Calculating amphibole formula from electron microprobe analysis data using a machine learning method based on principal components regression

verfasst von

Xiaoyan Li, Chao Zhang, Harald Behrens, Francois Holtz

Abstract

We present a new method for calculating amphibole formula from routine electron microprobe analysis (EMPA) data by applying a principal components regression (PCR)-based machine learning algorithm on reference amphibole data. The reference amphibole data collected from literature are grouped in two datasets, for Li-free and Li-bearing amphiboles respectively, which include Fe²⁺, Fe³⁺, OH contents and the ion site assignments determined by single crystal structure refinement. We established two PCR models, for Li-free and Li-bearing amphiboles respectively, by the 10-fold cross validation of training datasets and evaluated by independent test datasets. The results show that our models can successfully reproduce the reference data for most ions with an error less than ±0.01 atom per formula unit (apfu), for Fe³⁺ within an error less than ±0.2 apfu and for ^WOH and ^WO²⁻ with errors less than ±0.3 apfu. The error in estimated Fe³⁺/ΣFe ratio shows a rough negative dependence on FeO_T content (total iron expressed as FeO), ranging within ±0.3 for amphiboles with FeO_T ≥ 5 wt% and within ±0.2 for amphiboles with FeO_T ≥ 10 wt%. Our models are applicable to both ^W(OH, F, Cl)-dominant and ^WO-dominant amphiboles. It is notable that this method is not suitable for calculating mineral formula of amphiboles that have been affected by deprotonation as a result of secondary oxidation, but it could offer an estimation of initial ^WOH prior to the post-formation oxidation. A user-friendly Excel worksheet is provided with two independent PCR models for calculating the formula of Li-free amphibole and Li-bearing amphibole, respectively. An automatic nomenclature function is also provided according to the nomenclature criteria of the 2012 International Mineralogical Association (IMA) report.

Organisationseinheit(en)

Institut für Mineralogie

Typ

Artikel

Journal

LITHOS

Band

362-363

ISSN

0024-4937

Publikationsdatum

06.2020

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Geologie, Geochemie und Petrologie

Elektronische Version(en)

https://doi.org/10.1016/j.lithos.2020.105469 (Zugang: Geschlossen)