Scripps Institution of Oceanography, University of California San Diego, La Jolla, California, United States of America.
NOAA Fisheries Pacific Islands Fisheries Science Center, Honolulu, Hawaii, United States of America.
PLoS One. 2022 Apr 12;17(4):e0266424. doi: 10.1371/journal.pone.0266424. eCollection 2022.
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.
被动声学监测（PAM）已被证明是研究海洋哺乳动物的有力工具，它允许记录与生物学相关的因素，如运动模式或动物行为，同时在很大程度上保持非侵入性和具有成本效益。从 2008 年到 2019 年，在夏威夷、考艾和珍珠和赫尔姆斯礁的岛屿附近的一系列 PAM 记录中，收集了涵盖大多数齿鲸（齿鲸目）回声定位点击的频段。然而，由于该数据集的规模和物种级声学分类的复杂性，多年来多物种分析尚未完成。本研究展示了机器学习工具包如何通过使用无监督聚类方法和人类介导的分析相结合来检测和分类回声定位点击，从而有效地解决这个问题。使用这些方法，可以将归因于区域齿鲸属或种水平的十个独特的回声定位点击“类型”提取出来。在一个案例中，辅助观测和记录被用来将一种新的点击类型归因于糙齿海豚，Steno bredanensis。聚类定义的类型随后被用作基于神经网络的分类器的输入类，该分类器在 5 分钟的分箱数据段上进行训练、测试和评估。网络精度是可变的，在所有站点中，假虎鲸（Pseudorca crassidens）的精度最低（35-76%）。然而，除了考艾和珍珠和赫尔姆斯礁的一种短鳍领航鲸（Globicephala macrorhynchus）的叫声类（召回率>66%）外，所有情况下的准确性和召回率都很高（分别为>96%和>75%）。这些结果强调了机器学习在分析大型 PAM 数据集方面的效用。这里开发的分类器和时间序列将促进对包括齿鲸在内的时空模式的进一步分析。这些方法的更广泛应用可能会提高全球多物种 PAM 数据处理回声定位点击的效率，随着这些数据集的不断增长，这是必要的。
