Satellite Monitoring of North Atlantic Right Whales

Collecting Satellite Imagery of Right Whales

The Geospatial Artificial Intelligence for Animals (GAIA) team is commissioning the new collection of satellite imagery, known as tasking, in partnership with the U.S. Geological Survey. This effort will advance research on detecting North Atlantic right whales from space. Tasked imagery allows us to request data over specific locations and time periods when whales are most likely to be present. This is different from the more commonly accessed archival imagery which consists of satellite images collected in the past for other purposes. The targeted approach of tasking imagery increases the likelihood of capturing whales at the surface and observing them under a wide range of environmental and oceanographic conditions.

Current imagery collections focus on several key regions critical to the species’ life cycle and conservation. These include:

• Calving grounds in the southeastern United States
• Foraging habitats in the northeastern United States and Canada
• Areas known to present elevated risk of vessel strike and fishing gear entanglement

Collecting imagery in these locations will support ecological understanding and the development of tools that may help inform management and mitigation efforts.

The primary goal of this work is to build a robust, well-annotated training dataset. This dataset consists of satellite images in which experts carefully identify and label right whales to provide the examples needed to train and evaluate machine-learning models. By capturing whales across a range of sea states, lighting conditions, water clarity, and surface behaviors, the resulting models will be better equipped to detect whales under real-world conditions.

The team is also acquiring exploratory satellite imagery off the coast of Iceland, where North Atlantic right whales have occasionally been sighted outside of their normal range. This will help expand our understanding of the species’ movement patterns.

Cape Cod Bay Case Study: Comparing Satellite Whale Detection with Aerial Surveys

About the Geospatial Artificial Intelligence For Animals

This initiative is a collaborative effort led by NOAA with the U.S. Geological Survey, Microsoft AI for Good, the Naval Research Laboratory, and other partners. We are building a secure cloud-based application that detects whales and other marine mammals in very high-resolution satellite imagery. The system combines advanced image preprocessing and expert annotation to produce reliable training datasets for machine learning models. Initially focused on endangered whales such as North Atlantic right whales and Cook Inlet belugas, GAIA is designed to expand into other taxa and habitats. We are creating a flexible, scalable platform for biodiversity monitoring. Turning raw satellite imagery into actionable information will enable monitoring of vast and remote ocean areas and strengthen conservation outcomes by providing managers and policymakers with timely insights.