MétaCan
Menu
Back to cohort
Record W2967127111 · doi:10.1190/segam2019-3215762.1

A theory-guided deep learning formulation of seismic waveform inversion

2019· article· en· W2967127111 on OpenAlexaff
Jian Sun, Zhan Niu, K. A. Innanen, Junxiao Li, Daniel Trad

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEarth and Planetary Sciences
TopicSeismic Imaging and Inversion Techniques
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsInversion (geology)WaveformComputer scienceSeismic inversionGeologyArtificial intelligenceSeismologyPhysicsTelecommunicationsMeteorology

Abstract

fetched live from OpenAlex

Deep learning techniques appear to be poised to play very important roles in our processing flows for inversion and interpretation of seismic data. The most successful seismic applications of these complex pattern-identifying networks will, presumably, be those that also leverage the deterministic physical models on which we normally base our seismic methods. Motivated by the advantages of recurrent neural networks (RNN) for modelling dynamic processes, a theory-guided RNN is set up to address the forward and inverse problems. Starting from the mathematical form of the RNN, we deduce that, under certain assumptions, the RNN training process can be equivalent at leading order to gradient-based seismic full waveform inversion (FWI). Our numerical analysis shows the Adaptive Moment (or Adam) optimization with learning rate set to match the magnitudes of standard FWI updates appears to produce the most stable and well-behaved waveform inversion results, which is re-confirmed by a multidimensional 2D Marmousi experiment. Presentation Date: Tuesday, September 17, 2019 Session Start Time: 1:50 PM Presentation Time: 3:55 PM Location: 221D Presentation Type: Oral

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.015

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.011
GPT teacher head0.211
Teacher spread0.200 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations14
Published2019
Admission routes1
Has abstractyes

Explore more

Same topicSeismic Imaging and Inversion TechniquesFrench-language works237,207