High-efficient reflection retrieval from massive ambient noise using a deep-learning workflow
Bibliographic record
Abstract
Due to its low acquisition cost, background noise reflection wave imaging based on seismic interferometry (SI) shows excellent potential in exploration and reservoir monitoring. Unfortunately, body wave reflections are often overwhelmed by surface waves and other signals, making applying body-wave subsurface imaging robustly a hard to solve problem. Screening segments containing body wave events becomes the most crucial preprocessing goal to retrieve reflection events. In addition, long-term acquisition provides massive amounts of noisy data, requiring robust and efficient processing methods. To solve this problem, we propose a deep-learning workflow for quickly retrieving body wave events from massive ambient noise datasets. We feed relevant data to a convolutional autoencoder classifier (CAC) and directly determine whether the segment contains body wave events after training. The initial dataset is produced by processing field via the 3D illumination diagnosis method. Then, we continuously update the size and quality of the dataset through the prediction results of the initial data training. Besides, frequency-domain data are also feed to the network to increase the diversity of the training volume. These steps encourage CAC to learn characteristics from the dataset better. Prediction results on field data show that the deep learning workflow successfully retrieves body wave reflections with high accuracy and efficiency.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".