Spatially Constrained Machine Learning for PRISMA-Based Lithological Mapping of Phosphate Mine Waste Rocks
Minerals · 09.06.2026 · 16 (6) · 619
DOI: 10.3390/min16060619 ↗Kurz gefasst
Fachartikel in der Zeitschrift Minerals, online erschienen am 09.06.2026. Verfasst von Abdelhak El Mansour und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: OCP–UM6P APRA Project.
Abstract (Originalsprache)
Phosphate waste rock piles (PWRPs) generated by open-pit phosphate mining are highly heterogeneous and difficult to characterize using conventional point sampling alone, which limits representative resource assessment, selective recovery, and rehabilitation planning. This study develops an integrated framework combining PRISMA spaceborne hyperspectral imagery, ground-based mineralogical analyses, and spatially constrained machine learning to map lithological heterogeneity at the Benguerir phosphate mining site, Morocco. A three-stage spectral optimization workflow, including atmospheric band masking, Savitzky–Golay filtering, and analysis of variance (ANOVA)-based feature selection, was applied to identify the most discriminative Short-Wave Infrared (SWIR) bands for lithological classification. After removing redundant observations located within shared PRISMA pixel footprints, 127 spatially independent samples were retained for model development. Five supervised classifiers (Random Forest, Extra Trees, XGBoost, Support Vector Machine, and K-Nearest Neighbors) were evaluated under a spatially constrained cross-validation framework aligned with the 30 m native PRISMA pixel size. Ensemble-based models, especially Extra Trees and Random Forest, provided the most stable performance, with balanced accuracies of 0.56–0.69 and area under the receiver operating characteristic curve (AUC) values exceeding 0.95 for carbonate-dominated lithologies. Lower discrimination between phosphate and siliceous facies reflects intrinsic mineralogical mixing and spectral overlap at the sensor scale. Entropy-based uncertainty and posterior probability mapping revealed spatially structured prediction ambiguity concentrated along lithological boundaries and transitional zones, consistent with petrographic evidence of compositional heterogeneity. These results indicate that moderate but stable accuracies likely represent realistic performance limits for spaceborne hyperspectral mapping of complex mining environments under spatial constraints. The proposed framework provides a transferable and uncertainty-aware basis for lithological mapping, selective recovery assessment, and sustainable phosphate waste management.
Förderung
- OCP–UM6P APRA Project
Zitieren
APA
Mansour, A. E., Ouzemou, J., Elghali, A., Elmeknassi, M., Hakkou, R., Benzaazoua, M., & Laamrani, A. (2026). Spatially Constrained Machine Learning for PRISMA-Based Lithological Mapping of Phosphate Mine Waste Rocks. Minerals, 16(6), 619. https://doi.org/10.3390/min16060619
Vancouver
Mansour AE, Ouzemou J, Elghali A, Elmeknassi M, Hakkou R, Benzaazoua M, et al. Spatially Constrained Machine Learning for PRISMA-Based Lithological Mapping of Phosphate Mine Waste Rocks. Minerals. 2026;16(6):619. doi:10.3390/min16060619
BibTeX
@article{Mansour2026,
author = {Mansour, Abdelhak El and Ouzemou, Jamal-Eddine and Elghali, Abdellatif and Elmeknassi, Malak and Hakkou, Rachid and Benzaazoua, Mostafa and Laamrani, Ahmed},
title = {Spatially Constrained Machine Learning for PRISMA-Based Lithological Mapping of Phosphate Mine Waste Rocks},
journal = {Minerals},
year = {2026},
volume = {16},
number = {6},
pages = {619},
doi = {10.3390/min16060619}
}
EUVIMED