Efficient Earth Observation System for Acid Mine Drainage Monitoring

Acid Mine Drainage (AMD), a significant water pollutant from sulfide mineral oxidation in mining areas, generates sulfuric acid and harmful substances. Effective AMD management involves careful material handling, treatment, and water management. Imaging spectroscopy provides a practical alternative to traditional chemical analysis, identifying pyrite oxidation "hot spots" and sulfate mineral formation. This research develops robust AMD monitoring systems using machine learning techniques on optical multi- and hyperspectral data. We use hyperspectral (PIKA L camera, UAV) and multispectral (Sentinel-2, orbital) datasets at the Lítov post-mine dump (Sokolov lignite basin, Czech Republic). Validated against XRD mineralogy and Google Earthidentified hotspots, Radial Basis Function Support Vector Machine (RBF SVM) outperforms other ML methods in identifying AMD hot spots and class separation. RBF SVM effectively detects AMD discharge and distinguishes mineral mixtures (oxy-hydroxides and oxides) using both Pika L and Sentinel-2 data.

Acknowledgments:

The presented analysis was conducted under the support of the EC grant MultiMiner. The MultiMiner project is funded by the European Union’s Horizon Europe research and innovation actions programme under Grant Agreement No. 10109137474.