Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning
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...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-43358-0 |
| _version_ | 1797452117121695744 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Chen Yang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T15:04:08Z |
| format | Article |
| id | doaj.art-9141e788982d4c1ea0c6fa8eb0ce1a46 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-09T15:04:08Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-9141e788982d4c1ea0c6fa8eb0ce1a462023-11-26T13:45:12ZengNature PortfolioNature Communications2041-17232023-11-011411910.1038/s41467-023-43358-0Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learningChen Yang0Xinmei Zhang1Lorenzo Bruzzone2Bin Liu3Dawei Liu4Xin Ren5Jon Atli Benediktsson6Yanchun Liang7Bo Yang8Minghao Yin9Haishi Zhao10Renchu Guan11Chunlai Li12Ziyuan Ouyang13College of Earth Sciences, Jilin UniversityCollege of Earth Sciences, Jilin UniversityDepartment of Information Engineering and Computer Science, University of TrentoKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of SciencesKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of SciencesKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of SciencesFaculty of Electrical and Computer Engineering, University of Iceland, 102College of Computer Science and Technology, Jilin UniversityCollege of Computer Science and Technology, Jilin UniversityCollege of Information Science and Technology, Northeast Normal UniversityCollege of Computer Science and Technology, Jilin UniversityCollege of Computer Science and Technology, Jilin UniversityKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of SciencesKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of SciencesAbstract 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.https://doi.org/10.1038/s41467-023-43358-0 |
| spellingShingle | 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 Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning Nature Communications |
| title | Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning |
| title_full | Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning |
| title_fullStr | Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning |
| title_full_unstemmed | Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning |
| title_short | Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning |
| title_sort | comprehensive mapping of lunar surface chemistry by adding chang e 5 samples with deep learning |
| url | https://doi.org/10.1038/s41467-023-43358-0 |
| work_keys_str_mv | AT chenyang comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT xinmeizhang comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT lorenzobruzzone comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT binliu comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT daweiliu comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT xinren comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT jonatlibenediktsson comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT yanchunliang comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT boyang comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT minghaoyin comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT haishizhao comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT renchuguan comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT chunlaili comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning AT ziyuanouyang comprehensivemappingoflunarsurfacechemistrybyaddingchange5sampleswithdeeplearning |