Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning

Chen Yang; Xinmei Zhang; Lorenzo Bruzzone; Bin Liu; Dawei Liu; Xin Ren; Jon Atli Benediktsson; Yanchun Liang; Bo Yang; Minghao Yin; Haishi Zhao; Renchu Guan; Chunlai Li; Ziyuan Ouyang

doi:10.1038/s41467-023-43358-0

Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning

Nat Commun. 2023 Nov 20;14(1):7554. doi: 10.1038/s41467-023-43358-0.

Authors

Chen Yang^{1

2}, Xinmei Zhang³, Lorenzo Bruzzone⁴, Bin Liu⁵, Dawei Liu⁵, Xin Ren⁵, Jon Atli Benediktsson⁶, Yanchun Liang⁷, Bo Yang⁷, Minghao Yin⁸, Haishi Zhao⁹, Renchu Guan¹⁰, Chunlai Li¹¹, Ziyuan Ouyang^{5

12}

Affiliations

¹ College of Earth Sciences, Jilin University, Changchun, China. yangc616@jlu.edu.cn.
² Key Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, China. yangc616@jlu.edu.cn.
³ College of Earth Sciences, Jilin University, Changchun, China.
⁴ Department of Information Engineering and Computer Science, University of Trento, Trento, Italy.
⁵ Key Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, China.
⁶ Faculty of Electrical and Computer Engineering, University of Iceland, 102, Reykjavik, Iceland.
⁷ College of Computer Science and Technology, Jilin University, Changchun, China.
⁸ College of Information Science and Technology, Northeast Normal University, Changchun, China.
⁹ College of Computer Science and Technology, Jilin University, Changchun, China. zhaohs@jlu.edu.cn.
¹⁰ College of Computer Science and Technology, Jilin University, Changchun, China. guanrenchu@jlu.edu.cn.
¹¹ Key Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, China. licl@nao.cas.cn.
¹² Institute of Geochemistry, Chinese Academy of Sciences, Guiyang, China.

Abstract

Lunar surface chemistry is essential for revealing petrological characteristics to understand the evolution of the Moon. Existing chemistry mapping from Apollo and Luna returned samples could only calibrate chemical features before 3.0 Gyr, missing the critical late period of the Moon. Here we present major oxides chemistry maps by adding distinctive 2.0 Gyr Chang'e-5 lunar soil samples in combination with a deep learning-based inversion model. The inferred chemical contents are more precise than the Lunar Prospector Gamma-Ray Spectrometer (GRS) maps and are closest to returned samples abundances compared to existing literature. The verification of in situ measurement data acquired by Chang'e 3 and Chang'e 4 lunar rover demonstrated that Chang'e-5 samples are indispensable ground truth in mapping lunar surface chemistry. From these maps, young mare basalt units are determined which can be potential sites in future sample return mission to constrain the late lunar magmatic and thermal history.