3D seismic salt dome segmentation using a hybrid UNet with global attention, denoising pretraining, and discriminative transfer learning
Year: 2026
Type: article
Abstract: Automated delineation of salt structures from three-dimensional seismic data remains a fundamental challenge in structural interpretation, constrained by severe scarcity of expert-labeled training data and the persistent tendency of segmentation networks to misclassify acquisition noise as salt boundaries. We present the first application of unfactorized three-dimensional global self-attention to seismic salt dome segmentation, within a hybrid UNet combining volumetric convolution with complete spatial context modeling. The model is trained with self-supervised denoising pretext training across three unlabeled surveys, followed by discriminative transfer learning on binary Zechstein salt annotations from the Netherlands F3 block using layer-wise learning rate decay, gradual unfreezing, and Unified Focal Loss. This pretext task develops explicit noise-discrimination representations before salt-specific supervised adaptation, providing seismic-specific initialization that generic contrastive or masked objectives cannot. Validation on the F3 dataset achieved Dice = 0.843, IoU = 0.729, Precision = 0.831, and MCC = 0.829, representing statistically significant improvements of 5.0–9.2% over the state-of-the-art 3D CNN + Swin architecture. On the spatially distinct blind test partition containing a large Zechstein diapir, performance gaps widened to 10.8–17.9%, with the proposed model exhibiting substantially lower degradation (3.7% Dice reduction) versus Swin (8.7%) and the baseline CNN (11.7%). Zero-shot cross-basin evaluation on the recently released Gulf of America OCS volume (NAMSS survey B-51-94-LA) provides the first structural delineation of Louann Salt diapir geometries in this survey, confirming cross-basin generalization to geologically distinct salt morphologies and constituting an original geoscientific contribution to one of the world's most tectonically significant salt provinces.
Authors: Matin Mahzad, Majid Bagheri
Institution: University of Tehran
Language: English
Subfield: Geophysics
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,040
OpenAlex ID: W7167260641