Multi-Task Seismic Processing Using Generative Diffusion Models
Bibliographic record
Abstract
Summary Seismic data processing aim to address data challenges like noise contamination, incomplete acquisition, and limited low-frequency information, so we obtain accurate subsurface imaging and interpretation. However, most implementations, whether conventional or machine leaning (ML) based, do not utilize the distribution of features embedded in the data to address these challenges. Thus, we propose a generative seismic foundation model (GSFM), a unified framework based on generative diffusion models, designed to store the expected distribution of recorded seismic data for multiple seismic processing tasks (SPTs), including denoising, backscattered noise attenuation, interpolation, and low-frequency extrapolation. Unlike traditional neural network-based approaches, GSFM employs a dual-channel input structure with task-specific encoding labels, enabling it to distinguish and adapt to different tasks efficiently. The model undergoes supervised pre-training on synthetic data to capture an ideal seismic data distribution, followed by an iterative self-supervised fine-tuning strategy on field data to bridge the gap between synthetic and real data distributions. Our experiments on marine field data, where we use backscattered noise attenuation task as a example, demonstrate that GSFM outperforms both traditional NN-based methods and conventional pre-training strategies.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".