The origin and evolution of open habitats in North America inferred by Bayesian deep learning models

Some of the most extensive terrestrial biomes today consist of open vegetation, including temperate grasslands and tropical savannas. These biomes originated relatively recently in Earth's history, likely replacing forested habitats in the second half of the Cenozoic. However, the timing of their origination and expansion remains disputed. Here, we present a Bayesian deep learning model that utilizes information from fossil evidence, geologic models, and paleoclimatic proxies to reconstruct paleovegetation, placing the emergence of open habitats in North America at around 23 million years ago. By the time of the onset of theQuaternary glacial cycles, open habitatswere coveringmore than 30% of North America and were expanding at peak rates, to eventually become the most prominent natural vegetation type today. Our entirely datadriven approach demonstrates how deep learning can harness unexplored signals fromcomplex data sets to provide insights into the evolution of Earth's biomes in time and space.

Automated summary

A Bayesian deep learning model was used to reconstruct the emergence and expansion of open habitats in North America, utilizing fossil evidence, geologic models, and paleoclimatic proxies. The study suggests that these habitats originated around 23 million years ago and covered over 30% of North America by the onset of the Quaternary glacial cycles, eventually becoming the most prominent natural vegetation type today.