Suche von Lagerstätten mit Hilfe künstlicher Intelligenz

G.E.O.S., together with partners DIMAP Spectral and ImageAir, participated as team "Phar Lap" in the Explorer Challenge organised by Oz Minerals (Australia) via the platform "Unearthed". Based on several terabytes of exploration data for an area of several 1,000 km² with several thousand complete drill hole data, geophysical data, geological and other data, the challenge was to identify areas with expected IOCG (Iron-Oxide-Copper-Gold) mineralisation.

This required the use of artificial intelligence methods. In addition to the available data, multispectral airborne data was also acquired by the "Phar Lap" team and included in the algorithms. For this purpose, a complete workflow was developed and successfully implemented by G.E.O.S. in cooperation with the partners in the team within the available period from February to May 2019.

Searching for deposits with the help of Artificial Intelligence


  • Processing of drill core data and geophysical interpretation
  • Development of two different methods of machine learning
  • Training
  • Creation of Probabilistic Maps