Direction-Aware Masked Pretraining on 3D Seismic Data with Transfer to Cross-Area Acoustic Impedance Inversion
Abstract
Seismic feature extraction and acoustic impedance inversion are important for subsurface characterisation, but sparse well-log data limit the generalisation of data-driven inversion models across different areas. Self-supervised masked pretraining offers a way to exploit large volumes of unlabelled seismic data; however, conventional approaches often overlook the directional characteristics of 3D seismic data. We propose a direction-aware masked autoencoder (DA-MAE) that distinguishes lateral reflector structure from vertical waveform characteristics in 3D post-stack data. The framework incorporates this distinction into token representation, masking geometry, and reconstruction constraints on reflector continuity and waveform fidelity. We evaluate DA-MAE through masked reconstruction on an independent field survey and cross-area acoustic impedance inversion using two additional field areas. Reconstruction experiments show that performance is more sensitive to lateral token resolution than to moderate changes in vertical patch length, and that increasing encoder capacity does not fully compensate for coarse tokenization. Moreover, the preferred token scales and masking strategies vary between reconstruction and inversion, suggesting that reconstruction fidelity alone is not a reliable indicator of transferability. In cross-area inversion, the pretrained representations remain effective in the target area and improve impedance prediction, demonstrating their transferability across different seismic surveys. These results provide practical guidance for seismic-specific masked pretraining and its application to acoustic impedance inversion.
Related
- Bayesian Joint Velocity and Impedance Inversion via Diffusion Models Conditioned on Common Image Gathers
- Multimodal Interaction and Residual Fusion for Cross-Well Acoustic-Impedance Reconstruction
- Separation of Source, Site, and Path Effects Based on Elastic Radiative Transfer Theory, Part 2: Generalized Inversion of Source and Site Parameters and Application to Metropolitan France
- Structure-dependent failure modes of neural priors in acoustic full-waveform inversion
- 3D seismic salt dome segmentation using a hybrid UNet with global attention, denoising pretraining, and discriminative transfer learning
BibTeX
@misc{tang2026directionaware,
title = {{Direction-Aware Masked Pretraining on 3D Seismic Data with Transfer to Cross-Area Acoustic Impedance Inversion}},
author = {Man Tang and Zhaoyun Zong and Diqiong Jiang and Gen Li and Jiayun Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24615},
eprint = {2609.24615},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24615},
}
RIS
TY - UNPB
TI - Direction-Aware Masked Pretraining on 3D Seismic Data with Transfer to Cross-Area Acoustic Impedance Inversion
AU - Man Tang
AU - Zhaoyun Zong
AU - Diqiong Jiang
AU - Gen Li
AU - Jiayun Li
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.24615
UR - https://arxiv.org/abs/2609.24615
AB - Seismic feature extraction and acoustic impedance inversion are important for subsurface characterisation, but sparse well-log data limit the generalisation of data-driven inversion models across different areas. Self-supervised masked pretraining offers a way to exploit large volumes of unlabelled seismic data; however, conventional approaches often overlook the directional characteristics of 3D seismic data. We propose a direction-aware masked autoencoder (DA-MAE) that distinguishes lateral reflector structure from vertical waveform characteristics in 3D post-stack data. The framework incorporates this distinction into token representation, masking geometry, and reconstruction constraints on reflector continuity and waveform fidelity. We evaluate DA-MAE through masked reconstruction on an independent field survey and cross-area acoustic impedance inversion using two additional field areas. Reconstruction experiments show that performance is more sensitive to lateral token resolution than to moderate changes in vertical patch length, and that increasing encoder capacity does not fully compensate for coarse tokenization. Moreover, the preferred token scales and masking strategies vary between reconstruction and inversion, suggesting that reconstruction fidelity alone is not a reliable indicator of transferability. In cross-area inversion, the pretrained representations remain effective in the target area and improve impedance prediction, demonstrating their transferability across different seismic surveys. These results provide practical guidance for seismic-specific masked pretraining and its application to acoustic impedance inversion.
ER -