18
IRUS Total
Downloads
  Altmetric

Characterising soundscapes across diverse ecosystems using a universal acoustic feature set

File Description SizeFormat 
soundscape_paper_accepted_with_figs.pdfAccepted version1.43 MBAdobe PDFView/Open
supp_audio_1.wavSupporting information1.94 MBUnknownView/Open
supp_audio_2.wavSupporting information752.52 kBUnknownView/Open
Title: Characterising soundscapes across diverse ecosystems using a universal acoustic feature set
Authors: Sethi, S
Jones, NS
Fulcher, B
Picinali, L
Clink, DJ
Klinck, H
Orme, CDLO
Wrege, P
Ewers, R
Item Type: Journal Article
Abstract: Natural habitats are being impacted by human pressures at an alarming rate. Monitoring these ecosystem-level changes often requires labor-intensive surveys that are unable to detect rapid or unanticipated environmental changes. Here we have developed a generalizable, data-driven solution to this challenge using eco-acoustic data. We exploited a convolutional neural network to embed soundscapes from a variety of ecosystems into a common acoustic space. In both supervised and unsupervised modes, this allowed us to accurately quantify variation in habitat quality across space and in biodiversity through time. On the scale of seconds, we learned a typical soundscape model that allowed automatic identification of anomalous sounds in playback experiments, providing a potential route for real-time automated detection of irregular environmental behavior including illegal logging and hunting. Our highly generalizable approach, and the common set of features, will enable scientists to unlock previously hidden insights from acoustic data and offers promise as a backbone technology for global collaborative autonomous ecosystem monitoring efforts.
Issue Date: 21-Jul-2020
Date of Acceptance: 10-Jun-2020
URI: http://hdl.handle.net/10044/1/80904
DOI: 10.1073/pnas.2004702117
ISSN: 0027-8424
Publisher: National Academy of Sciences
Start Page: 17049
End Page: 17055
Journal / Book Title: Proceedings of the National Academy of Sciences of USA
Volume: 117
Issue: 29
Copyright Statement: © 2020 The Author(s). Published under thePNAS license (https://www.pnas.org/authors/fees-and-licenses)
Sponsor/Funder: Rainforest Research Sdn Bhd
World Wide Fund for Nature (WWF)
Engineering & Physical Science Research Council (E
Natural Environment Research Council (NERC)
Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (E
Funder's Grant Number: LBEE_P34395
UCL Ref: 542177
EP/K503733/1
NE/L012456/1
EP/N014529/1
EP/R511547/1
Keywords: Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
machine learning
acoustic
soundscape
monitoring
ecology
BIG DATA
INDEXES
ECOLOGY
ACCURACY
acoustic
ecology
machine learning
monitoring
soundscape
Acoustics
Ecosystem
Environmental Monitoring
Firearms
Forestry
Machine Learning
Sound
Sound Spectrography
Speech
Sound Spectrography
Speech
Ecosystem
Environmental Monitoring
Acoustics
Sound
Forestry
Firearms
Machine Learning
Publication Status: Published
Online Publication Date: 2020-07-07
Appears in Collections:Mathematics
Applied Mathematics and Mathematical Physics
Dyson School of Design Engineering
Faculty of Natural Sciences
Faculty of Engineering