A Machine Learning‐Based Approach to Clinopyroxene Thermobarometry: Model Optimization and Distribution for Use in Earth Sciences

Thermobarometry is a fundamental tool to quantitatively interrogate magma plumbing systems and broaden our appreciation of volcanic processes. Developments in random forest‐based machine learning lend themselves to a data‐driven approach to clinopyroxene thermobarometry, allowing users to access lar...

Full description

Saved in:
Bibliographic Details
Published in:Journal of geophysical research. Solid earth 2022-04, Vol.127 (4), p.e2021JB022904-n/a
Main Authors: Jorgenson, C., Higgins, O., Petrelli, M., Bégué, F., Caricchi, L.
Format: Article
Language:English
Subjects:
Algorithms
Chemical composition
Chemistry and Physics of Minerals and Rocks/Volcanology
clinopyroxene thermobarometry
Computational Geophysics
Crystallization
Crystals
Datasets
Decision trees
Distribution
Earth science
Earth sciences
Estimates
Experimental Mineralogy and Petrology
Freeware
Geochemical Modeling
Geochemistry
Geophysics
Informatics
Lava
Learning algorithms
Machine Learning
Machine learning for Solid Earth observation, modeling and understanding
machine learning random forest
Magma
Mean
Median (statistics)
Methods
Mineral and Crystal Chemistry
Mineralogy and Petrology
Minerals
model optimization
Modelling
Neural Networks, Fuzzy Logic, Machine Learning
Optimization
Prediction models
Scripts
Standard error
Storage
Temperature
Thermobarometry
Uncertainty
Volcanic eruptions
Volcanic rocks
Volcanology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thermobarometry is a fundamental tool to quantitatively interrogate magma plumbing systems and broaden our appreciation of volcanic processes. Developments in random forest‐based machine learning lend themselves to a data‐driven approach to clinopyroxene thermobarometry, allowing users to access large experimental data sets that can be tailored to individual applications in Earth Sciences. We present a methodological assessment of random forest thermobarometry using the R freeware package extraTrees. We investigate the model performance, the effect of hyperparameter tuning, and assess different methods for calculating uncertainties. Deviating from the default hyperparameters used in the extraTrees package results in little difference in overall model performance (
ISSN:2169-9313
2169-9356
DOI:10.1029/2021JB022904