Cetaceans are protected worldwide but vulnerable to incidental harm from an expanding array of human activities at sea. Managing potential hazards to these highly-mobile populations increasingly requires a detailed understanding of their seasonal distributions and habitats. Pursuant to the urgent need for this knowledge for the U.S. Atlantic and Gulf of Mexico, we integrated 23 years of aerial and shipboard cetacean surveys, linked them to environmental covariates obtained from remote sensing and ocean models, and built habitat-based density models for 26 species and 3 multi-species guilds using distance sampling methodology. In the Atlantic, for 11 well-known species, model predictions resembled seasonal movement patterns previously suggested in the literature. For these we produced monthly mean density maps. For lesser-known taxa, and in the Gulf of Mexico, where seasonal movements were less well described, we produced year-round mean density maps. The results revealed high regional differences in small delphinoid densities, confirmed the importance of the continental slope to large delphinoids and of canyons and seamounts to beaked and sperm whales, and quantified seasonal shifts in the densities of migratory baleen whales. The density maps, freely available online, are the first for these regions to be published in the peer-reviewed literature.

Determining which species are at greatest risk, where they are most vulnerable, and what are the trajectories of their communities and populations is critical for conservation and management. Globally distributed, wide-ranging whales and dolphins present a particular challenge in data collection because no single research team can record data over biologically meaningful areas. Flukebook.org is an open-source web platform that addresses these gaps by providing researchers with the latest computational tools. It integrates photo-identification algorithms with data management, sharing, and privacy infrastructure for whale and dolphin research, enabling the global collaborative study of these global species. With seven automatic identification algorithms trained for 15 different species, resulting in 37 species-specific identification pipelines, Flukebook is an extensible foundation that continually incorporates emerging AI techniques and applies them to cetacean photo identification through continued collaboration between computer vision researchers, software engineers, and biologists. With over 2.0 million photos of over 52,000 identified individual animals submitted by over 250 researchers, the platform enables a comprehensive understanding of cetacean populations, fostering international and cross-institutional collaboration while respecting data ownership and privacy. We outline the technology stack and architecture of Flukebook, its performance on real-world cetacean imagery, and its development as an example of scalable, extensible, and reusable open-source conservation software. Flukebook is a step change in our ability to conduct large-scale research on cetaceans across biologically meaningful geographic ranges, to rapidly iterate population assessments and abundance trajectories, and engage the public in actions to protect them.

Photo identification is an important tool used in the field of conservation biology to estimate population abundance and monitor trends over time. However, manually matching photographs to known individuals is time‐consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crowdsourcing platform Kaggle to automate the identification of endangered North Atlantic right whales. The winning solution was able to automatically identify individual whales with 87% accuracy using a series of convolutional neural networks to identify the region of interest, rotate, and crop the images, create standardized ‘passport’ photographs, and identify the correct individual whale. The recent advances in deep learning coupled with this fully automated workflow have yielded impressive results and have the potential to revolutionize traditional data collection methods for the abundance and distribution of wild populations. We anticipate that presenting these results to a broad audience will further bridge the gap between the data science and conservation biology communities and encourage others to utilize computer vision in population monitoring. This article is protected by copyright. All rights reserved

The goal of this research was to determine when harbor seal pup vocalizations become sufficiently distinctive to allow individual recognition. A total of 4593 calls were analyzed from 15 captive pups. Nineteen were harsh, broadband, staccato calls used in an aggressive context. The rest were tonal “mother attraction calls,” having an inverted “v”- or “u”-shaped spectrogram with harmonics and a fundamental frequency around $200–600\mathrm{Hz}$ . Calls were individually distinctive even in pups less than $2\text{weeks}$ old, suggesting that mothers may be able to recognize pup vocalizations at this early age. Classification rates from discriminant function analysis were generally comparable to those of other phocids and less than in otariids, supporting the theory that recognition is more highly developed in otariids. Significant differences were found between male and female pup calls, and there were significant interactions between pup sex and age. The results of this study should be interpreted with caution until the findings are verified in wild harbor seal pups.

Monitoring marine mammals is of broad interest to governments and individuals around the globe. Very high-resolution (VHR) satellites hold the promise of reaching remote and challenging locations to fill gaps in our knowledge of marine mammal distribution. The time has come to create an operational platform that leverages the increased resolution of satellite imagery, proof-of-concept research, advances in cloud computing, and machine learning to monitor the world’s oceans. The Geospatial Artificial Intelligence for Animals (GAIA) initiative was formed to address this challenge with collaborative innovation from government agencies, academia, and the private sector. In this paper, we share lessons learned, challenges faced, and our vision for how VHR satellite imagery can enhance our understanding of cetacean distribution in the future.

Photo identification is an important tool in the conservation management of endangered species, and recent developments in artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, the National Oceanic and Atmospheric Administration hosted a Kaggle data science competition to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning algorithms developed by Deepsense.ai were able to identify individuals with 87% accuracy using a series of convolutional neural networks to identify the region of interest, create standardized photographs of uniform size and orientation, and then identify the correct individual. Since that time, we have brought in many more collaborators as we moved from prototype to production. Leveraging the existing infrastructure by Wild Me, the developers of Flukebook, we have created a web-based platform that allows biologists with no machine learning expertise to utilize semi-automated photo identification of right whales. New models were generated on an updated dataset using the winning Deepsense.ai algorithms. Given the morphological similarity between the North Atlantic right whale and closely related southern right whale (Eubalaena australis), we expanded the system to incorporate the largest long-term photo identification catalogs around the world including the United States, Canada, Australia, South Africa, Argentina, Brazil, and New Zealand. The system is now fully operational with multi-feature matching for both North Atlantic right whales and southern right whales from aerial photos of their heads (Deepsense), lateral photos of their heads (Pose Invariant Embeddings), flukes (CurvRank v2), and peduncle scarring (HotSpotter). We hope to encourage researchers to embrace both broad data collaborations and artificial intelligence to increase our understanding of wild populations and aid conservation efforts.