Accurate reconstruction method of virtual shot records in passive source time-lapse monitoring based on SBA network
Bibliographic record
Abstract
ABSTRACT Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry (SI). It has become a low-cost, environmentally friendly alternative to active source seismic, showing great potential. However, this method faces many challenges in practical applications, including uneven distribution of underground sources and complex survey environments. These situations seriously affect the reconstruction quality of virtual shot records, resulting in unguaranteed imaging results and greatly limiting passive source seismic exploration applications. In addition, the quality of the reconstructed records is directly related to the time length of the noise records, but in practice it is often difficult to obtain long-term, high-quality noise segments containing body wave events. To solve the above problems, we propose a deep learning method for reconstructing passive source virtual shot records and apply it to passive source time-lapse monitoring. This method combines the UNet network and the BiLSTM (Bidirectional Long Short-Term Memory) network for extracting spatial features and temporal features respectively. It introduces the spatial attention mechanism to establish a hybrid SUNet-BiLSTM-Attention (SBA) network for supervised training. Through pre-training and fine-tuning training, the network can accurately reconstruct passive source virtual shot records directly from short-time noisy segments containing body wave events. The experimental results of theoretical data show that the virtual shot records reconstructed by the network have high resolution and signal to noise ratio (SNR), providing high-quality data for subsequent monitoring and imaging. Finally, to further validate the effectiveness of proposed method, we applied it to field data collected from gas storage in northwest China. The reconstruction results of field data effectively improve the quality of virtual records and obtain more reliable time-lapse imaging monitoring results, which have significant practical value.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".