© Ben Koger
How and why do groups of animals move and what role do some individuals play in this? To study the behavior of community-dwelling species like the zebra and its mates, the researchers introduced a new method of data collection by drone and subsequent analysis by artificial intelligence. In this way, information about the animals can be collected without interference and with relatively little effort, which could benefit their conservation and behavioral research, the scientists say.
Some steppe and bush dwellers, species of monkeys and many other animal species are known for their pronounced social communication: they form larger communities or herds that roam together, exhibiting interesting patterns of group dynamics. How these systems function and the importance of some of the factors are exciting from a biological point of view and could also be important for the protection of endangered species. However, research on this topic is difficult and time consuming: certain aspects of group dynamics remain hidden or must be painstakingly recorded through assessments. Data collection by providing individuals with data loggers and motion sensors is also time consuming and also associated with stress on some endangered animal species.
Eagle eyes and computer algorithms
For this reason, scientists led by Benjamin Kuger of the Max Planck Institute for Animal Behavior in Konstanz are working on an alternative. Now they present their concept, which can be used in the case of animal species that live in open areas or with little vegetation: they use drones that look at entire groups of animals from above, and collect a set of data that can then be evaluated in a special way to generate information. Hinge.
In a concrete sense, this means that the researchers launched a drone equipped with computer-controlled recording technology and directed it high above a group of animals so that they would not be disturbed. The aircraft then records in detail individual individuals, their movements and behavior as well as 3D features of the landscape including vegetation. After the drone returns, the data is read and analyzed by special computer algorithms that can automatically recognize the information in the recordings.
Comprehensive information on group dynamics
We often recorded 20 or more different individuals at the same time. As a human, it can take weeks to locate each individual in a single half-hour video view. So the first challenge was how to automatically identify the animals we were interested in,” says Koger. This was made possible by artificial intelligence: the researchers used powerful deep learning algorithms that could “learn” to recognize individual characteristics of the animals. Another challenge, the researchers explained, was purifying data to record animal movements.Because the videos were also affected by drone movements and distortions caused by landscape structures.However, the team apparently managed to overcome hurdles and develop a workable system, as exemplified by the example of Grevy’s zebras in Kenya and Gelada monkeys in Ethiopia.
“The strength of our image-based method is that it is a comprehensive solution,” says Koger. Since the drone captures not only groups of animals, but also landscapes, a very comprehensive dataset is obtained that contains information about the social and environmental context of all animals in the observed group. In this way, it can be demonstrated without intervention how social and spatial structures influence behavioral processes, such as decision-making and information exchange in groups.
In conclusion, senior author Blair Costello from the University of Konstanz says: “One of the strengths of our method is that it can be adapted to many different animal species and environments. I believe that this method can help us develop an understanding of the mechanisms by which individual behaviors generate systemic phenomena of interest.” relevance to conservation,” says the scientist.
Video: Explanation of the concept of the new process. © Ben Koger
Source: University of Constance, specialized article: Journal of Animal Ecology, doi: https://doi.org/10.1111/1365-2656.13904
“Alcohol buff. Troublemaker. Introvert. Student. Social media lover. Web ninja. Bacon fan. Reader.”