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 (<0.2 kbar and <3°C difference in standard error estimate, SEE). However, accuracy is greatly affected by how the final value from the distribution of trees in the random forest is selected (mean, median, or mode). Using the mean value leads to higher residuals between experimental and predicted P and T, whereas using median values produces smaller residuals. Additionally, this work provides two scripts for users to apply the methodology to natural data sets. The first script permits modification and filtering of the model calibration data set. The second script contains premade models, where users can rapidly input their data to recover PT estimates (SEE clinopyroxene‐only model: 3.2 kbar, 72.5°C and liquid‐clinopyroxene model: 2.7 kbar, 44.9°C). Additionally, the scripts allow the user to estimate the uncertainty for each analysis, which in some cases is significantly smaller than the reported SEE. These scripts are open source and can be accessed at https://github.com/corinjorgenson/RandomForest-cpx-thermobarometer.
Establishing a quantitative link between magmatic processes occurring at depth and volcanic eruption dynamics is essential to forecast the future behaviour of volcanoes, and to correctly interpret monitoring signals at active centres. Chemical zoning in minerals, which captures successive events or states within a magmatic system, can be exploited for such a purpose. However, to develop a quantitative understanding of magmatic systems requires an unbiased, reproducible method for characterising zoned crystals. We use image segmentation on thin section scale chemical maps to segment textural zones in plagioclase phenocrysts. These zones are then correlated throughout a stratigraphic sequence from Saint Kitts (Lesser Antilles), composed of a basal pyroclastic flow deposit and a series of fall deposits. Both segmented phenocrysts and unsegmented matrix plagioclase are chemically decoupled from whole rock geochemical trends, with the latter showing a systematic temporal progression towards less chemically evolved magma (more anorthitic plagioclase). By working on a stratigraphic sequence, it is possible to track the chemical and textural complexity of segmented plagioclase in time, in this case on the order of millennia. In doing so, we find a relationship between the number of crystal populations, deposit thickness and time. Thicker deposits contain a larger number of crystal populations, alongside an overall reduction in this number towards the top of the deposit. Our approach provides quantitative textural parameters for volcanic and plutonic rocks, including the ability to measure the amount of crystal fracturing. In combination with mineral chemistry, these parameters can strengthen the link between petrology and volcanology, paving the way towards a deeper understanding of the magmatic processes controlling eruptive dynamics.
Establishing a quantitative link between magmatic processes occurring at depth and volcanic eruption dynamics is essential to forecast the future behaviour of volcanoes, and to correctly interpret monitoring signals at active centres. Chemical zoning in minerals, which captures successive events or states within a magmatic system, can be exploited for such a purpose. However, to develop a quantitative understanding of magmatic systems requires an unbiased, reproducible method for characterising zoned crystals. We use image segmentation on thin section scale chemical maps to segment textural zones in plagioclase phenocrysts. These zones are then correlated throughout a stratigraphic sequence from Saint Kitts (Lesser Antilles), composed of a basal pyroclastic flow deposit and a series of fall deposits. Both segmented phenocrysts and unsegmented matrix plagioclase are chemically decoupled from whole rock geochemical trends, with the latter showing a systematic temporal progression towards less chemically evolved magma (more anorthitic plagioclase). By working on a stratigraphic sequence, it is possible to track the chemical and textural complexity of segmented plagioclase in time, in this case on the order of millennia. In doing so, we find a relationship between the number of crystal populations, deposit thickness and time. Thicker deposits contain a larger number of crystal populations, alongside an overall reduction in this number towards the top of the deposit. Our approach provides quantitative textural parameters for volcanic and plutonic rocks, including the ability to measure the amount of crystal fracturing. In combination with mineral chemistry, these parameters can strengthen the link between petrology and volcanology, paving the way towards a deeper understanding of the magmatic processes controlling eruptive dynamics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.