Sensing ecosystem dynamics via audio source separation: A case study of marine soundscapes off northeastern Taiwan.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Subject Terms:
    • Abstract:
      Remote acquisition of information on ecosystem dynamics is essential for conservation management, especially for the deep ocean. Soundscape offers unique opportunities to study the behavior of soniferous marine animals and their interactions with various noise-generating activities at a fine temporal resolution. However, the retrieval of soundscape information remains challenging owing to limitations in audio analysis techniques that are effective in the face of highly variable interfering sources. This study investigated the application of a seafloor acoustic observatory as a long-term platform for observing marine ecosystem dynamics through audio source separation. A source separation model based on the assumption of source-specific periodicity was used to factorize time-frequency representations of long-duration underwater recordings. With minimal supervision, the model learned to discriminate source-specific spectral features and prove to be effective in the separation of sounds made by cetaceans, soniferous fish, and abiotic sources from the deep-water soundscapes off northeastern Taiwan. Results revealed phenological differences among the sound sources and identified diurnal and seasonal interactions between cetaceans and soniferous fish. The application of clustering to source separation results generated a database featuring the diversity of soundscapes and revealed a compositional shift in clusters of cetacean vocalizations and fish choruses during diurnal and seasonal cycles. The source separation model enables the transformation of single-channel audio into multiple channels encoding the dynamics of biophony, geophony, and anthropophony, which are essential for characterizing the community of soniferous animals, quality of acoustic habitat, and their interactions. Our results demonstrated the application of source separation could facilitate acoustic diversity assessment, which is a crucial task in soundscape-based ecosystem monitoring. Future implementation of soundscape information retrieval in long-term marine observation networks will lead to the use of soundscapes as a new tool for conservation management in an increasingly noisy ocean. Author summary: Understanding the status of biodiversity and its changing patterns is crucial for conservation management. Ecological assessment in deep-sea environments is challenging owning to the limited accessibility and visibility. Nevertheless, we can listen to underwater sounds to investigate the acoustic behaviors of marine animals. This study applied machine learning techniques to analyze underwater recordings transmitted from a deep seafloor observatory off northeastern Taiwan. In particular, our computational approach does not require preexisting labels in the procedure of model building. The model can automatically learn acoustic features and effectively separate sounds of marine mammals, fishes, and shipping activities with minimal supervision. The analysis of 2.5 years of audio data revealed that the studied continental shelf environment has a high diversity of sound-producing animals, and the community structure changes with diurnal, lunar, and seasonal cycles. The applied techniques also generated a database of environmental and anthropogenic sounds, which can facilitate future investigations on how human activities affect the acoustic environment and biodiversity. Our technique is entirely based on passive acoustics, which minimizes interference with animals. It also transforms audio recordings into highly interpretable ecological data, which can be useful for tracking changes in marine biodiversity. [ABSTRACT FROM AUTHOR]
    • Abstract:
      Copyright of PLoS Computational Biology is the property of Public Library of Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)