Mineralogical and geochemical constraints on the origin of the variable REE enrichments in the Kangdian IOCG province, SW China

Liu, Lei; Zhang, Wei; Chang, Jin; Chen, Wei Terry

doi:10.1016/j.oregeorev.2021.104381

Cited by 5 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DOI: https://doi.org/10.2138/am-2023-9115. http://www.minsocam.org/ and trace element data have been reported (Adlakha et al, 2018;Bruand et al, 2019;Cao et al, 2022;Chakhmouradian et al, 2017;Chen and Zhang, 2018;Chen et al, 2019;Gao et al, 2020;Glorie et al, 2019;Henrichs et al, 2018;Hoshino et al, 2017;La Cruz et al, 2020;Li et al, 2021;Liu et al, 2021;Long et al, 2023;Lupulescu et al, 2017;Meng et al, 2021;Mercer et al, 2020;Palma et al, 2019;Qu et al, 2021;Sun et al, 2022;Tang et al, 2021;Xie et al, 2018;Xu et al, 2023;Yang et al, 2018;Zafar et al, 2019;Zhang et al, 2021), it is challenging to validate these individual indicators and binary discrimination techniques due to a large area overlap of compositional spots, suggesting that those traditional low-dimensional classifiers that seemed to work well in specific systems might be invalid in other systems or datasets of larger scales.…”

Section: Introductionmentioning

confidence: 99%

Machine learning applied to apatite compositions for determining mineralization potential

Zheng,

Xu,

Lentz

et al. 2024

American Mineralogist

View full text Add to dashboard Cite

Apatite major and trace element chemistry is a widely used tracer of mineralization, as it sensitively records the characteristics of the magmatic-hydrothermal system at the time of its crystallization. Previous studies have proposed useful indicators and binary discrimination diagrams to distinguish between apatites from mineralized and unmineralized rocks; however, their efficiency has been found to be somewhat limited in other systems and larger scale datasets.This work applied a machine learning (ML) method to classify the chemical compositions of apatites from both fertile and barren rocks, aiming to help determine the mineralization potential of unknown system. Approximately 13,328 apatite compositional analyses were compiled and labeled from 241 locations in 27 countries worldwide, and three apatite geochemical datasets were established for XGBoost ML model training. The classification results suggest that the developed models (accuracy: 0.851-0.992; F1 score: 0.839-0.993) are much more accurate and efficient than conventional methods (accuracy: 0.242-0.553). Feature importance analysis of the models demonstrates that Cl, F, S, V, Sr/Y, V/Y, Eu*, (La/Yb) N , and La/Sm are important variables in apatite that discriminate fertile and barren host rocks and indicates that V/Y and Cl/F ratios and the S content, in particular, are crucial parameters to discriminating metal enrichment and mineralization potential. This study suggests that ML is a robust tool for processing highdimensional geochemical data and presents a novel approach that can be applied to mineral exploration.

show abstract