English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
  Local TagsRelease HistoryDetailsSummary

Released
Conference Paper

Estimating the thermal conductivity of plutonic rocks from major oxide composition using data-driven machine learning

Authors

Yu,  Ruyang
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Shu,  Jiang
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

/persons/resource/fuchs

Fuchs,  Sven
4.8 Geoenergy, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Peng,  Peng
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Li,  Yuanping
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Wang,  Hu
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

External Ressource
No external resources are shared
Fulltext (public)
There are no public fulltexts stored in GFZpublic
Supplementary Material (public)
There is no public supplementary material available
Citation

Yu, R., Shu, J., Fuchs, S., Peng, P., Li, Y., Wang, H. (2023): Estimating the thermal conductivity of plutonic rocks from major oxide composition using data-driven machine learning, XXVIII General Assembly of the International Union of Geodesy and Geophysics (IUGG) (Berlin 2023).
https://doi.org/10.57757/IUGG23-3751


Cite as: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5020793
Abstract
The thermal conductivity of plutonic rocks is essential to accurately estimate the temperature distribution in the earth’s crust and to model heat-related processes in geodynamics. This study compiled an extensive dataset of 530 representative plutonic rock samples, containing thermal conductivity, major oxide composition and (for two subsets of data) modal mineralogy. Three data-driven machine learning algorithms (ML; i.e., support vector regression, random forest and extreme gradient boosting) are employed to estimate the thermal conductivity of plutonic rocks using the major oxide composition feature as input variables first time. The performance of such ML-based models is evaluated against a geochemically-compositional model and eight mineral-driven physically-based empirical mixing models. Results show that the means of predicted thermal conductivity by the ML-based models and the geochemically-compositional model are no actual difference from the measured thermal conductivity, with a significance level of 5%. However, the best performing non-ML model for estimating thermal conductivity, the geochemically-compositional model, is outperformed by the ML-based models. The highest prediction accuracy was achieved by extreme gradient boosting, which can reduce the mean absolute percentage error and root mean square error by more than 50%. Besides, SiO2 is confirmed as the most important independent variable, followed by Al2O3, TiO2, CaO, and K2O. The present study explores, for the first time, the use of ML algorithms to estimate the thermal conductivity of plutonic rocks from their major oxide composition.