Multi-geophysical information neural network for seismic tomography
Bibliographic record
Abstract
ABSTRACT Velocity is a key parameter in geophysics, particularly in near-surface studies, wherein subsurface structures are shaped by complex geologic processes. Accurate modeling of such structures is critical for imaging deeper formations and improving subsurface interpretations. Modern data acquisition techniques, such as digital geologic outcrops and micrologging, provide valuable structural information that enhances the accuracy of near-surface velocity models. Traveltime tomography has long been a widely used approach for near-surface velocity modeling. However, its application is often constrained by challenges surrounding the management of complex grid configurations and the nonlinear nature of inversion, particularly when integrating data sets of varying types, scales, and resolutions. Physics-informed neural networks have recently emerged as a promising solution to these challenges. Nevertheless, the inherent underdetermination in inversion means that these methods continue to suffer from issues with nonuniqueness and limited resolution, rendering them insufficient for near-surface modeling. To address these challenges, a novel method, the multi-geophysical information neural network for seismic tomography (MINN-tomo), is developed. This approach directly incorporates diverse data sets into the loss function, providing a unified framework for handling data fusion across different scales during nonlinear inversion. Considering data acquisition for the near-surface, geologic outcrops and micrologging are incorporated to ensure spatial continuity and improve the velocity resolution, thereby enhancing the accuracy of the near-surface velocity model. The flexibility and efficiency of MINN-tomo are verified using four representative synthetic models: one featuring significant near-surface characteristics, one based on the rugged seabed topography of the South China Sea, one derived from the near-surface segment of the Foothill model, and the standard Marmousi model. Additionally, the impact of key parameters within the developed framework is evaluated, highlighting its robustness and adaptability.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".