EUVIMEDEUVIMED entdecken
Crossref

Mapping volcanic facies for critical mineral exploration through seismic attributes and machine learning

Danial Mansourian, David Lubo-Robles, Heather Bedle

Interpretation · 01.11.2026 · 14 (4) · T445-T469

DOI: 10.1190/int-2026-1061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Interpretation, online erschienen am 03.11.2026. Verfasst von Danial Mansourian und 2 weiteren Autor:innen. Die Arbeit nennt 107 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Critical minerals (CMs) are essential for emerging technologies; however, their exploration remains challenging because they occur in complex geologic settings and often exhibit weak seismic expression. Volcanic facies (VFs) are one of their sources of occurrence, where minerals such as lead, cobalt, copper, and nickel often accumulate and scatter due to hydrothermal processes. This study proposed a facies-specific machine learning (ML) workflow that integrated a multiattribute approach with supervised and unsupervised ML, aiming to resolve VFs in a complex geologic setting in the Otway Basin, South Australia. Twenty-two seismic attributes were calculated, from which facies-specific attribute combinations were selected. Attributes were then used as input into self-organizing maps (SOM) and independent component analysis (ICA) to find sills, lava flows, anddikes, whereas probabilistic neural networks (PNN) was applied for supervised classification of pyroclastics, mounds, and laccoliths that were not identified using unsupervised methods. Results indicated that SOM better discriminated between sills and lava, and effectively identified dike geometry. ICA improved the delineation of dike boundaries and enhanced the contrast between the intrusions and the background medium, revealing features that were less distinct in SOM results. PNN successfully resolved complex features such as laccoliths. The methodology demonstrated that specific attribute combinations processed through SOM, ICA, and PNN can effectively discriminate between closely related volcanic features that are structurally favorable for CM accumulation.

Zitieren

APA

Mansourian, D., Lubo-Robles, D., & Bedle, H. (2026). Mapping volcanic facies for critical mineral exploration through seismic attributes and machine learning. Interpretation, 14(4), T445-T469. https://doi.org/10.1190/int-2026-1061

Vancouver

Mansourian D, Lubo-Robles D, Bedle H. Mapping volcanic facies for critical mineral exploration through seismic attributes and machine learning. Interpretation. 2026;14(4):T445-T469. doi:10.1190/int-2026-1061

BibTeX
@article{Mansourian2026,
  author = {Mansourian, Danial and Lubo-Robles, David and Bedle, Heather},
  title = {Mapping volcanic facies for critical mineral exploration through seismic attributes and machine learning},
  journal = {Interpretation},
  year = {2026},
  volume = {14},
  number = {4},
  pages = {T445--T469},
  doi = {10.1190/int-2026-1061}
}
Kostenlos starten →