{"id":"W2986812080","doi":"10.1190/geo2018-0786.1","title":"Seismic velocity estimation: A deep recurrent neural-network approach","year":2019,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Deep learning; Convolutional neural network; Mean squared error; Computer science; Interval (graph theory); Midpoint; Artificial intelligence; Seismic velocity; Data set; Recurrent neural network; Pattern recognition (psychology); Algorithm; Geology; Seismology; Mathematics; Geometry; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001458759,0.0001261981,0.000147385,0.00002697611,0.0001174475,0.00005128053,0.000200266,0.00004699593,0.0003742497],"category_scores_gemma":[0.000007062774,0.0001102255,0.00006352612,0.0002424833,0.00004287019,0.0002198827,0.00001700037,0.0001789164,0.001234769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005699867,"about_ca_system_score_gemma":0.00002400801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00057709,"about_ca_topic_score_gemma":0.000001695777,"domain_scores_codex":[0.9990869,0.00004666219,0.0001340506,0.0002474989,0.0002054526,0.000279409],"domain_scores_gemma":[0.9995392,0.00004762735,0.00007000563,0.0002468878,0.00003024214,0.0000660315],"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":[0.0000198299,0.00002943761,0.03698134,0.00005015525,0.00001518377,0.000001553895,0.0002324615,0.1915727,0.000001966078,0.000182773,0.02316533,0.7477473],"study_design_scores_gemma":[0.0001029679,0.00005584135,0.02621036,0.00001123132,0.000007688981,0.000005429722,0.00003554861,0.960866,0.00002487465,0.004360453,0.008167509,0.0001520593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9428405,0.0003563121,0.02224813,0.0004744802,0.0012991,0.0004026986,0.00002180522,0.0004317515,0.03192522],"genre_scores_gemma":[0.9854822,0.00001941326,0.01209412,0.001604332,0.0001971242,0.000001554387,0.0002018093,0.000004314577,0.0003951817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7692934,"threshold_uncertainty_score":0.9995429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126925514394411,"score_gpt":0.2031054588135575,"score_spread":0.1918362036696134,"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."}}