The goal of this project is to develop simple and powerful machine learning models that can be used for paleontological research.

The Science

The following research has been completed thanks in part to the ml4paleo project:

Automated segmentation of synchrotron-scanned fossils. During MAD, Matelsky JK, Gustafsson FK, Voeten DFAE, Chen D, Wester BA, Kording KP, Ahlberg PE, Schön TB (2025) Automated segmentation of synchrotron-scanned fossils. Fossil Record 28(1): 103-114. https://doi.org/10.3897/fr.28.e139379

The Code

All code is open-source and licensed under an Apache 2.0 license. The code is available on GitHub at @j6k4m8/ml4paleo.

The Team

The project is co-led by Melanie During, Fredrik Gustaffson, and Jordan Matelsky.

Melanie During

University of Uppsala

Fredrik Gustaffson

University of Uppsala

Jordan Matelsky

University of Pennsylvania

Johns Hopkins University Applied Physics Laboratory

With mentorship and guidance from

Per Ahlberg

University of Uppsala

Thomas Schön

University of Uppsala

Konrad Kording

University of Pennsylvania

Brock Wester

Johns Hopkins University Applied Physics Laboratory