Machine Learning Thermobarometry for Biotite‐Bearing Magmas

Li, Xiaoyan; Zhang, Chao

doi:10.1029/2022jb024137

Cited by 37 publications

(15 citation statements)

References 145 publications

(148 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A type of random forest machine learning algorithm, Extremely Randomized Trees, was used to train all the models using the package “ranger” and the splitrule “extratrees” (Wright & Ziegler, 2017) in R (R Core Team, 2013), as it has been shown to have the highest predictive capability among a selection of supervised learning algorithms (e.g., Li & Zhang, 2022; Petrelli et al., 2020). In short, random forest algorithms are an ensemble machine learning approach involving multiple decision trees, where the output of all individual trees is aggregated to form an averaged prediction.…”

Section: Developing Hygrothermobarometric and Anorthite Content Modelsmentioning

confidence: 99%

Plagioclase‐Saturated Melt Hygrothermobarometry and Plagioclase‐Melt Equilibria Using Machine Learning

Cutler,

Cassidy,

Blundy

2024

Geochem Geophys Geosyst

View full text Add to dashboard Cite

Compositions of plagioclase‐melt pairs are commonly used to constrain temperatures (T), dissolved water contents (H2O) and pressures (P) of pre‐eruptive magma storage and transport. However, previous plagioclase‐based thermometers, hygrometers, and barometers can have significant errors, leading to imprecise reconstructions of conditions during plagioclase growth. Here, we explore whether we can refine existing plagioclase‐based hygrothermobarometers with either plagioclase‐melt or melt‐only chemistry (±T/H2O), calibrated using random forest machine learning on experimental petrology data (n = 1,152). We find that both the plagioclase‐melt and melt‐only models return similar cross‐validation root‐mean‐square errors (RMSEs), as the melt holds most of the P‐T‐H2O information rather than the plagioclase. T/H2O‐dependent melt models have test set RMSEs of 25°C, 0.70 wt.% and 76 MPa for temperature, H2O content and pressure, respectively, while T/H2O‐independent models have RMSEs of 38°C, 0.97 wt.% and 91 MPa. The melt thermometer and hygrometer are applicable to a wide range of plagioclase‐bearing melts at temperatures between 664 and 1355°C, and with H2O concentrations up to 11.2 wt.%, while the melt barometer is suitable for pressures of ≤500 MPa. An updated plagioclase‐melt equilibrium model has also been calibrated, allowing the equilibrium anorthite content to be predicted with an error of 5.8 mol%. The new P‐T‐H2O‐An models were applied to matrix glasses and melt inclusions from the 1980 Mount St Helens (USA) and 2014–2015 Holuhraun (Iceland) eruptions, corroborating previous independent estimates and observations. Models are available at https://github.com/kyra‐cutler/Plag‐saturated‐melt‐P‐T‐H2O‐An, enabling assessment of plagioclase‐melt equilibrium and characterization of last‐equilibrated P‐T‐H2O conditions of plagioclase‐saturated magmas.

show abstract

Section: Developing Hygrothermobarometric and Anorthite Content Modelsmentioning

confidence: 99%

Plagioclase‐Saturated Melt Hygrothermobarometry and Plagioclase‐Melt Equilibria Using Machine Learning

Cutler,

Cassidy,

Blundy

2024

Geochem Geophys Geosyst

View full text Add to dashboard Cite

show abstract

“…These are the problems that do not have existing accepted solutions, rely heavily on judgments of highly experienced experts, yet could lead to the most profound scientific insights if investigated properly. A few studies explore the promise of ML in multi‐disciplinary data integration for predicting drought behavior in the Colorado River Basin based on various Earth System Models (Talsma et al., 2022), for predicting sea surface variabilities in the South China Sea (Shao et al., 2021), for geothermal heat flow prediction from multiple geophysical and geological datasets (Lösing & Ebbing, 2021), for identifying volcano's transition from non‐eruptive to eruptive states (Manley et al., 2021), for understanding the geodynamic history using geochemical data (Jorgenson et al., 2022; X. Lin et al., 2022; X. Li & Zhang, 2022; Saha et al., 2021; Thomson et al., 2021; Y. Wang et al., 2021), and for characterizing geodetic signals by their sources (Hu et al., 2021). Albert (2022) uses an unsupervised deep NN structure to predict future atmospheric structures from past measurements to enable infrasound propagation modeling.…”

Section: Highlightsmentioning

confidence: 99%

“…A few studies explore the promise of ML in multi-disciplinary data integration for predicting drought behavior in the Colorado River Basin based on various Earth System Models (Talsma et al, 2022), for predicting sea surface variabilities in the South China Sea (Shao et al, 2021), for geothermal heat flow prediction from multiple geophysical and geological datasets (Lösing & Ebbing, 2021), for identifying volcano's transition from non-eruptive to eruptive states (Manley et al, 2021), for understanding the geodynamic history using geochemical data (Jorgenson et al, 2022;X. Lin et al, 2022;X. Li & Zhang, 2022;Saha et al, 2021;Thomson et al, 2021;, and for characterizing geodetic signals by their sources (Hu et al, 2021).…”

Section: Multiphysical and Multi-disciplinary Information Integrationmentioning

confidence: 99%

Machine Learning Developments and Applications in Solid‐Earth Geosciences: Fad or Future?

