The first record of killer whale (Orcinus orca) predation on false killer whales (Pseudorca crassidens) is reported here. On 25 March 2010, a group of 50 to 60 false killer whales, including approximately 15 calves and accompanied by three to five bottlenose dolphins (Tursiops sp.), were sighted in the Bay of Islands, New Zealand. Within 30 min, they were approached by a group of approximately eight killer whales. Five false killer whales were attacked, with at least three rammed from below, forcing them out of the water. After 29 min, the killer whales were milling at the surface and feeding on the carcass of a false killer whale calf, possibly the only individual killed. The killer whales had prolific fresh and healed oval wounds, which were attributed to cookie cutter shark (Isistius sp.) bites.

On a global scale, false killer whales (Pseudorca crassidens) remain one of the lesser‐known delphinids. The occurrence, site fidelity, association patterns, and presence/absence of foraging in waters off northeastern New Zealand are examined from records collected between 1995 and 2012. The species was rarely encountered; however, of the 61 distinctive, photo‐identified individuals, 88.5% were resighted, with resightings up to 7 yr after initial identification, and movements as far as 650 km documented. Group sizes ranged from 20 to ca. 150. Results indicate that all individuals are linked in a single social network. Most observations were recorded in shallow (<100 m) nearshore waters. Occurrence in these continental shelf waters is likely seasonal, coinciding with the shoreward flooding of a warm current. During 91.5% of encounters, close interspecific associations with common bottlenose dolphins (Tursiops truncatus) were observed. Photo‐identification reveals repeat inter‐ and intraspecific associations among individuals with 34.2% of common bottlenose dolphins resighted together with false killer whales over 1,832 d. While foraging was observed during 39.5% of mixed‐species encounters, results suggest that social and antipredatory factors may also play a role in the formation of these mixed‐species groups.

No abstract

Researchers can investigate many aspects of animal ecology through noninvasive photo–identification. Photo–identification is becoming more efficient as matching individuals between photos is increasingly automated. However, the convolutional neural network models that have facilitated this change need many training images to generalize well. As a result, they have often been developed for individual species that meet this threshold. These single‐species methods might underperform, as they ignore potential similarities in identifying characteristics and the photo–identification process among species. In this paper, we introduce a multi‐species photo–identification model based on a state‐of‐the‐art method in human facial recognition, the ArcFace classification head. Our model uses two such heads to jointly classify species and identities, allowing species to share information and parameters within the network. As a demonstration, we trained this model with 50,796 images from 39 catalogues of 24 cetacean species, evaluating its predictive performance on 21,192 test images from the same catalogues. We further evaluated its predictive performance with two external catalogues entirely composed of identities that the model did not see during training. The model achieved a mean average precision (MAP) of 0.869 on the test set. Of these, 10 catalogues representing seven species achieved a MAP score over 0.95. For some species, there was notable variation in performance among catalogues, largely explained by variation in photo quality. Finally, the model appeared to generalize well, with the two external catalogues scoring similarly to their species' counterparts in the larger test set. From our cetacean application, we provide a list of recommendations for potential users of this model, focusing on those with cetacean photo–identification catalogues. For example, users with high quality images of animals identified by dorsal nicks and notches should expect near optimal performance. Users can expect decreasing performance for catalogues with higher proportions of indistinct individuals or poor quality photos. Finally, we note that this model is currently freely available as code in a GitHub repository and as a graphical user interface, with additional functionality for collaborative data management, via Happywhale.com.

No abstract