Machine learning with taxonomic family delimitation aids in the classification of ephemeral beaked whale events in passive acoustic monitoring.

Passive acoustic monitoring is an essential tool for studying beaked whale populations. This approach can monitor elusive and pelagic species, but the volume of data it generates has overwhelmed researchers' ability to quantify species occurrence for effective conservation and management efforts. Automation of data processing is crucial, and machine learning algorithms can rapidly identify species using their sounds. Beaked whale acoustic events, often infrequent and ephemeral, can be missed when co-occurring with signals of more abundant, and acoustically active species that dominate acoustic recordings. Prior efforts on large-scale classification of beaked whale signals with deep neural networks (DNNs) have approached the class as one of many classes, including other odontocete species and anthropogenic signals. That approach tends to miss ephemeral events in favor of more common and dominant classes. Here, we describe a DNN method for improved classification of beaked whale species using an extensive dataset from the western North Atlantic. We demonstrate that by training a DNN to focus on the taxonomic family of beaked whales, ephemeral events were correctly and efficiently identified to species, even with few echolocation clicks. By retrieving ephemeral events, this method can support improved estimation of beaked whale occurrence in regions of high odontocete acoustic activity.

Beaked whales demonstrate a marked acoustic response to the use of shipboard echosounders.

The use of commercial echosounders for scientific and industrial purposes is steadily increasing. In addition to traditional navigational and fisheries uses, commercial sonars are used extensively for oceanographic research, benthic habitat mapping, geophysical exploration, and ecosystem studies. Little is known about the effects of these acoustic sources on marine animals, though several studies have already demonstrated behavioural responses of cetaceans to shipboard echosounders. Some species of cetaceans are known to be particularly sensitive to acoustic disturbance, including beaked whales. In 2011 and 2013, we conducted cetacean assessment surveys in the western North Atlantic in which a suite of Simrad EK60 echosounders was used to characterize the distribution of prey along survey tracklines. Echosounders were alternated daily between active and passive mode, to determine whether their use affected visual and acoustic detection rates of beaked whales. A total of 256 groups of beaked whales were sighted, and 118 definitive acoustic detections were recorded. Regression analyses using generalized linear models (GLM) found that sea state and region were primary factors in determining visual sighting rates, while echosounder state was the primary driver for acoustic detections, with significantly fewer detections (only 3%) occurring when echosounders were active. These results indicate that beaked whales both detect and change their behaviour in response to commercial echosounders. The mechanism of this response is unknown, but could indicate interruption of foraging activity or vessel avoidance, with potential implications for management and mitigation of anthropogenic impacts.