{"id":"W2983807332","doi":"10.1190/geo2019-0138.1","title":"A theory-guided deep-learning formulation and optimization of seismic waveform inversion","year":2019,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"Penn West Exploration (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inversion (geology); Seismic inversion; Broyden–Fletcher–Goldfarb–Shanno algorithm; Recurrent neural network; Inverse problem; Algorithm; Nonlinear system; Waveform; Artificial neural network; Deep learning; Mathematical optimization; Artificial intelligence; Mathematics; Geology; Seismology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001686967,0.00006820272,0.00009609041,0.00005643265,0.00006471925,0.00001471824,0.00005776421,0.00003265406,0.0002380298],"category_scores_gemma":[0.0000155512,0.00005836614,0.0000267694,0.000117612,0.00002568134,0.0002859654,0.00001164436,0.00007553979,0.00005149646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003612248,"about_ca_system_score_gemma":0.0000105022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006440244,"about_ca_topic_score_gemma":0.000001222043,"domain_scores_codex":[0.9995093,0.00003529137,0.0001121568,0.0001181252,0.0001182573,0.0001068588],"domain_scores_gemma":[0.9996959,0.00005516863,0.00009031229,0.00008886752,0.00004095011,0.00002881878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007541056,0.00001561894,0.1297906,0.0001074883,0.00002107297,7.655746e-7,0.001382419,0.3885682,0.0003877825,0.001328235,0.0003645496,0.4779578],"study_design_scores_gemma":[0.0001836209,0.000079909,0.008024626,0.00002113861,0.000008653576,0.000001846007,0.0002196426,0.9835541,0.001334726,0.005780042,0.0007104885,0.00008120204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9674248,0.00005545302,0.02612403,0.00005703601,0.0000994276,0.0001307011,0.000003530619,0.00007031322,0.006034675],"genre_scores_gemma":[0.9954996,0.0000570505,0.00370458,0.0002902638,0.00001938506,1.986574e-7,0.00009400852,0.00000284739,0.0003320267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5949859,"threshold_uncertainty_score":0.2606259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007396725858046595,"score_gpt":0.1944332774883335,"score_spread":0.1870365516302869,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}