Predicting Mineralogy with Hyperspectral Data: A Benchmark Dataset and Machine Learning Framework to Enable Hyperspectral Geometallurgy
Minerals · 26.06.2026 · 16 (7) · 674
DOI: 10.3390/min16070674 ↗Kurz gefasst
Fachartikel in der Zeitschrift Minerals, online erschienen am 26.06.2026. Verfasst von Samuel T. Thiele und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon Europe research and innovation programme, UK Research and Innovation, Saxon State Office for Environment, Agriculture and Geology.
Abstract (Originalsprache)
Mineralogical data acquired from drillcores provide important constraints for resource estimation, geometallurgical modelling, mineral exploration, and geological interpretation. While hyperspectral imaging is rapidly gaining traction for these applications, it lacks the ability to accurately quantify mineral abundances without extensive calibration data. Here, we build on previous work to demonstrate and benchmark workflows that combine scanning electron microscope (SEM) mineral maps with large-extent multimodal hyperspectral imaging data. The goal is to relate hyperspectral features and mineral abundances using supervised machine learning models, and then apply these models to infer mineralogy across entire drillcores. We adapt the learning process to the non-uniform (unbalanced) composition of most rocks, and achieve reasonable accuracy for most rock-forming minerals. However, we also find that prediction accuracy depends strongly on the representativity of training data—so models often fail to produce accurate maps of rare and accessory minerals. Robust, adaptive and ideally semi-automated sampling approaches might address this shortcoming by identifying locations which ensure optimal coverage of hyperspectral variance. We also emphasise that upscaling from SEM to drillcore scale inevitably involves extrapolation, meaning predictions should always be validated. However, once validated, upscaled mineralogy predictions could provide crucial quantitative data that bridge the scale gap between petrographic observations, metallurgical tests, and geometallurgical models.
Förderung
- European Union’s Horizon Europe research and innovation programme
- UK Research and Innovation
- Saxon State Office for Environment, Agriculture and Geology
Zitieren
APA
Thiele, S. T., Kirsch, M., Frenzel, M., Tolosana-Delgado, R., Kamath, A. V., Guy, B. M., Kim, Y., Tuşa, L., Járóka, T., & Gloaguen, R. (2026). Predicting Mineralogy with Hyperspectral Data: A Benchmark Dataset and Machine Learning Framework to Enable Hyperspectral Geometallurgy. Minerals, 16(7), 674. https://doi.org/10.3390/min16070674
Vancouver
Thiele ST, Kirsch M, Frenzel M, Tolosana-Delgado R, Kamath AV, Guy BM, et al. Predicting Mineralogy with Hyperspectral Data: A Benchmark Dataset and Machine Learning Framework to Enable Hyperspectral Geometallurgy. Minerals. 2026;16(7):674. doi:10.3390/min16070674
BibTeX
@article{Thiele2026,
author = {Thiele, Samuel T. and Kirsch, Moritz and Frenzel, Max and Tolosana-Delgado, Raimon and Kamath, Akshay V. and Guy, Bradley M. and Kim, Yonghwi and Tuşa, Laura and Járóka, Tom and Gloaguen, Richard},
title = {Predicting Mineralogy with Hyperspectral Data: A Benchmark Dataset and Machine Learning Framework to Enable Hyperspectral Geometallurgy},
journal = {Minerals},
year = {2026},
volume = {16},
number = {7},
pages = {674},
doi = {10.3390/min16070674}
}
EUVIMED