Probabilistic inversion of seafloor compliance for oceanic crustal shear velocity structure using mixture density neural networks
Bibliographic record
Abstract
SUMMARY Measurements of various physical properties of oceanic sediment and crustal structures provide insight into a number of geological and geophysical processes. In particular, knowledge of the shear wave velocity (VS) structure of marine sediments and oceanic crust has wide ranging implications from geotechnical engineering projects to seismic mantle tomography studies. In this study, we propose a novel approach to nonlinearly invert compliance signals recorded by colocated ocean-bottom seismometers and high-sample-rate pressure gauges for shallow oceanic shear wave velocity structure. The inversion method is based on a type of machine learning neural network known as a mixture density neural network (MDN). We demonstrate the effectiveness of the MDN method on synthetic models with a fixed deployment depth of 2015 m and show that among 30 000 test models, the inverted shear wave velocity profiles achieve an average error of 0.025 km s−1. We then apply the method to observed data recorded by a broad-band ocean-bottom station in the Lau basin, for which a VS profile was estimated using Monte Carlo sampling methods. Using the mixture density network approach, we validate the method by showing that our VS profile is in excellent agreement with the previous result. Finally, we argue that the mixture density network approach to compliance inversion is advantageous over other compliance inversion methods because it is faster and allows for standardized measurements.
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 | 0.003 |
| 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".