Improving Ore Kupferschiefer Assessments with support Vector Machine - Université de Lorraine Access content directly
Poster Communications Year : 2013

Improving Ore Kupferschiefer Assessments with support Vector Machine

Jean-Jacques Royer
  • Function : Author
Jürgen Hartsch
  • Function : Author

Abstract

In this work, we explain the procedure to obtain a better assessment of high copper concentration values from geologic-datasets obtained from restored 3D models. The potential copper zones within the Kupferschiefer (Zechstein base) are predicted for the North-Sudetic Trough in Germany, using geological and geochemical datasets from unfolded/unfaulted 3D models using SKUA Kine3D®. We define the blueprints based on known high copper value locations of the Fore-Sudetic region in Poland, then applying Support Vector Machine (SVM), with the R package e1071, for the mineralized or barren classification. We compared the results of prediction using geo-datasets from restored and non-restored models in the training protocol, finding the first more acquired with the reality. We used the geo-datasets from the restored models of the Fore-Sudetic region for the final assessment in the North Sudetic Trough and compared the results using Weight of Evidence (WofE) procedure, obtaining improved predictions than WofE. The final SVM model and training geo-datasets can even predict other high copper concentrations at the base of Zechstein in Germany.
No file

Dates and versions

hal-04062350 , version 1 (07-04-2023)

Identifiers

Cite

Pablo Mejía-Herrera, Jean-Jacques Royer, Jürgen Hartsch. Improving Ore Kupferschiefer Assessments with support Vector Machine. École Thématique CNRS: ressources minérales-défis scientifiques et sociétaux, 2013, Geneve, Switzerland. ⟨10.13140/RG.2.1.5170.6963⟩. ⟨hal-04062350⟩
10 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More