O’Malley

Beroza

et al. 2023

JGR Solid Earth

View full text Add to dashboard Cite

After decades of low but continuing activity, applications of machine learning (ML) in solid Earth geoscience have exploded in popularity. This special collection provides a snapshot of those applications, which range from data processing to inversion and interpretation, for which ML appears particularly well suited. Inevitably, there are variations in the degree to which these methods have been developed. We hope that the progress seen in some areas will inspire efforts in others. Challenges remain, including the formidable task of how geoscience can keep pace with developments in ML while ensuring the scientific rigor that our field depends on, but with improvements in sensor technology and accelerating rates of data accumulation, the methods of ML seem poised to play an important role for the foreseeable future.

show abstract

“…The calculated temperatures of Tongchang-Chang'anchong biotites display the range of 776-830 • C, using the thermometer of [59]. We also calculated the Cl/OH ratios in the melt by the compositions of biotites according to the method of [60].…”

Section: Biotitementioning

confidence: 99%

In Situ Mineralogical Constraints on Magmatic Process for Porphyry Deposits in the Upper Crust: A Case from Tongchang–Chang’anchong Porphyry Deposits, SW China

Wang

Zheng

et al. 2023

Minerals

View full text Add to dashboard Cite

The magmatic process within upper crust encompasses various contents such as the transition between magmatic and hydrothermal systems and changes in oxygen fugacity (ƒO2), which ultimately play key roles in the formation of porphyry Cu deposits (PCDs). However, tracing these magmatic processes, especially in porphyry systems, is not an easy task. This study reported the detailed process of magmatic fluid exsolution and systematical variation of magmatic ƒO2 within the upper crust of a Tongchang–Chang’anchong porphyry Cu deposit, based on detailed investigations of mineral crystallization sequences and compositional features of the minerals in the fertile porphyries. Results indicate that the fertile porphyries show a high initial ƒO2, with ΔFMQ ≥ +3.0 (ΔFMQ is the deviation of logƒO2 from the fayalite–magnetite–quartz (FMQ) buffer). The magmatic ƒO2 (ΔFMQ) continued to decrease to ~+2 until fluid exsolution occurred at ~790 °C due to wall-rock contamination. The magmatic fluid exsolution process caused a temporary increase in the ƒO2 (to ΔFMQ = ~+3.4). The high magmatic ƒO2 during this process (790–750 °C) resulted in a higher content of ore-forming materials in the exsolved magmatic fluid. When the temperature dropped below 750 °C, the magmatic ƒO2 began to continuously decrease and eventually reached ΔFMQ = ~+0.6. The lower magmatic ƒO2 hindered the further migration of ore-forming materials through the exsolved fluid during this process (< 750 °C). Results of this study indicate that the initial magma during the upper crustal magmatic process of PCDs generally has a high ƒO2, and the contamination of reduced components can significantly decrease the magmatic ƒO2. The early magmatic fluid exsolution process can maintain a high magmatic ƒO2 condition, thereby efficiently extracting ore-forming minerals and producing ore-forming fluids, which is the key to the formation of PCDs. The latter continuous decrease in magmatic ƒO2 during the fluid exsolution process may be the reason preventing the Tongchang–Chang’anchong porphyry Cu deposit to form a giant PCD.

show abstract

Machine Learning Thermobarometry for Biotite‐Bearing Magmas

Cited by 37 publications

References 145 publications

Plagioclase‐Saturated Melt Hygrothermobarometry and Plagioclase‐Melt Equilibria Using Machine Learning

Plagioclase‐Saturated Melt Hygrothermobarometry and Plagioclase‐Melt Equilibria Using Machine Learning

Machine Learning Developments and Applications in Solid‐Earth Geosciences: Fad or Future?

In Situ Mineralogical Constraints on Magmatic Process for Porphyry Deposits in the Upper Crust: A Case from Tongchang–Chang’anchong Porphyry Deposits, SW China

Contact Info

Product

Resources

About