Knowledge Management System Of Guangzhou Institute of Geochemistry,CAS
Ji, Shichao1,2; Huang, Fang3; Wang, Shaoze4; Gupta, Priyantan5; Seyfried, William6; Zhang, Hejia7; Chu, Xu8; Cao, Wentao9; Zhangzhou, J.10 | |
Identifying serpentine minerals by their chemical compositions with machine learning | |
Source Publication | AMERICAN MINERALOGIST |
ISSN | 0003-004X |
2024-02-26 | |
Volume | 109Issue:2Pages:315-324 |
DOI | 10.2138/am-2022-8688 |
Language | 英语 |
WOS Research Area | Geochemistry & Geophysics ; Mineralogy |
Abstract | The three main serpentine minerals, chrysotile, lizardite, and antigorite, form in various geological settings and have different chemical compositions and rheological properties. The accurate identification of serpentine minerals is thus of fundamental importance to understanding global geochemical cycles and the tectonic evolution of serpentine-bearing rocks. However, it is challenging to distinguish specific serpentine species solely based on geochemical data obtained by traditional analytical techniques. Here, we apply machine learning approaches to classify serpentine minerals based on their chemical compositions alone. Using the Extreme Gradient Boosting (XGBoost) algorithm, we trained a classifier model (overall accuracy of 87.2%) that is capable of distinguishing between low-temperature (chrysotile and lizardite) and high-temperature (antigorite) serpentines mainly based on their SiO2, NiO, and Al2O3 contents. We also utilized a k-means model to demonstrate that the tectonic environment in which serpentine minerals form correlates with their chemical compositions. Our results obtained by combining these classification and clustering models imply the increase of Al2O3 and SiO2 contents and the decrease of NiO content during the transformation from low- to high-temperature serpentine (i.e., lizardite and chrysotile to antigorite) under greenschist-blueschist conditions. These correlations can be used to constrain mass transfer and the surrounding environments during the subduction of hydrated oceanic crust. |
Keyword | Serpentine machine learning XGBoost, classifications k-means clustering |
WOS ID | WOS:001155433300014 |
Indexed By | SCI |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.gig.ac.cn/handle/344008/76234 |
Collection | 中国科学院矿物学与成矿学重点实验室 |
Corresponding Author | Huang, Fang |
Affiliation | 1.Chinese Acad Sci, Guangzhou Inst Geochem, CAS Key Lab Mineral & Metallogeny, Guangdong Prov Key Lab Mineral Phys & Mat, Guangzhou 510640, Peoples R China 2.Chinese Acad Sci, Ctr Excellence Deep Earth Sci, Beijing, Peoples R China 3.CSIRO Mineral Resources, Kensington, WA 6151, Australia 4.Ohio Univ, Phys & Astron Dept, Surface Sci Lab, Athens, OH 74501 USA 5.Indian Inst Technol, Kharagpur 721302, W Bengal, India 6.Univ Minnesota, Dept Earth & Environm Sci, Minneapolis, MN 55455 USA 7.Yale Univ, Sch Environm, New Haven, CT 06511 USA 8.Univ Toronto, Dept Earth Sci, Toronto, ON M5S3B1, Canada 9.SUNY Coll Fredonia, Dept Geol & Environm Sci, Fredonia, NY 14063 USA 10.Zhejiang Univ, Sch Earth Sci, Hangzhou 310058, Peoples R China |
Recommended Citation GB/T 7714 | Ji, Shichao,Huang, Fang,Wang, Shaoze,et al. Identifying serpentine minerals by their chemical compositions with machine learning[J]. AMERICAN MINERALOGIST,2024,109(2):315-324. |
APA | Ji, Shichao.,Huang, Fang.,Wang, Shaoze.,Gupta, Priyantan.,Seyfried, William.,...&Zhangzhou, J..(2024).Identifying serpentine minerals by their chemical compositions with machine learning.AMERICAN MINERALOGIST,109(2),315-324. |
MLA | Ji, Shichao,et al."Identifying serpentine minerals by their chemical compositions with machine learning".AMERICAN MINERALOGIST 109.2(2024):315-324. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment