Reconstructing Earth’s atmospheric oxygenation history using machine learning

Guoxiong Chen; Qiuming Cheng; Timothy W. Lyons; Jun Shen; Frits Agterberg; Ning Huang; Molei Zhao

doi:10.1038/s41467-022-33388-5

Nature Communications (Oct 2022)

Reconstructing Earth’s atmospheric oxygenation history using machine learning

Guoxiong Chen,
Qiuming Cheng,
Timothy W. Lyons,
Jun Shen,
Frits Agterberg,
Ning Huang,
Molei Zhao

Affiliations

Guoxiong Chen: State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences
Qiuming Cheng: State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences
Timothy W. Lyons: Department of Earth and Planetary Sciences, University of California
Jun Shen: State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences
Frits Agterberg: Geological Survey of Canada
Ning Huang: State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences
Molei Zhao: State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences

DOI: https://doi.org/10.1038/s41467-022-33388-5
Journal volume & issue: Vol. 13, no. 1
pp. 1 – 13

Abstract

Read online

Earth’s oxygenation history can be reconstructed using machine learning and mafic igneous geochemical data. Agreement with independent proxy predictions for surface conditions implies that interior processes are critical in atmospheric oxygenation.

Published in Nature Communications

ISSN: 2041-1723 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science
Website: https://www.nature.com/ncomms/

About the journal