Low‐Dimensional Controls on Oceanic Basalt Geochemistry Revealed by Regression‐Based Machine Learning Models
Open Access
- 25 November 2025
- journal article
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 2 (4)
Abstract
The low dimensionality of basalt geochemical data has long been inferred but has not been quantitatively evaluated from the relationships among elemental contents. We developed regression‐based machine learning models and examined the relationships among elemental contents for basalts. We applied an extended gradient boosting algorithm (natural gradient boosting), which allows predictions with associated probability distributions, to a training data set of global basalt compositions, including midocean ridge, ocean island, and volcanic arc basalts. From four input elements (Th, Nb, Zr, and Ti), the trained models can successfully predict the contents of 12 trace elements (Rb, Ba, U, La, Ce, Pb, Sr, P, Nd, Y, Yb, and Lu; R 2 > 0.7) and 5 major elements (SiO 2 , MgO, Na 2 O, CaO, and K 2 O; R 2 > 0.67). The adopted model interpretation techniques quantitatively identified key input features for output element estimations, such as similar elemental incompatibility (e.g., Th‐Rb contents) and elemental ratios/products involving different incompatible elements (e.g., Zr/Th ratios for Yb contents). This is consistent with well‐established geochemical principles related to elemental incompatibility and tectonic setting and was achieved without prior geochemical knowledge of the samples. On a projection of a reduced two‐dimensional map constructed from the four input elements, numerical variations of the identified key input features were correlated with the output contents. Given the successfully constructed regression‐based models based on only four input elements, basalt geochemical data have a low dimensionality. Moreover, our approach can potentially provide a more comprehensive understanding of the link between basalt geochemistry and geological processes.Keywords
All Related Versions
Funding Information
- Japan Science and Technology Agency (JPMJSP2114)
- Japan Science and Technology Agency (JP21H05200)
- Japan Society for the Promotion of Science (23KJ0097)
- Japan Society for the Promotion of Science (22H05296)
- Japan Society for the Promotion of Science (23K22600)
- Japan Society for the Promotion of Science (22H04932)
- Japan Society for the Promotion of Science (JP16K21728)
This publication has 35 references indexed in Scilit:
- A practical approach for discriminating tectonic settings of basaltic rocks using machine learningApplied Computing and Geosciences, 2023
- Geochemical fingerprinting of continental and oceanic basalts: A machine learning approachEarth-Science Reviews, 2022
- Lithosphere thickness controls the extent of mantle melting, depth of melt extraction and basalt compositions in all tectonic settings on Earth – A review and new perspectivesEarth-Science Reviews, 2021
- Subduction zone geochemistryGeoscience Frontiers, 2019
- Precursors predicted by artificial neural networks for mass balance calculations: Quantifying hydrothermal alteration in volcanic rocksComputers & Geosciences, 2016
- Quantifying chemical weathering intensity and trace element release from two contrasting basalt profiles, Deccan Traps, IndiaChemical Geology, 2014
- Intra-oceanic island arc origin for Iratsu eclogites of the Sanbagawa belt, central Shikoku, southwest JapanChemical Geology, 2011
- The composition of the EarthChemical Geology, 1995
- Case studies on the origin of basaltContributions to Mineralogy and Petrology, 1983
- Petrogenetic implications of Ti, Zr, Y, and Nb variations in volcanic rocksContributions to Mineralogy and Petrology, 1979