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

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.

Authors

Institutions

Publication Details

Journal
Mining
Published
2026-11-16
DOI
https://doi.org/10.3390/mining6040108
Primary Topic
Remote-Sensing Image Classification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

V. Flores, Mizraim Uriel Flores, Gildardo Godínez-Garrido, Juan-Carlos González-Islas et al.
2 links
Mining
Remote-Sensing Image Classification
article

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

V. Flores, Mizraim Uriel Flores, Gildardo Godínez-Garrido, Juan-Carlos González-Islas, Ma. de Jesús Gutiérrez-Sánchez, Asdrúbal López‐Chau
article en

Abstract

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.

MiningVol. 6(4)
Universidad Autónoma del Estado de Hidalgo (MX), Universidad Autónoma del Estado de México (MX)
Remote-Sensing Image Classification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon