Ground-truth-calibrated onshore and offshore subsurface infrastructure image from deep-learning-based 3D inversion of magnetic data
Bibliographic record
Abstract
Abstract In this study, we demonstrate the application of deep-learning-based 3D inversion of magnetic data to image subsurface infrastructure. We highlight results from two case studies: an onshore survey at Texas A&M University's Rellis Campus site and an offshore survey in the northern Gulf of Mexico (GOM), off the coast of Louisiana. The onshore case utilized drone-acquired magnetic data to map buried utilities before construction. The offshore case employed a boat-towed magnetometer approximately 3.5 m above the seafloor to locate oil well conductors disrupted by Hurricane Ivan in 2004 and presently buried under 35 to 45 m of sediment. The inversion results at the Rellis site were validated against excavation data, revealing strong agreement in target location and depth (within 17 cm). In the GOM survey, the artificial intelligence (AI)-driven inversion successfully extended conductor imaging beyond the limits of acoustic methods, providing critical information on conductor geometry near the well conductor bay. This work highlights the effectiveness of AI-driven inversion techniques in enhancing subsurface imaging, offering cost-effective and scalable solutions for applications in utility mapping, environmental monitoring, and hazard assessment. The results demonstrate that AI-based workflows can be adapted to various geophysical settings, providing new opportunities for high-resolution imaging of complex subsurface features in onshore and offshore environments.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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".