Controllable Velocity Synthesis Using Generative Diffusion Models
Bibliographic record
Abstract
Summary An accurate seismic velocity model of the Earth is of paramount importance in various geophysical and geological applications, providing insights into the subsurface structures, its natural resource potential, and seismic hazard assessment. By incorporating prior information into such velocity models, we enhance their precision and reliability in inverse problems in which the data coverage is limited. To accomplish this, we propose to use conditional generative diffusion models for velocity synthesis, in which we readily incorporate our priors. Such controllable generation allows us to guide the generation process to meet specific features we want in the generated velocities. Moreover, it can furnish the velocity model with desired features by utilizing target velocity classes, well logs, and structures as training datasets to bolster data-driven geophysical methods. We train several diffusion models separately with a condition given by either class labels, well logs, reflectivity images, or all of them together, and analyze these generated velocities. Tests on the OpenFWI dataset demonstrate that the proposed method can control the velocity generation even with out-of-distribution conditions, providing potential priors to velocity inverse problems as well as the target-specific training datasets for machine learning-based geophysical methods.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".