Organizations: School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China. · Geophysical Technology Research and Development Center, BGP, Zhuozhou, Hebei, 072751, China · School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China.
Large gaps in seismic acquisition disrupt reflection events and hinder spectral recovery. Existing seismic interpolation deep unfolding networks primarily rely on localized spatial priors, limiting their ability to aggregate the global context necessary for reconstructing these extensive missing regions. We propose a spatial-spectral interactive projection-onto-convex-sets network (SSI-POCS) to tackle this severely ill-posed problem. By unfolding the classical iterative solver, our network integrates physical consistency with dual-domain deep priors via learned transforms, soft thresholding, and exact data reinsertion. Within the learned prior, a spatial Restormer branch captures local waveform structures, while a fast Fourier convolution (FFC) branch extracts global context, effectively suppressing incoherent components and enhancing spectral energy concentration in the f−k domain. A dual-domain fusion module exchanges these complementary features via bidirectional channel attention and gated modulation, yielding substantial interpolation improvements. To overcome the severe loss of lateral continuity caused by large gaps, we introduce structural similarity (SSIM) supervision, complemented by focal frequency loss (FFL) and transform consistency constraints to suppress incoherent high-frequency components and regularize training. Experiments on a synthetic salt dome and a North Sea field dataset under 50% random and consecutive trace removal demonstrate the effectiveness of SSI-POCS. It significantly enhances event continuity across large gaps and mitigates artifacts, achieving a 3.285~dB SNR improvement over the best competing method while reducing parameters by 75.66%.
Figures & tables
Fig. 1: Overall architecture of the proposed deep unrolling framework.
Fig. 2: Detailed architecture of a single unrolled stage.
Fig. 3: Detailed structure of the Dual-domain Fusion Module (DFM).
Fig. 4: Qualitative comparison of reconstruction results on the MAVO dataset under 50% trace removal. (a) Random undersampling (shot 180). (b) Consecutive large gaps (shot 548). We restore the seismic data to its original amplitude range.
Dataset
SEG C3
MAVO
Model
MAE ↓
SNR ↑
SSIM ↑
MAE ↓
SNR ↑
SSIM ↑
Curvelet
2.366e-02
20.131
0.784
1.292e-02
24.600
0.869
POCSNet
1.664e-02
22.486
0.890
9.237e-03
26.550
0.929
SPNet
1.236e-02
22.281
0.883
9.444e-03
26.446
0.926
D3UNet
1.366e-02
24.304
0.920
8.138e-03
27.840
0.937
Ours
7.356e-03
31.082
0.974
4.749e-03
33.988
0.973
TABLE I: Test-set results with 50% random trace removal. Bold: best.
Dataset
SEG C3
MAVO
Model
MAE ↓
SNR ↑
SSIM ↑
MAE ↓
SNR ↑
SSIM ↑
Curvelet
2.220e-01
1.0578
0.517
2.333e-01
1.0598
0.509
POCSNet
3.174e-02
17.810
0.724
1.660e-02
23.178
0.866
SPNet
3.875e-02
15.578
0.719
2.298e-02
19.110
0.860
D3UNet
2.825e-02
18.527
0.729
1.317e-02
24.241
0.870
Ours
2.415e-02
20.241
0.817
1.111e-02
27.526
0.898
TABLE II: Test-set results with 50% contiguous trace removal.
Fig. 5: f – k spectra for MAVO examples with consecutive trace removal: (a)–(c) 50% removal (shot 548); (d)–(f) 30% removal (shot 2).
Figure 8
Fig. 6: Branch ablation in the f – k domain (SEG C3 section 24-24).
Fig. 7: Loss ablation on SEG C3. (a) and (b) Effect of LSSIM (highlighting complex dipping events). (c) and (d) Effect of LFFL on the f – k spectra (highlighting spectral leakage).
Fusion
Loss Functions
MSE ↓
SSIM ↑
SNR ↑
Concat
DFM
LSSIM
LFFL
✓
5.604e-04
0.954
26.936
✓
4.952e-04
0.958
27.503
✓
✓
4.723e-04
0.963
27.734
✓
✓
✓
4.719e-04
0.963
27.736
*All models use the Spa–FFC architecture and the base L1+SymLoss supervision.
TABLE III: Comprehensive Ablation Study.
Fig. 8: Model performance and complexity analysis. (a) Impact of the unrolling depth N on validation SNR and computational memory. (b) Performance-complexity trade-off: SNR versus parameter count.
