Code of the Ocean: Using AI to Protect Endangered Whales 

Source: ShutterStock

In the vast expanse of our oceans, whales reign as majestic giants. Once hunted to the brink of extinction, they have made a bit of a comeback. However, they face new dangers in the form of climate change, underwater noise pollution, and the relentless rise in global shipping traffic. 

One of the most endangered of the whale species is the North Atlantic right whale. It has been endangered under the Endangered Species Act since 1970. The U.S. National Oceanic and Atmospheric Administration. estimates that only 370 remain, with only 70 reproductively active females. Swift and effective measures are needed to protect these vulnerable creatures from extinction.

Artificial intelligence (AI) is playing a key role in protecting the species. Researchers at Rutgers University-New Brunswick have developed a new AI tool that can predict whale habitat and movement, guiding ships across the Atlantic to avoid them. The tool is designed to prevent deadly collisions while advancing conservation efforts and sustainable ocean development.

The project is led by Ahmed Aziz Ezzat, an assistant professor in Industrial and Systems Engineering at the School of Engineering, along with Josh Kohut, a marine sciences professor who was appointed dean of research at the School of Environmental and Biological Sciences last month. The researchers’ report was published in Nature Scientific Reports.

Source: Shutterstock

The AI tool works by analyzing vast amounts of oceanographic and biological data to predict where whales are likely to be at a given time. Unlike typical computer programs that follow specific instructions, the machine-learning (ML) program used by the researchers analyzed large data sets to identify patterns. As it processed more data, the AI improved its predictions and classifications.

Where did the researchers get data that covers the entire Atlantic Ocean? Some of the data comes from satellite-based observations collected by scientists at the Rutgers University Center for Ocean Observing Leadership, dating back to 1992. The AI tool also uses data from torpedo-shaped underwater gliders that navigate the mid-Atlantic coast. These gliders measure key seawater properties and capture the underwater calls of whales and other marine mammals. 

What about factors that influence whale movements? According to Kohut, the AI tool is rooted in several factors known to attract whales, such as water temperature, salinity, and the presence of food sources. By correlating whale movements with these environmental conditions, the tool predicts where and when whales are most likely to be in specific areas. 

“With this program, we’re correlating the position of a whale in the ocean with environmental conditions,” explains Kohut. “This allows us to become much more informed in 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.”

The AI tool allows the researchers to create a “probability map” across the Atlantic Ocean. The project was initially aimed at developing a map of whale presence in the ocean to support responsible wind farm development and operation. However, the researchers realized that the AI tool could have a broader impact on protecting the species. They have made the details public as an addendum to their research paper. 

“These tools are valuable and would solidly benefit anyone engaged in the blue economy – including fishing, shipping, and developing alternative forms of energy sustainably,” Ezzat said. “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.”

Source: Shutterstock

Kohut emphasizes that the success of the tool demonstrates the power of AI in advancing the field of oceanography. While the data existed, there was no efficient and effective way to utilize that information. AI technology has now enabled researchers to combine and analyze vast data sets, making them practical and efficient for use in ways previously not possible. 

AI has been used by several other researchers to advance whale protection efforts. MIT's CSAIL and Project CETI researchers have leveraged ML algorithms to decode whale communication. Their work has helped predict whale movements and revealed intricate patterns in vocalization that were unknown. 

NOAA Fisheries has applied ML algorithms to combine AI with environmental monitoring to create an efficient system for identifying and tracking North Atlantic right whales. The system has helped speed up the identification process, catalog the right whales, and allow researchers to monitor whale populations. It has also helped researchers gather a better understanding of whale social structure and plan conservation efforts. 

The use of AI in marine research holds great promise for further safeguarding whale populations and enhancing our understanding of marine life. As AI systems become more sophisticated, we can expect them to have a greater impact on the protection of our planet and its inhabitants.