MétaCan
Menu
Back to cohort
Record W4285163143 · doi:10.3997/2214-4609.202210843

Deep Null Space Regularization for Seismic Inverse Problems

2022· article· en· W4285163143 on OpenAlex
K. Torres Bautista, Mauricio D. Sacchi

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue83rd EAGE Annual Conference & Exhibition · 2022
Typearticle
Languageen
FieldEarth and Planetary Sciences
TopicSeismic Imaging and Inversion Techniques
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsRegularization (linguistics)Inverse problemDeconvolutionSingular value decompositionAlgorithmIterative reconstructionComputer scienceInversion (geology)Synthetic dataMathematical optimizationApplied mathematicsMathematicsArtificial intelligenceMathematical analysis

Abstract

fetched live from OpenAlex

Summary We investigate the use of null space regularizing networks for linear ill-posed seismic inverse problems by combining a classic regularization method with the learned deep decomposition framework. This method extends the popular learned post-processing approach by learning how to improve an initial reconstruction with estimated missing components from the null space of the forward operator while naturally enforcing that the high-resolution prediction is always consistent with the low-resolution input. Unlike traditional model-based reconstruction algorithms, this approach does not make any prior explicit assumption on the solution. Employing a deep decomposition architecture, we consider the inversion of noisy data sets where an additional denoising component on the range of the pseudo-inverse is also trained. To illustrate the approach, we present two numerical examples: a single channel deconvolution and a tomographic (ray-based) inversion. By combining the classical regularization method of truncated singular value decomposition and the deep decomposition approach, we show that it is possible to achieve significant improvements upon the initial reconstruction.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.712
Threshold uncertainty score0.997

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0040.000

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.

Opus teacher head0.028
GPT teacher head0.231
Teacher spread0.203 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it