Seismic data interpolation must reconcile reconstruction fidelity with the computational budgets of acquisition quality control and subsequent imaging. Fixed-depth unfolding networks are optimized for a single operating point, whereas their intermediate estimates may be insufficiently trained for early deployment. We present MetaPOCS, a meta-learned multi-exit unfolding framework for budget-aware seismic interpolation. Building on a spatial--spectral POCS reconstruction backbone, MetaPOCS supervises intermediate stages and preserves the acquired traces at every exit. A Meta-GF-based optimization procedure constructs exit-oriented parameter displacements from a common initialization and learns their fusion weights through an equal-exit outer objective. The weights vary across parameter tensors and respect the nested support of the reconstruction stages. We derive the resulting fusion hypergradient to characterize how the outer objective reallocates competing updates, and distinguish this mechanism from scalar loss reweighting. At inference, one checkpoint provides a set of reconstruction budgets through a latency-calibrated exit policy. The evaluation framework couples matched-cost interpolation comparisons with finite-update diagnostics and a fixed reverse-time-migration operator, connecting multi-exit optimization to waveform and imaging fidelity. MetaPOCS thus provides a unified formulation for studying the reconstruction--computation trade-off of seismic unfolding across deployment budgets.
Baisong Jiang, Chunxia Zhang, Xiaoli Wei +3
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China. · Business School, Beijing Wuzi University, Beijing, 101149, China. · Geophysical Technology Research and Development Center, BGP, Zhuozhou, Hebei, 072751, China.
Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial and error can explore systematically. Deep-learning methods encode the reconstruction rules in learned weights rather than in an explicit operator that can be inspected and modified. We propose SeisEvo (Seismic Algorithm Evolution), which does not optimize a single reconstruction result but searches for the algorithm that produces it. Starting from a classical reconstruction algorithm, an LLM-driven multi-agent search modifies only the components that the user has opened for editing, without prescribing the mechanism to be discovered. Candidates that violate the physical constraints of the task are rejected outright, and the remaining ones are scored by execution. The output is neither an agent system nor a neural network, but a standalone white-box algorithm that requires no agent or neural network at inference time. For interpolation without added noise, the search discovered a residual-gated, phase-aligned dip-consistency projection; Evo-POCS improves the SNR over classic POCS by 3.49 dB on average across missing ratios from 30% to 70%. For simultaneous interpolation and denoising, it discovered a reliability-grouped singular-value shrinkage; Evo-MSSA improves the average reconstruction SNR by more than 7 dB over classic MSSA and by more than 3 dB over a stronger rank-reduction baseline. Both operators retain their gains on data not used during the search. To the best of our knowledge, this is the first study to formulate the design of a seismic reconstruction operator as a constrained, LLM-driven program evolution task. Agentic algorithm evolution can thus complement deep learning in discovering explicit, inspectable, and deployable seismic processing algorithms.
Yingjie Xu, Siwei Yu, Jianwei Ma
School of Mathematics and Center of Geophysics, Harbin Institute of Technology, Harbin, Heilongjiang, China · Department of Mathematics, National University of Singapore, Singapore · School of Earth and Space Sciences, Peking University, Beijing, China
In marine seismic acquisition, seismic interference (SI) occurs when energy from nearby external seismic source(s) is captured. It typically appears as coherent noise with linear or non-linear movement and varying amplitudes across different sail lines. SI is commonly observed and poses a challenge for seismic data processing. We present a case history of a previously proposed deep neural network (DNN)-based workflow applied for SI attenuation across a marine seismic block in the Camie Field of Angola. This field survey covers over 345 km2 and is marked by the challenge of multiple SI types. The employed DNN-based workflow performs SI attenuation in the common shot domain based on a supervised learning framework: a small subset of the SI-contaminated data was first processed by a conventional geophysical algorithm to obtain an estimate of the SI noise, which was then manually blended with the SI-free common shot gathers from the same survey to generate the training pairs. To ensure signal fidelity, several techniques were applied to improve the DNN's performance. A key highlight of this case history is its scale: this represents a real-world, large-scale processing project and we present a comprehensive comparison of the DNN-based workflow with the conventional geophysical algorithm across the entire survey block, focusing on both processing quality and processing time. The results demonstrate the outstanding performance of the employed DNN-based workflow, which achieved higher SI removal accuracy, with less signal leakage and more complete SI removal. The promising results of this application also open up possibilities for integrating deep learning into other seismic denoising tasks. In addition, we discuss the limitations of this case history, aiming to provide insights for future research and applications in the field.
Jing Sun, Song Hou
Delft University of Technology, Faculty of Electrical Engineering, Mathematics and Computer Science, Van Mourik Broekmanweg 6, Delft 2628 XE, The Netherlands. · VIRIDIEN (UK) Ltd, Crompton Way, Manor Royal Estate, Crawley, West Sussex RH10 9QN, UK.