Hyperspectral sensing as a tool for smart environmental monitoring in mine waste management

The use of hyperspectral imaging (HSI) at different scales has become a big ally for a large range of applications in remote sensing, especially within the mining life cycle. In this contribution, we explore the use of HSI sensing, particularly to monitor mine waste at different constellations that might face environmental damaging phenomena: Acid Mine Drainage (AMD). Failure to accurately monitor and remediate such a complex process, leads to long-term impacts on ecosystems and human health, in addition to significant financial consequences and reputational damage to operators. We propose a workflow to integrate hyperspectral visible to near-infrared (VNIR) data, together with mineralogical and geochemical data to precisely map the extent of acid mine drainage using machine learning algorithms. Collected data from the field and further laboratory analyses on a few specimens provide the ground-truth and training data to support the proposed mapping algorithms. Results consist of semi-quantified concentration of dissolved metals, physicochemical properties in water bodies, and associated AMD minerals sub-products (e.g., goethite, jarosite, schwertmannite) within mine waste materials, as well as mineralogical characterization for predictive modeling at laboratory scale.  Regardless of the scale of acquisition, spectral imaging represents a cost-effective tool to enhance the quality of classical environmental analyses both in active and post-mining scenarios, which can increase the overall accuracy of the monitoring, allowing frequent and multi-temporal observations to reveal risk scenarios, take fast corrective actions and keep a continuous control.