DEEP-SEAM: an explainable semi-supervised deep learning framework for mineral prospectivity mapping

Luo, Zijing; Farahbakhsh, Ehsan; Hore, Stephen; Müller, R. Dietmar

doi:10.5194/gmd-19-2593-2026

Articles | Volume 19, issue 7

https://doi.org/10.5194/gmd-19-2593-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-2593-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 7

Model description paper

|

07 Apr 2026

Model description paper |

| 07 Apr 2026

DEEP-SEAM: an explainable semi-supervised deep learning framework for mineral prospectivity mapping

Zijing Luo, Ehsan Farahbakhsh, Stephen Hore, and R. Dietmar Müller

Model code and software

An explainable semi-supervised deep learning framework for mineral prospectivity mapping Zijing Luo et al. https://github.com/EarthByte/MPM_Curnamona_REE

An explainable semi-supervised deep learning framework for mineral prospectivity mapping: DEEP-SEAM v1.0 Zijing Luo et al. https://doi.org/10.5281/zenodo.17098677

Short summary

By combining multi-source data with advanced processing techniques, our deep learning model effectively identifies mineralisation patterns despite extremely limited deposit samples, analyses data and validates the geological relevance of its decisions through explainability analysis, providing a universally reliable solution for artificial intelligence-assisted mineral prospectivity mapping.