Dual-Domain Deep Unfolding Network With Implicit Regularization for Seismic Data Reconstruction
- 9 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-17
Abstract
Deep unfolding networks (DUNs), which offer strong interpretability, have gradually attracted increasing attention in seismic data reconstruction. Most existing DUN approaches are limited to unfolding in the time-space (t–x) domain, making it difficult to fully exploit the multiscale features of seismic signals, thereby decreasing reconstruction performance and often leading to the loss of fine details. To overcome the above limitation, a dual-domain optimization framework is proposed, in which the traditional iterative process is replaced by neural networks, yielding a dual-domain deep unfolding network (D3U-Net) based on implicit regularization. The proposed method combines prior information from both the t–x domain and the wavelet domain, guiding the network to simultaneously capture spatial structural information and frequency characteristics at each stage, thus achieving cooperative reconstruction in both domains and enhancing detail recovery. Meanwhile, an implicit regularization mechanism is introduced, where a learnable neural network substitutes the conventional proximal mapping operator and does not require manual specification of the weights of the regularization term, simplifying the tuning process and endowing the network with greater flexibility and adaptability. Experiments conducted on synthetic data, the BP2004 dataset, and field marine seismic data demonstrate that D3U-Net achieves superior reconstruction accuracy and stability under both regular and random seismic-trace missing scenarios compared with current state-of-the-art methods, confirming overall advantages in reconstruction fidelity, generalization capability, and interpretability.Keywords
Funding Information
- Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project (2024ZD1004101)
- National Natural Science Foundation of China (42274164)
- National Natural Science Foundation of China (42074151)
This publication has 44 references indexed in Scilit:
- FDSANet: Seismic Data Reconstruction Based on a Frequency-Domain Self-Attention NetworkIEEE Geoscience and Remote Sensing Letters, 2025
- Seismic denoising diffusion restoration model for seismic data processingEngineering Applications of Artificial Intelligence, 2025
- D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive SensingIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Seismic Data Reconstruction via Wavelet-Based Residual Deep LearningIEEE Transactions on Geoscience and Remote Sensing, 2022
- Consecutively Missing Seismic Data Interpolation Based on Coordinate Attention UnetIEEE Geoscience and Remote Sensing Letters, 2021
- Interpolating Seismic Data With Conditional Generative Adversarial NetworksIEEE Geoscience and Remote Sensing Letters, 2018
- Seismic data reconstruction using a sparsity-promoting apex shifted hyperbolic Radon-curvelet transformStudia Geophysica et Geodaetica, 2018
- ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing2018
- 3D simultaneous seismic data reconstruction and noise suppression based on the curvelet transformApplied Geophysics, 2017
- Curvelet-based POCS interpolation of nonuniformly sampled seismic recordsJournal of Applied Geophysics, 2012