Articles | Volume 16, issue 4/5
https://doi.org/10.5194/se-16-351-2025
https://doi.org/10.5194/se-16-351-2025
Research article
 | 
15 May 2025
Research article |  | 15 May 2025

Multiphysics property prediction from hyperspectral drill core data

Akshay V. Kamath, Samuel T. Thiele, Moritz Kirsch, and Richard Gloaguen

Related authors

TensorWeave 1.0: Interpolating geophysical tensor fields with spatial neural networks
Akshay V. Kamath, Samuel T. Thiele, Hernan Ugalde, Bill Morris, Raimon Tolosana-Delgado, Moritz Kirsch, and Richard Gloaguen
EGUsphere, https://doi.org/10.5194/egusphere-2025-2345,https://doi.org/10.5194/egusphere-2025-2345, 2025
Short summary
Hyperspectral mapping of density, porosity, stiffness, and strength in hydrothermally altered volcanic rocks
Samuel T. Thiele, Gabor Kereszturi, Michael J. Heap, Andréa de Lima Ribeiro, Akshay Kamath, Maia Kidd, Matías Tramontini, Marina Rosas-Carbajal, and Richard Gloaguen
EGUsphere, https://doi.org/10.5194/egusphere-2025-1904,https://doi.org/10.5194/egusphere-2025-1904, 2025
Short summary

Cited articles

Albawi, S., Mohammed, T. A., and Al-Zawi, S.: Understanding of a convolutional neural network, 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, 2017, 1–6, https://doi.org/10.1109/ICEngTechnol.2017.8308186, 2017. a
Asquith, G., Krygowski, D., Henderson, S., and Hurley, N.: Basic Well Log Analysis, American Association of Petroleum Geologists, https://doi.org/10.1306/Mth16823, 2004. a, b
Baker, P.: Density logging with gamma rays, Transactions of the AIME, 210, 289–294, https://doi.org/10.2118/940-g, 1957. a
Borg, G., Piestrzyński, A., Bachmann, G. H., Puttman, W., Walther, S., and Fiedler, M.: An overview of the European Kupferschiefer deposits, Economic Geology Special Publication, Special Publication, 455–486, 2012. a
Bourbié, T., Coussy, O., and Zinszner, B.: Acoustics of Porous Media, Editions TECHNIP, ISBN 0872010252, 1987. a
Download
Short summary
We developed a deep learning model that uses hyperspectral imaging data to predict key physical rock properties, specifically density, slowness, and gamma-ray values. Our model successfully learned to translate hyperspectral information into predicted physical properties. Tests on independent data gave accurate results, demonstrating the potential of hyperspectral data for mapping physical rock properties.
Share