal November 2012
What does a zero mean? Understanding false, random and structural zeros in ecology journal May 2019
Bioacoustic monitoring of animal vocal behavior for conservation journal June 2019
Acoustic communication in fishes: Temperature plays a role journal March 2018
Sound production in four damselfish (Dascyllus) species: phyletic relationships? journal July 2009
Why the damselfish Chromis chromis is a key species in the Mediterranean rocky littoral - a quantitative perspective journal March 2018
Acoustic Ambient Noise in the Ocean: Spectra and Sources journal December 1962
Humpback whale (Megaptera novaeangliae) song occurrence at American Samoa in long-term passive acoustic recordings, 2008–2009 journal October 2012
Brown meagre vocalization rate increases during repetitive boat noise exposures: A possible case of vocal compensation journal November 2012
Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish journal December 2015
Comparison of passive acoustic soniferous fish monitoring with supervised and unsupervised approaches journal April 2018
Automatic fish sounds classification journal May 2018
Beluga whale acoustic signal classification using deep learning neural network models journal March 2020
Transfer learning for efficient classification of grouper sound journal September 2020
Impacts of Biodiversity Loss on Ocean Ecosystem Services journal November 2006
Climate Change Impacts on Marine Ecosystems journal January 2012
Observational Study of Behavior: Sampling Methods journal January 1974
Sound production and spectral hearing sensitivity in the Hawaiian sergeant damselfish, Abudefduf abdominalis journal November 2007
Regression Models for Count Data in R journal January 2008
Cohabitation of Competing Territorial Damselfishes on a Caribbean Coral Reef journal August 1984
Coral size, health and structural complexity: effects on the ecology of a coral reef damselfish journal June 2012
Effects of tidal current-induced flow on reef fish behaviour and function on a subtropical rocky reef journal November 2016
The Effect of Algal-Gardening Damselfish on the Resilience of the Mesoamerican Reef journal July 2019
Comparing the Underwater Soundscapes of Four U.S. National Parks and Marine Sanctuaries journal August 2019
Fish Spawning Aggregations Dynamics as Inferred From a Novel, Persistent Presence Robotic Approach journal January 2020
A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset journal March 2021
Automatic Taxonomic Classification of Fish Based on Their Acoustic Signals journal December 2016
The Distribution of Planktivorous Damselfishes (Pomacentridae) on the Great Barrier Reef and the Relative Influences of Habitat and Predation journal February 2019

Similar Records

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
American Samoa
Damselfishes
convolutional neural network
fish acoustics
passive acoustic monitoring