{"id":"W3011523529","doi":"10.1190/geo2019-0282.1","title":"Missing well log prediction using convolutional long short-term memory network","year":2020,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Geology; Continental shelf; Well logging; Interval (graph theory); Field (mathematics); Submarine pipeline; Convolutional neural network; Monte Carlo method; Data set; Data mining; Computer science; Statistics; Artificial intelligence; Geophysics; Geotechnical engineering; Oceanography; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004614488,0.0009437469,0.0004402484,0.000650814,0.0002497635,0.0004803629,0.001097843,0.0007378788,0.001480053],"category_scores_gemma":[0.001013139,0.0003507367,0.0004659758,0.0005732898,0.0002796132,0.0009159367,0.000479651,0.0008878633,0.0005708179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007367974,"about_ca_system_score_gemma":0.0009870981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02536289,"about_ca_topic_score_gemma":0.03221768,"domain_scores_codex":[0.9998345,0.00001812047,0.000009395831,0.00005289711,0.00003699588,0.00004810232],"domain_scores_gemma":[0.9996046,0.0001287993,0.0000481353,0.00004016696,0.0001521688,0.00002611765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004000343,0.0002544305,0.01081842,0.00005641934,0.0001170636,0.0002386232,0.00004819432,0.7254192,0.009749955,0.0009075555,0.006116694,0.2458735],"study_design_scores_gemma":[0.000002530493,0.00001047504,0.0003640545,0.000002298856,0.000004768786,0.000004892515,0.000003533996,0.9981441,0.001130272,0.0002424388,0.000087883,0.000002706034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4647965,0.00111296,0.5191422,0.0008090971,0.0002473476,0.00006447083,0.001803221,0.008010406,0.004013843],"genre_scores_gemma":[0.96591,0.0001187412,0.02960296,0.0001171795,0.0000244554,0.00003113124,0.001368768,0.00004782111,0.002778958],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02536289,"threshold_uncertainty_score":0.05043054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02844117712710026,"score_gpt":0.217970512758864,"score_spread":0.1895293356317638,"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."}}