Skip to content


Published: 3 February 2021

Fusing Machine Learning and Computer Vision Techniques for Automatic Drill Core Analysis on Visual and Compositional Data.

Quantitative and qualitative geological models of mineral deposits form the basis of the mining value chain, including all subsequent decisions on valuation, mining method, processing method and measures to alleviate environmental impact of mining.

The main input data in such models are derived from analysis of drill cores.

ML4DrillCore goal is embedded in the general vision of more effective and efficient discovery and characterization of mineral deposits.

In the context of digital transformation, this can be done by implementing new innovative Computer Vision (CV) and Machine Learning (ML) methods for the analysis of visual and compositional data, which can assist in making logging both more time-efficient and consistent.

A synergy between the domain-expertise of the Ore Geology group and the artificial intelligence expertise provided by the Machine Learning group has great potential to provide a disruptive technological change in the field of acquisition and analysis of drill core data in the mining industry.


Foteini Liwicki

Foteini Liwicki, Associate Professor

Phone: +46 (0)920 491004
Organisation: Machine Learning, Embedded Intelligent Systems LAB, Department of Computer Science, Electrical and Space Engineering