Preprints
https://doi.org/10.5194/egusphere-2024-3448
https://doi.org/10.5194/egusphere-2024-3448
20 Nov 2024
 | 20 Nov 2024
Status: this preprint is open for discussion.

Multiphysics property prediction from hyperspectral drill core data

Akshay Kamath, Samuel Thiele, Moritz Kirsch, and Richard Gloaguen

Abstract. Hyperspectral data provides rich quantitative information on both the mineralogical and fine-scale textural properties of rocks, which, in turn, largely control their petrophysical characteristics. We therefore developed a deep learning model to predict petrophysical properties directly from hyperspectral drill core data. Our model learns relevant features from high-dimensional hyperspectral data and co-registered sonic, gamma-gamma density and gamma-ray logs to infer slowness, density, and gamma-ray counts. We demonstrated the performance of this approach on data acquired in the Spremberg region of Germany. Our results demonstrate that with meticulous pre-processing steps and thorough data cleaning, one can overcome the difference in capturing resolution and learn the relationship between hyperspectral data and petrophysics. Using a test dataset from a spatially independent borehole, we generate a pixel-resolution (≈ 1 mm2) model of the petrophysical properties and resample it to match the measured logs. This test indicates substantial accuracy, with R2 scores and root-mean-squared errors (RMSE) of 0.7 and 16.55 μs.m-1, 0.86 and 0.06 g.cm-3 and 0.90 and 15.29 API for the slowness, density and gamma-ray readings respectively. Overall, our findings lay the groundwork for building deep learning models that can learn to predict physical and mechanical rock properties from hyperspectral data. Such models could provide the high-resolution but large-extent data needed to bridge the different scales of mechanical and petrophysical characterisation.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Akshay Kamath, Samuel Thiele, Moritz Kirsch, and Richard Gloaguen

Status: open (until 17 Jan 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Akshay Kamath, Samuel Thiele, Moritz Kirsch, and Richard Gloaguen
Akshay Kamath, Samuel Thiele, Moritz Kirsch, and Richard Gloaguen

Viewed

Total article views: 123 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
86 30 7 123 3 3
  • HTML: 86
  • PDF: 30
  • XML: 7
  • Total: 123
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 20 Nov 2024)
Cumulative views and downloads (calculated since 20 Nov 2024)

Viewed (geographical distribution)

Total article views: 119 (including HTML, PDF, and XML) Thereof 119 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 13 Dec 2024
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.