Key Takeaways:
- An app called DinoTracker uses artificial intelligence to identify dinosaurs from their footprints
- The app analyzes 2,000 unlabelled footprint silhouettes to determine similarities and differences
- The system identifies eight features that reflect variations in imprint shapes, such as toe spread and heel position
- The app allows users to upload and manipulate footprints to see how varying features affect similarities
- The AI system supports the idea that some dinosaur footprints are remarkably birdlike, despite being older than the oldest bird skeletons
Introduction to DinoTracker
The world of paleontology has just gotten a whole lot more exciting with the introduction of DinoTracker, an app that uses artificial intelligence to identify dinosaurs from the footprints they left behind. As Prof Steve Brusatte, a co-author of the work, notes, "When we find a dinosaur footprint, we try to do the Cinderella thing and find the foot that matches the slipper." However, this is not always a simple task, as the shape of a dinosaur footprint depends on various factors, including the type of sand or mud it was walking through and the motion of its foot. The app, developed by Brusatte and his colleagues, aims to make this process easier and more accurate.
The Challenges of Identifying Dinosaur Footprints
Previous AI systems have been trained on footprints that have already been labeled as having been made by particular types of dinosaurs. However, as Dr. Gregor Hartmann, the first author of the new research, points out, "You never find a footprint and alongside [it] the dinosaur that had made this footprint." This means that the labels may be incorrect, and therefore, the AI system may also be flawed. Hartmann notes, "No offence to palaeontologists and such, but most likely some of these labels are wrong." This highlights the need for a more robust and accurate method of identifying dinosaur footprints.
How DinoTracker Works
To address this challenge, Brusatte, Hartmann, and their colleagues took a different approach. They fed their AI system with 2,000 unlabelled footprint silhouettes, which then determined how similar or different the imprints were from each other by analyzing a range of features it identified as meaningful. The system discovered eight features that reflected variations in the imprints’ shapes, such as the spread of the toes, amount of ground contact, and heel position. As Hartmann explains, "The system clustered prints with those expected from classifications made by human experts about 90% of the time." This suggests that the app is a powerful tool for identifying dinosaur footprints.
The Birdlike Footprints
One of the most interesting findings of the study is the presence of birdlike footprints in the Triassic and early Jurassic periods, which are remarkably similar to those of modern birds. Brusatte notes, "If these tracks were made by birds, that would mean that birds have a much older, much deeper ancestry than we used to think. And not just a few million years but tens of millions of years." However, as Brusatte himself cautions, "I suspect it is more likely that these tracks were made by meat-eating dinosaurs with very birdlike feet – maybe bird ancestors, but not true birds." This highlights the complexity and nuance of the findings, and the need for further research to fully understand the implications.
Limitations and Future Directions
While the DinoTracker app is a significant breakthrough, it is not without its limitations. Dr. Jens Lallensack, of Humboldt University of Berlin, notes that the features of interest identified by the new system are not necessarily based on the shape of the foot itself. He suggests that the birdlike tracks may be a result of the way the foot of a regular theropod sank into soft ground, rather than evidence of an early appearance of birds. This highlights the need for further research and refinement of the app to fully understand its potential and limitations.
Conclusion
In conclusion, the DinoTracker app is a powerful tool for identifying dinosaur footprints, with significant implications for our understanding of dinosaur evolution and behavior. As Brusatte notes, "The system is not just a tool for identifying footprints, but also a way to explore the evolution of dinosaur locomotion and behavior." While there are limitations and challenges to be addressed, the app has the potential to revolutionize the field of paleontology and provide new insights into the lives of these fascinating creatures. As Hartmann says, "The app is a first step towards a more accurate and robust method of identifying dinosaur footprints, and we are excited to see where it will take us."
https://www.theguardian.com/science/2026/jan/26/scientists-launch-ai-dinotracker-app-that-identifies-dinosaur-footprints
