EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multiband UAV Segmentation and Geometric Characterization of Mine Tailings: A Site-Held-Out Comparison of U-Net and MobileNetV3-Large

Gildardo Godínez-Garrido, Asdrúbal López Chau, Juan-Carlos Gonzalez-Islas, Víctor Hugo Flores Sánchez, Mizraim Uriel Flores Guerrero, Ma. de Jesús Gutiérrez-Sánchez

Mining · 16.11.2026 · 6 (4) · 108

DOI: 10.3390/mining6040108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mining, online erschienen am 16.11.2026. Verfasst von Gildardo Godínez-Garrido und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gildardo Godínez-Garrido by the Consejo de Ciencia, Tecnología e Innovación de Hidalgo (CITNOVA), Mexico.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable mapping of mine tailings deposits from unmanned aerial vehicle (UAV) products requires evaluation protocols that separate within-site interpolation from transfer to geographically unseen deposits. This study evaluates an eight-channel multiband segmentation workflow for six mining environments in Hidalgo, Mexico, using 4531 aligned 256×256-pixel tiles and nine overlapping semantic annotations. The quantitative analysis focuses on tailings and slope. U-Net and MobileNetV3-Large + Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) are assessed using a reproducible tile-level split (70/15/15, seed 42), six-fold leave-one-site-out (LOSO) validation with three seeds, a full six-site, three-seed A1–A6 input band ablation and a common-hardware benchmark. On the reproducible fixed split, MobileNetV3-Large + LR-ASPP outperforms U-Net in the global branch for tailings (Dice 0.9462 vs. 0.8944) and slope (0.7525 vs. 0.7214), while the class-specific MobileNetV3 tailings branch reaches a Dice score of 0.9507, confirming consistent performance for the tailings class. Under the stricter LOSO protocol, the tailings Dice is essentially tied (0.7356 for MobileNetV3 and 0.7361 for U-Net), whereas the slope Dice is 0.4878 and 0.4703, respectively. Each architecture ranks first at three of the six sites for both labels, and paired Wilcoxon tests on site-level means do not indicate systematic architecture dominance (p=0.8438). On an NVIDIA A100-SXM4-40GB benchmark, U-Net is faster (349.5 vs. 112.7 tiles/s), whereas MobileNetV3 uses 20.1% less peak measured graphics processing unit (GPU) memory. Reproducible digital terrain model (DTM)-referenced geometric postprocessing produces similar area estimates but greater sensitivity in volume. In the 216-job global model band ablation, the RGB+Z+D+GZ configuration without X,Y (A4) reaches the highest mean tailings Dice for U-Net (0.7452) and MobileNetV3 (0.7582). Adding local GZ relative to A3 improves the mean slope Dice by 0.2292 and 0.0903, respectively, with the same positive direction at all six sites; no five-contrast Holm-adjusted Wilcoxon result is significant at 0.05. The results indicate that geographic domain shift dominates a simple architecture ranking; external deposits, independent annotation and survey-grade geometric references remain necessary before operational use.

Förderung

  • Gildardo Godínez-Garrido by the Consejo de Ciencia, Tecnología e Innovación de Hidalgo (CITNOVA), Mexico

Zitieren

APA

Godínez-Garrido, G., Chau, A. L., Gonzalez-Islas, J., Sánchez, V. H. F., Guerrero, M. U. F., & Gutiérrez-Sánchez, M. D. J. (2026). Multiband UAV Segmentation and Geometric Characterization of Mine Tailings: A Site-Held-Out Comparison of U-Net and MobileNetV3-Large. Mining, 6(4), 108. https://doi.org/10.3390/mining6040108

Vancouver

Godínez-Garrido G, Chau AL, Gonzalez-Islas J, Sánchez VHF, Guerrero MUF, Gutiérrez-Sánchez MDJ. Multiband UAV Segmentation and Geometric Characterization of Mine Tailings: A Site-Held-Out Comparison of U-Net and MobileNetV3-Large. Mining. 2026;6(4):108. doi:10.3390/mining6040108

BibTeX
@article{GodnezGarrido2026,
  author = {Godínez-Garrido, Gildardo and Chau, Asdrúbal López and Gonzalez-Islas, Juan-Carlos and Sánchez, Víctor Hugo Flores and Guerrero, Mizraim Uriel Flores and Gutiérrez-Sánchez, Ma. de Jesús},
  title = {Multiband UAV Segmentation and Geometric Characterization of Mine Tailings: A Site-Held-Out Comparison of U-Net and MobileNetV3-Large},
  journal = {Mining},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {108},
  doi = {10.3390/mining6040108}
}
Kostenlos starten →