Machine Learning for Identification of Primary Water Concentrations in Mantle Pyroxene

Chen, Huan; Su, Cheng; Tang, Yongquan; Li, An-Zhou; Wu, Shengjun; Xia, Qunke; ZhangZhou, J

doi:10.1029/2021gl095191

Cited by 9 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, several studies have demonstrated that the data-driven machine learning methods can be powerful tools for solving complex problems in mineralogy, petrology, and geochemistry (Petrelli and Perugini 2016;Chen et al 2021;Huang et al 2022;Lin et al 2022;Nathwani et al 2022;Qin et al 2022;Wang et al 2022;Zou et al 2022), and for the construction of thermobarometers (Petrelli et al 2020;Higgins et al 2022;Jorgenson et al 2022;Li and Zhang 2022), without having any a priori knowledge. These research advances suggest that the machine learning method has the potential to be used for calibrating a mineral chemical-based oxybarometer.…”

Section: Introductionmentioning

confidence: 99%

Machine-learning oxybarometer developed using zircon trace-element chemistry and its applications

Zou,

Brzozowski,

Chen

et al. 2024

American Mineralogist

View full text Add to dashboard Cite

Magmatic oxygen fugacity (fO2) is a fundamental property to understanding the long-term evolution of the Earth’s atmosphere and the formation of magmatic-hydrothermal mineral deposits. Classically, the magmatic fO2 is estimated using mineral chemistry, such as Fe-Ti oxides, zircon, and hornblende. These methods, however, are only valid within certain limits and/or require a significant amount of a priori knowledge. In this contribution, a new oxybarometer, constructed by data-driven machine learning algorithms using trace elements in zircon and their corresponding independent fO2 constraints, is provided. Seven different algorithms are initially trained and then validated on a data set that was never utilized in the training processes. Results suggest that the oxybarometer constructed by the extremely randomized trees model has the best performance, with the largest R2 value (0.91 ± 0.01), smallest RMSE (0.45 ± 0.03), and low propagated analytical error (~0.10 log units). Feature importance analysis demonstrates that U, Ti, Th, Ce, and Eu in zircon are the key trace elements that preserve fO2 information. This newly developed oxybarometer has been applied in diverse systems, including arc magmas and mid-ocean ridge basalts, fertile and barren porphyry systems, and global S-type detrital zircon, which provide fO2 constraints that are consistent with other independent methods, suggesting that it has wide applicability. To improve accessibility, the oxybarometer was developed into a software application aimed at enabling more consistent and reliable fO2 determinations in magmatic systems, promoting further research.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine-learning oxybarometer developed using zircon trace-element chemistry and its applications

Zou,

Brzozowski,

Chen

et al. 2024

American Mineralogist

View full text Add to dashboard Cite

show abstract

“…Recent studies have shown the potential of machine learning (ML) in solving complex problems in Earth science (Chen et al., 2021; Guo et al., 2021; Lin et al., 2020; Petrelli et al., 2020; Petrelli & Perugini, 2016; Rouet‐Leduc et al., 2018; Zhao et al., 2019). The ML methods are data‐driven and can unravel complexities in large data sets without a predefined conceptual model (Bergen et al., 2019).…”

Section: Introductionmentioning

confidence: 99%

Quantifying Continental Crust Thickness Using the Machine Learning Method

Guo

Yang

2023

JGR Solid Earth

View full text Add to dashboard Cite

In addition, crustal thickness through time in the continental crust can be used to track changes in global or regional scale tectonic settings Tang, Ji, et al., 2021). Although present crustal thickness is well constrained from oceanic regions (5-10 km) to continental orogens (over 70 km, such as in the Himalaya-Tibet) (Laske et al., 2013), quantifying crustal thickness in the geologic past remains challenging.Proxies used to calculate crustal thickness include maximum Ce/Y in basalts (Mantle & Collins, 2008), Sr/Y and (La/Yb) N of intermediate rocks (Chapman et al., 2015;F. Y. Hu et al., 2017;Profeta et al., 2015) and europium anomalies (Eu/Eu*) in detrital zircons (Tang, Ji, et al., 2021). These proxies are all calibrated by correlations between the geochemical indices of young magmatic rocks and geophysically determined crustal thickness.

show abstract

A review of machine learning in geochemistry and cosmochemistry: Method improvements and applications

Zhou

Wen

et al. 2022

Applied Geochemistry

View full text Add to dashboard Cite

Machine Learning for Identification of Primary Water Concentrations in Mantle Pyroxene

Abstract: The major constituent minerals in the mantle contain a small amount of H 2 O, mainly in the form of hydrogen defects in nominally anhydrous minerals (Bell & Rossman, 1992). The presence of H 2 O significantly affects the physical and chemical properties of minerals and rocks (e.g.,

Cited by 9 publications

References 54 publications

Machine-learning oxybarometer developed using zircon trace-element chemistry and its applications

Machine-learning oxybarometer developed using zircon trace-element chemistry and its applications

Quantifying Continental Crust Thickness Using the Machine Learning Method

A review of machine learning in geochemistry and cosmochemistry: Method improvements and applications

Contact Info

Product

Resources

About