Rutgers University-New Brunswick researchers have created an artificial intelligence (AI) tool that will assist in forecasting the habitat of endangered whales and directing ships along the Atlantic coast to steer clear of them. The tool will help prevent fatal accidents and inform conservation plans and responsible ocean development. The study was published in Nature Scientific Reports.
Image Credit: Foto 4440/Shutterstock.com
The researchers claimed their approach enhanced current capabilities to monitor the ocean for the distribution of significant marine species, like the critically endangered North Atlantic right whale, using an AI-powered computer program that learns from patterns found between two enormous databases.
Since 1970, the Endangered Species Act has listed North Atlantic right whales as endangered. The US National Oceanic and Atmospheric Administration estimates that around 370 individuals remain, including approximately 70 reproductively active females.
Josh Kohut, a Marine Science Professor appointed Dean of Research at the School of Environmental and Biological Sciences in January, and Ahmed Aziz Ezzat, an Assistant Professor in the School of Engineering's Department of Industrial and Systems Engineering, spearheaded the endeavor. Ezzat oversees an applied machine learning research team for the physical sciences and engineering. Jiaxiang Ji, a doctoral student at the School of Engineering and the study’s first author, made a substantial contribution to the endeavor.
Kohut compared the program's output to what could be discovered by monitoring a home's occupants' movements and determining whether there is food in the kitchen and a TV in the den. Such factors may influence why people are in specific locations at certain times of the day. He stated that identifying specific patterns provides predictive power.
With this program, we’re correlating the position of a whale in the ocean with environmental conditions. This allows us to become much more informed on decision making about where the whales might be. We can predict the time and location that represents a higher probability for whales to be around. This will enable us to implement different mitigation strategies to protect them.
Josh Kohut, School of Environmental and Biological Sciences, Rutgers University
The researchers' initial goal was to create high-resolution models of the North Atlantic right whale population to ethically facilitate the development and operation of offshore wind farms. However, they disclosed the specifics as an addendum to their research paper and claimed that the findings have much wider ramifications.
These tools are valuable and would solidly benefit anyone engaged in the blue economy – including fishing, shipping, and developing alternative forms of energy sustainably. This approach can support a wise and environmentally responsible use of these waters so that we achieve our economic objectives, and at the same time make sure that we cause minimal to no harm to the environmental habitat of these creatures.
Ahmed Aziz Ezzat, Assistant Professor, Department of Industrial and Systems Engineering, Rutgers University
The researchers' machine-learning program examined vast data sets to find patterns and connections, in contrast to conventional computer programs with explicit written instructions. To improve its classifications or predictions, the AI program modified its internal model as it came across more data.
“The outcome of the machine-learning model is basically a prediction of where and when you will have a higher likelihood of encountering a marine mammal,” said Ezzat, describing it as a “probability map.”
The computer model analyzes all of the satellite-based and underwater glider data gathered by researchers at the Rutgers University Center for Ocean Observing Leadership since its founding in 1992 by then-Assistant Professor Scott Glenn, who is currently a Distinguished Professor in the Department of Marine and Coastal Sciences. The University of Delaware's publicly available satellite data products were also included in the analysis.
The autonomous, torpedo-shaped underwater gliders speed beneath the mid-Atlantic coast's ocean surface. The gliders measure various seawater parameters, such as temperature, salinity, current strength, and chlorophyll concentrations. In addition, the gliders record the underwater calls of whales and other marine mammals, allowing them to be located in space and time, and bounce sound waves off schools of fish to determine their size. Among other things, satellite data includes measurements of fronts, water color, and sea surface temperature.
“We’ve had the data but, until now, we’ve not been able to put the two sets – those detections of where the whales are, and what the environment is like at those places – together. This is a demonstration of the power of employing AI methodologies to advance our ability to predict or estimate where these whales are,” said Kohut.
Jeeva Ramasamy, an undergraduate computer science major, and Laura Nazzaro, a lab manager in the Department of Marine and Coastal Sciences, were among the other Rutgers scientists involved in the study.
Journal Reference:
Ji, J., et al. (2025) Machine learning for modeling North Atlantic right whale presence to support offshore wind energy development in the U.S. Mid-Atlantic. Scientific Reports. doi.org/10.1038/s41598-024-80084-z