Machine learning methods for analysis of the global fossil record Lecture 1 Indrė Žliobaitė Ecological and Biospheric data conservation data Fossil databases Weather stations http://www.iucnredlist.org/ Environment observation sensors http://www.worldclim.org/methods1 Satellite imaging data https://www.atm.helsinki.fi/SMEAR/index.php/smear-ii https://neo.sci.gsfc.nasa.gov/view.php?datasetId=MCD12C1_T1 What can be answered using machine learning ● Reconstructing how life was in the past and how life works in general ● Analyzing relations between organisms and environments, understanding biospheric change processes ● Analyzing why and how species evolve ● Understanding circumstances of early human evolution Environment: Temperature Precipitation Occurring Productivity animals: Seasonality Species A Vegetation type Species B Woody cover Species C ... ... Features of animals: Body mass Slim legs? Sharp teeth? ... Why understanding the past? Climate change Source: https://climate.nasa.gov/evidence/ Extreme events Source: https://climate.nasa.gov/evidence/ Reconstructing and analyzing climate over time Fortelius et al 2002 Circumstances of early human environments Source: http://humanorigins.si.edu/evidence/human-family-tree Circumstances of early human environments Image credits: Mauricio Anton Source: https://www.nature.com/nature/journal/v507/n7492/full/507303a.html