Garnet major-element composition as an indicator of host-rock type: a machine learning approach using the random forest classifier / supplementary data
Garnet major-element composition as an indicator of host-rock type: a machine learning approach using the random forest classifier / supplementary data
Schoenig, J.; von Eynatten, H.; Tolosana Delgado, R.; Meinhold, G.
Abstract
The database includes 13615 garnet compositions of eight oxides commonly analysed in lab routines: SiO2, TiO2, Al2O3, Cr2O3, FeOtotal, MnO, MgO, and CaO (in wt%). These are complemented by the following covariables:
setting and metamorphic facies class: code indicating the geologic/tectonic setting of the host rock
composition class: code indicating the compositional class of the host rock
author: authors of the original paper providing the data
journal: journal of the original paper
region: origin of the data, in the format "region, country"
sample name: sample ID in the original paper
Pavg(kbar): if available, indicated pressure
Tavg(°C): if available, indicated temperature
host-rock type and/or metamorphic facies: facies indication of host rock
lithology and/or protolith: composition indication of host rock
SiO2: wt%
TiO2: wt%
Al2O3: wt%
Cr2O3: wt%
FeOtotal: wt%
MnO: wt%
MgO: wt%
CaO: wt%
This research was funded by DFG grant EY 23/27-1.
Keywords: garnet major-element composition; host-rock discrimination
Verknüpfte Publikationen
- DOI: 10.1007/s00410-021-01854-w has this (Id 33278) publication as part
-
Forschungsdaten im HZDR-Daten-Repositorium RODARE
Publication date: 2021-10-21 Embargoed access
DOI: 10.14278/rodare.1219
Versions: 10.14278/rodare.1220
License: CC-BY-4.0
Downloads
Permalink: https://www.hzdr.de/publications/Publ-33278