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.

Espírito Santo state is located on the eastern margin of Brazil, in a transitional tropical-subtropical area (18°S–21°S) dominated by oligotrophic waters. With the exception of humpback whales (Megaptera novaeangliae), the cetacean community of Espírito Santo has been understudied. In addition to the chronic impacts from fisheries, marine pollution, urban development, and coastal habitat degradation, in November 2015 the cetacean communities of Espírito Santo were challenged by the greatest environmental disaster in Brazil’s history. The Mariana dam disaster caused 60 million cubic meters of mining waste to be washed into the Doce River, which ultimately flowed to the coastal waters of Espírito Santo, with a high concentration of heavy metals. This study reviews and updates information on cetacean strandings in the state of Espírito Santo (excluding humpback whales) prior to this disaster. From 1975 to September 2015, there were 461 recorded cetacean strandings, representing 20 species. An average 1.18 strandings per 100 km per month were recorded since a state-wide daily beach survey program was implemented in October 2010, contrasting with the 0.14 strandings per 100 km per month in previous years. Six species comprised the majority (94.7%) of stranding events: Guiana dolphin (Sotalia guianensis), Franciscana (Pontoporia blainvillei), rough-toothed dolphin (Steno bredanensis), bottlenose dolphin (Tursiops truncatus), sperm whale (Physeter macrocephalus), and melon-headed whale (Peponocephala electra). Oceanic cetaceans stranded most frequently on the southern portion of Espírito Santo, where the continental platform is narrower, whereas the strandings of coastal cetaceans such as Guiana dolphins and Franciscanas were concentrated near estuaries, especially the Doce River. This is particularly concerning in face of the Mariana dam disaster, which drastically altered the estuarine and coastal environment associated with the Doce River.

Seabirds have been historically used to monitor environmental contamination. The aim of the present study was to test the suitability of a species belonging to the Procellariiformes group, the Manx shearwater, Puffinus puffinus, as a sentinel of environmental health, by determining contaminant levels (trace metals and organochlorine compounds) from carcass tissues and by isolating Vibrio spp. and Aeromonas spp. from live specimens. To this end, 35 Puffinus puffinus carcasses wrecked on the north-central coast of the state of Rio de Janeiro, Brazil, and two carcasses recovered in Aracruz, on the coast of the state of Espírito Santo, Brazil, were sampled, and fragments of muscle and hepatic tissues were collected for contaminant analyses. Swabs from eleven birds found alive at the north-central coast of Rio de Janeiro were collected for isolation of the aforementioned bacteria.