Joint Deblending and Multi-Source Wavefield Reconstruction via Regularization by Denoising (RED)
Bibliographic record
Abstract
Summary Seismic acquisition demands higher-quality data with extended bandwidth, which is essential for applications like Full Waveform Inversion (FWI). At the same time, cost reduction and minimizing environmental impact are critical priorities. Surveys employing diverse source types, often named Dispersed Source Arrays (DSA) or their variants, have been proposed as viable solutions. However, merging the outputs of different sources into a single broadband volume typically relies on traditional processing sequences and customized merging procedures, complicating workflows and adding unnecessary burdens during processing. This paper extends Non-uniform DSA to blended acquisition introduces an inversion technique for joint deblending and bandwidth reconstruction. By leveraging compressive sensing principles, the proposed method uses a frequency sampling operator to encode the spectral and spatial characteristics of different source types. This enables non-uniform subsampling across various frequency bands. A modified multi-source wavefield reconstruction technique integrates Regularization by Denoising (RED) to utilize denoising engines and regularize the inverse problem. Combining RED with first-order optimization methods, like the Inexact Alternating Direction Method of Multipliers (InADMM) provides an efficient inversion-based alternative to solve for joint deblending and bandwidth reconstruction of blended NU-DSA data, eliminating additional processing stages.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".