stub AI Helps Observe Previously Unreported Animal Behaviors - Unite.AI
Connect with us

Artificial Intelligence

AI Helps Observe Previously Unreported Animal Behaviors

Updated on

One of the most exciting aspects of artificial intelligence (AI) is that the technology is constantly helping experts discover new information about our environment. This is the case once again as a research team from Osaka University has created a new animal-borne data-collection system that relies on AI. This system is what helped discover previously unreported behaviors in seabirds, specifically in regards to foraging.


One of the currently used techniques to observe wild animals, including their behaviors and social interactions, is bio-logging. The technique involves mounting lightweight video cameras or other devices meant to gather data onto the bodies of the animals. While bio-logging is seen as one of the best techniques for preventing disturbance of the animal, it has some downsides.

Specifically, bio-logging requires a high level of battery life, and the systems are expensive. 

Takuya Maekawa is the corresponding author of the study, which was published in Communications Biology and titled “Machine learning enables improved runtime precision for bio-loggers on seabirds.”

“Since bio-loggers attached to small animals have to be small and lightweight, they have short runtimes and it was therefore difficult to record interesting infrequent behaviors,” Maekawa said. 

“We have developed a new AI-equipped bio-logging device that allows us to automatically detect and record the specific target behaviors of interest based on data from low-cost sensors such as accelerometers and geographic positioning systems (GPS),” Maekawa continued.

With the use of the low-cost sensors, less reliance can be placed on the high-cost sensors, which include video cameras. These high-cost sensors then only need to be used during the most likely times in which the specific target behavior can be captured. 

【AI on Animals】青森の海鳥が仲間の魚を横取り!AIを用いたバイオロギングによる海鳥の生態観測


Paired with Machine Learning

By pairing these systems with machine learning techniques, the high-cost sensors can be targeted toward behaviors which are highly interesting but infrequent. This means that those infrequent behaviors have a higher chance of being observed. 

The AI-assisted video camera system developed by the team at Osaka University was tested on black-tailed gulls and streaked shearwaters. Both animals were kept in their natural environments, which are on islands off the coast of Japan. 

Joseph Korpela is lead author of the paper.

“The new method improved the detection of foraging behaviors in the black-tailed gulls 15-fold compared with the random sampling method,” Korpela said. “In the streaked shearwaters, we applied a GPS-based AI-equipped system to detect specific local flight activities of these birds. The GPS-based system had a precision of 0.59 — far higher than the 0.07 of a periodic sampling method involving switching the camera on every 30 minutes.”

According to the researchers, there are many possible applications for this AI technology, including anti-poaching uses and to gain insight into the relationships and interactions between humans and wild animals. 

“These systems have a huge range of possible applications including detection of poaching activity using anti-poaching tags,” Maekawa says. “We also anticipate that this work will be used to reveal the interactions between human society and wild animals that transmit epidemics such as coronavirus.” 


Alex McFarland is a tech writer who covers the latest developments in artificial intelligence. He has worked with AI startups and publications across the globe.