Machine learning reveals how often fish schooling evolved—and repeatedly disappeared
Scientists have used new machine learning techniques to investigate a topic no one has ever found a way to study: the evolution of fish moving together in schools across thousands of species. The new paper, published Nov. 6 in the Proceedings of the National Academy of Sciences,
The study's findings on the evolution of fish schooling behavior are fascinating, particularly given the challenges of analyzing such complex behavior across thousands of species. By leveraging machine learning techniques, researchers have made a significant breakthrough in understanding this phenomenon. The fact that fish schooling evolved multiple times, only to disappear, raises intriguing questions about the selective pressures that drive this behavior.
In the context of biomechanics and animal locomotion, the study's results have implications for our understanding of collective behavior and its role in the survival and success of different species. Fish schooling is a remarkable example of self-organization, where individual fish respond to local cues to create a coordinated, emergent behavior. The fact that this behavior has evolved and been lost multiple times suggests that it may be highly dependent on specific environmental conditions or ecological niches.
As researchers continue to explore the evolution of collective behavior, it will be interesting to see how these findings inform the development of new machine learning approaches and biomechanical models. Key areas to watch include the application of these techniques to other complex biological systems, as well as the integration of insights from ecology, evolution, and biomechanics to better understand the intricate relationships between behavior, environment, and species success.
Originally reported by phys.org. MechNews adds analysis for science & discovery readers.