# Machine learning reveals how often fish schooling evolved—and repeatedly disappeared

Source: [Biology News - Evolution, Cell theory, Gene theory, Microbiology, Biotechnology](https://phys.org/news/2026-11-machine-reveals-fish-schooling-evolved.html) · 2026-11-09 · Life
Page: https://themorning.science/story/machine-learning-reveals-how-often-fish-schooling-evolved-and-repeatedly-disappe-46f66ced568e0ef0
Kind: research · Impact: low

## In brief

- Researchers used new machine learning techniques to study the evolution of fish schooling across thousands of species.
- The findings, published Nov. 6 in the Proceedings of the National Academy of Sciences, indicate that schooling evolved multiple times and also repeatedly disappeared.
- The study addresses a question that previously had no established method for investigation.

## Why it matters

The work offers a way to study how collective behaviour evolves across many species at once, which had not been practical before. It suggests that schooling is not a one-way trait, which matters for how biologists reconstruct the evolutionary history of fish behaviour.

## Timeline

- 2026-11-06: Paper published in the Proceedings of the National Academy of Sciences

## Coverage

- [Machine learning reveals how often fish schooling evolved—and repeatedly disappeared](https://phys.org/news/2026-11-machine-reveals-fish-schooling-evolved.html) — Biology News - Evolution, Cell theory, Gene theory, Microbiology, Biotechnology, 2026-11-09

Tags: fish, schooling, evolution, machine learning, collective behavior

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Science – https://themorning.science