Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods.
Passive acoustic monitoring (PAM) has proven a powerful tool for the study of marine mammals, allowing for documentation of biologically relevant factors such as movement patterns or animal behaviors while remaining largely non-invasive and cost effective. From 2008-2019, a set of PAM recordings cov...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0266424 |
| _version_ | 1811343781013749760 |
|---|---|
| author | Morgan A Ziegenhorn Kaitlin E Frasier John A Hildebrand Erin M Oleson Robin W Baird Sean M Wiggins Simone Baumann-Pickering |
| author_facet | Morgan A Ziegenhorn Kaitlin E Frasier John A Hildebrand Erin M Oleson Robin W Baird Sean M Wiggins Simone Baumann-Pickering |
| author_sort | Morgan A Ziegenhorn |
| collection | DOAJ |
| description | Passive acoustic monitoring (PAM) has proven a powerful tool for the study of marine mammals, allowing for documentation of biologically relevant factors such as movement patterns or animal behaviors while remaining largely non-invasive and cost effective. From 2008-2019, a set of PAM recordings covering the frequency band of most toothed whale (odontocete) echolocation clicks were collected at sites off the islands of Hawai'i, Kaua'i, and Pearl and Hermes Reef. However, due to the size of this dataset and the complexity of species-level acoustic classification, multi-year, multi-species analyses had not yet been completed. This study shows how a machine learning toolkit can effectively mitigate this problem by detecting and classifying echolocation clicks using a combination of unsupervised clustering methods and human-mediated analyses. Using these methods, it was possible to distill ten unique echolocation click 'types' attributable to regional odontocetes at the genus or species level. In one case, auxiliary sightings and recordings were used to attribute a new click type to the rough-toothed dolphin, Steno bredanensis. Types defined by clustering were then used as input classes in a neural-network based classifier, which was trained, tested, and evaluated on 5-minute binned data segments. Network precision was variable, with lower precision occurring most notably for false killer whales, Pseudorca crassidens, across all sites (35-76%). However, accuracy and recall were high (>96% and >75%, respectively) in all cases except for one type of short-finned pilot whale, Globicephala macrorhynchus, call class at Kaua'i and Pearl and Hermes Reef (recall >66%). These results emphasize the utility of machine learning in analysis of large PAM datasets. The classifier and timeseries developed here will facilitate further analyses of spatiotemporal patterns of included toothed whales. Broader application of these methods may improve the efficiency of global multi-species PAM data processing for echolocation clicks, which is needed as these datasets continue to grow. |
| first_indexed | 2024-04-13T19:34:55Z |
| format | Article |
| id | doaj.art-d87f3e7d8941401b8a80bc6d1b811bbe |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-13T19:34:55Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-d87f3e7d8941401b8a80bc6d1b811bbe2022-12-22T02:33:03ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01174e026642410.1371/journal.pone.0266424Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods.Morgan A ZiegenhornKaitlin E FrasierJohn A HildebrandErin M OlesonRobin W BairdSean M WigginsSimone Baumann-PickeringPassive acoustic monitoring (PAM) has proven a powerful tool for the study of marine mammals, allowing for documentation of biologically relevant factors such as movement patterns or animal behaviors while remaining largely non-invasive and cost effective. From 2008-2019, a set of PAM recordings covering the frequency band of most toothed whale (odontocete) echolocation clicks were collected at sites off the islands of Hawai'i, Kaua'i, and Pearl and Hermes Reef. However, due to the size of this dataset and the complexity of species-level acoustic classification, multi-year, multi-species analyses had not yet been completed. This study shows how a machine learning toolkit can effectively mitigate this problem by detecting and classifying echolocation clicks using a combination of unsupervised clustering methods and human-mediated analyses. Using these methods, it was possible to distill ten unique echolocation click 'types' attributable to regional odontocetes at the genus or species level. In one case, auxiliary sightings and recordings were used to attribute a new click type to the rough-toothed dolphin, Steno bredanensis. Types defined by clustering were then used as input classes in a neural-network based classifier, which was trained, tested, and evaluated on 5-minute binned data segments. Network precision was variable, with lower precision occurring most notably for false killer whales, Pseudorca crassidens, across all sites (35-76%). However, accuracy and recall were high (>96% and >75%, respectively) in all cases except for one type of short-finned pilot whale, Globicephala macrorhynchus, call class at Kaua'i and Pearl and Hermes Reef (recall >66%). These results emphasize the utility of machine learning in analysis of large PAM datasets. The classifier and timeseries developed here will facilitate further analyses of spatiotemporal patterns of included toothed whales. Broader application of these methods may improve the efficiency of global multi-species PAM data processing for echolocation clicks, which is needed as these datasets continue to grow.https://doi.org/10.1371/journal.pone.0266424 |
| spellingShingle | Morgan A Ziegenhorn Kaitlin E Frasier John A Hildebrand Erin M Oleson Robin W Baird Sean M Wiggins Simone Baumann-Pickering Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. PLoS ONE |
| title | Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. |
| title_full | Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. |
| title_fullStr | Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. |
| title_full_unstemmed | Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. |
| title_short | Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods. |
| title_sort | discriminating and classifying odontocete echolocation clicks in the hawaiian islands using machine learning methods |
| url | https://doi.org/10.1371/journal.pone.0266424 |
| work_keys_str_mv | AT morganaziegenhorn discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT kaitlinefrasier discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT johnahildebrand discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT erinmoleson discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT robinwbaird discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT seanmwiggins discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods AT simonebaumannpickering discriminatingandclassifyingodontoceteecholocationclicksinthehawaiianislandsusingmachinelearningmethods |