Semantic edge detection of fractures in geological outcrops using edge aware dilated convolutional networks
- 1Electrical and Computer Engineering, Texas A&M University
- 2Petroleum Engineering, Texas A&M University
Abstract
Natural fracture networks govern subsurface fluid flow, rock-mass stability, and strain accommodation in the brittle crust, yet their automated delineation from outcrop imagery remains challenging due to multi-scale size variability, low contrast between fracture boundaries and host-rock texture, and scene clutter from vegetation, shadows, and blast artifacts. Standard encoder-decoder networks apply fixed-size receptive fields that inadequately span the fractal-like scale range of natural discontinuity networks, while gradient-based classical detectors lack the semantic context required to suppress non-structural scene edges. We introduce GeoFractNet: a dilated U-Net coupling ConvNeXt encoder blocks with multi-scale dilated convolutions ( d ∈ {1, 2, 4, 8} ), gated edge-aware skip connections fusing Scharr and Gabor filter responses, and a Sobel Edge-Aware (SEA) Loss that directly penalizes gradient misalignment at fracture boundaries. The model output is a binary semantic edge map (per-pixel classification of fracture-boundary pixels versus background) rather than a vectorized fracture trace network; conversion to discrete trace objects requires subsequent post-processing. Trained on GeoCrack, an open-access fracture edge dataset of 12,158 annotated patches from 49 structurally and lithologically diverse outcrops across five countries, GeoFractNet achieves mIoU = 0.91 , Dice = 0.92 , and Boundary F 1 = 0.90 , outperforming all evaluated classical and deep-learning baselines. Compared to the best performing network in literature, YOLACT++, GeoFractNet reduces false positives by 38% and recovers 94% of long-range fracture edges missed by classical (Canny) edge detection on a curated hard-negative evaluation subset (420 patches containing vegetation, blast holes, and strong illumination gradients). Ablation studies confirm that the gated edge-aware skip connections and SEA Loss provide the largest incremental gains in boundary-sensitive metrics, with no architectural component degrading performance at any ablation step. Code, model weights, and the GeoCrack dataset are openly released, providing a reproducible benchmark for automated fracture characterization in structural geology, geomechanics, and reservoir analogue studies.
Related
- Effect of Simulated Soft-Tissue Edema on Ultrasonographic Detection of Nondisplaced Dentoalveolar Fractures: An Ex Vivo Animal Model Study
- Comparison of Hockey-Stick and Conventional Linear Ultrasound Transducers for Detection of Non-Displaced Dentoalveolar Fractures: An Ex Vivo Paired Comparative Study
- A method for lung cancer detection by means of explainable convolutional neural networks
- Comparative evaluation of convolutional and transformer-based object detection models for brain tumor localization in MRI
- Lightweight convolutional neural network for UAV onboard visual anomaly detection and localization
BibTeX
@article{yaqoob2026semantic,
title = {{Semantic edge detection of fractures in geological outcrops using edge aware dilated convolutional networks}},
author = {Mohammed Yaqoob and Mohammed Ishaq and Mohammed Yusuf Ansari and Thomas Daniel Seers},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-58908-x},
url = {https://doi.org/10.1038/s41598-026-58908-x},
note = {CC BY},
}
RIS
TY - JOUR
TI - Semantic edge detection of fractures in geological outcrops using edge aware dilated convolutional networks
AU - Mohammed Yaqoob
AU - Mohammed Ishaq
AU - Mohammed Yusuf Ansari
AU - Thomas Daniel Seers
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-58908-x
UR - https://doi.org/10.1038/s41598-026-58908-x
AB - Natural fracture networks govern subsurface fluid flow, rock-mass stability, and strain accommodation in the brittle crust, yet their automated delineation from outcrop imagery remains challenging due to multi-scale size variability, low contrast between fracture boundaries and host-rock texture, and scene clutter from vegetation, shadows, and blast artifacts. Standard encoder-decoder networks apply fixed-size receptive fields that inadequately span the fractal-like scale range of natural discontinuity networks, while gradient-based classical detectors lack the semantic context required to suppress non-structural scene edges. We introduce GeoFractNet: a dilated U-Net coupling ConvNeXt encoder blocks with multi-scale dilated convolutions ( d ∈ {1, 2, 4, 8} ), gated edge-aware skip connections fusing Scharr and Gabor filter responses, and a Sobel Edge-Aware (SEA) Loss that directly penalizes gradient misalignment at fracture boundaries. The model output is a binary semantic edge map (per-pixel classification of fracture-boundary pixels versus background) rather than a vectorized fracture trace network; conversion to discrete trace objects requires subsequent post-processing. Trained on GeoCrack, an open-access fracture edge dataset of 12,158 annotated patches from 49 structurally and lithologically diverse outcrops across five countries, GeoFractNet achieves mIoU = 0.91 , Dice = 0.92 , and Boundary F _1 = 0.90 , outperforming all evaluated classical and deep-learning baselines. Compared to the best performing network in literature, YOLACT++, GeoFractNet reduces false positives by 38% and recovers 94% of long-range fracture edges missed by classical (Canny) edge detection on a curated hard-negative evaluation subset (420 patches containing vegetation, blast holes, and strong illumination gradients). Ablation studies confirm that the gated edge-aware skip connections and SEA Loss provide the largest incremental gains in boundary-sensitive metrics, with no architectural component degrading performance at any ablation step. Code, model weights, and the GeoCrack dataset are openly released, providing a reproducible benchmark for automated fracture characterization in structural geology, geomechanics, and reservoir analogue studies.
SN - 2045-2322
ER -