Data science and evolution

Machine learning for fossil data analysis

The focus is on extracting and interpreting patterns from the global fossil record and related biospheric datasets to understand biological, ecological and environmental change processes and interrelations among them over time.

Machine learning methodologies are used for analyzing evolutionary contexts, global scale relationships between animals, their environments, reconstructing past climates and environmental change. Advanced computational approaches help to more accurately reconstruct the evolutionary context of early hominins, and better understand the ongoing anthropogenic global change.

The 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.

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. 

Selected publications

  • A survey of computational methods for fossil data analysis by Žliobaitė et al. 2017 in Evolutionary Ecology ResearchPDFpreprint
  • Relative abundances and palaeoecology of four suid genera in the Turkana Basin, Kenya, during late Miocene to Pleistocene by 
    Rannikko et al. 2017 in 
    Palaeogeography, Palaeoclimatology, Palaeoecology. DOI
  • Ecosystem evolution and hominin paleobiology at East Turkana, northern Kenya between 2.0 and 1.4 Ma by Patterson et al. 2017 in Palaeogeography, Palaeoclimatology, PalaeoecologyDOI
  • Herbivore teeth predict climatic limits in Kenyan ecosystems by Žliobaitė et al. 2016 in PNASDOI (open access)
  • An ecometric analysis of the fossil mammal record of the Turkana Basin by Fortelius et al. 2016 in Philosophical Transactions B. DOI (open access)
  • Improving Adaptation through Evolution and Learning: A Response to Watson and Szathmáry by Žliobaitė and Stenseth 2016 in Trends in Ecology and Evolution. DOI  PDF


Media coverage