Machine learning for fossil data analysis

Fossils are preserved remains or traces of animals, plants, and other organisms from the remote past. The fossil record gives clues about the history of life and environmental changes over millions of years, it helps to understand environmental change, biological and ecological processes and can be used to reconstruct past climate and human impact on the environment.

Fossil record is “big data” in a sense that it comes from many different sources, it is biased due to how fossils preserve and how they are collected, identification is interpretation based and uncertain in many ways, records are of varying quality over time.

Machine learning for fossil data analysis is about extracting and interpreting patterns from rich and multifaceted fossil data to understand biological, ecological and climate processes and interrelations between them over time and being able to extrapolate them into the future. 


Žliobaitė, I., Rinne, J., Toth, A., Mechenich, M., Liu, L., Behrensmeyer, A.K., Fortelius, M. (2016).
Herbivore teeth predict climatic limits in Kenyan ecosystems.
PNAS 113(45), p. 12751-12756link (open access)

Fortelius, M., Žliobaitė, I., Kaya, F., Bibi, F., Bobe, R., Leakey, L., Leakey, M., Patterson, D., Rannikko, J., Werdelin, L. (2016).
An ecometric analysis of the fossil mammal record of the Turkana Basin.
Philosophical Transactions B 371(1698), p. 1-13. link (open access)

Žliobaitė, I. and Stenseth, N. Chr. (2016). Improving Adaptation through Evolution and Learning: A Response to Watson and Szathmáry. Trends in Ecology and Evolution 31(12), p. 892-893. PDFpreprint  DOI


Oct 2016 » Ecometrics beyond limits at Kurtén Club, University of Helsinki slides


Research internship -- machine learning for fossil data analysis, apply by March 1, 2017.