Deep-LSRTM: least-squares reverse time migration via learned projection operators
Bibliographic record
Abstract
Summary Recently, deep neural network applications have emerged as powerful alternatives to standard seismic inversion and imaging techniques. In this work, we solve the least-squares migration problem by adopting an iterative deep-neural network framework. This method substitutes the projection operator of classical gradient projection methods with convolutional neural networks to predict reflectivity model updates. It also incorporates the forward and adjoint wave operators into the learning process, evolving in response to the least-squares gradient. After training with 1000 randomly generated samples, our networks learn the updating parameters such as the step length and the effect of regularization directly from the training data to estimate accurate reflectivity distributions. To demonstrate the effectiveness of the proposed framework, we consider two synthetic cases: a folded and faulted model and the Marmousi model. Unlike well-established standard LSRTM schemes that require many iterations to improve subsurface imaging, our learned approach produces high-quality results only in a few iterations. This work is a step forward in merging deep learning techniques with seismic imaging problems for effective inversion of reflectivity models similar to those computable via least-squares migration.
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 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".