{"id":"W3017785036","doi":"10.1016/j.petrol.2020.107324","title":"Supervised data-driven approach to early kick detection during drilling operation","year":2020,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Drilling; Margin (machine learning); Artificial neural network; Constant false alarm rate; ALARM; Binary classification; Reliability (semiconductor); Submarine pipeline; Engineering; False alarm; Petroleum engineering; Simulation; Computer science; Artificial intelligence; Support vector machine; Machine learning; Power (physics); Geotechnical engineering; Mechanical engineering","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":[0.000451703,0.0001663995,0.0002303291,0.0003248232,0.000111266,0.0002190856,0.0004535479,0.00004488826,0.000001448196],"category_scores_gemma":[0.000130954,0.0001620937,0.00003425332,0.0005533975,0.00002296597,0.001153985,0.00009071222,0.0002978533,0.00000493037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009132951,"about_ca_system_score_gemma":0.00002953699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003180875,"about_ca_topic_score_gemma":3.916172e-7,"domain_scores_codex":[0.9986613,0.000005000604,0.0003432918,0.0002233474,0.0004428571,0.000324173],"domain_scores_gemma":[0.9992924,0.0000167018,0.00003569692,0.0001795483,0.00009497703,0.000380652],"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":[0.000004280827,0.000002936943,0.0000717363,0.00006138398,0.00001086008,0.000003351552,0.0004334298,0.7195272,0.2791672,0.000006915539,0.000006956618,0.0007038203],"study_design_scores_gemma":[0.0002477115,0.00006267149,0.002186425,0.00005137945,0.00001559334,0.00005287083,0.0001006244,0.9815066,0.01522347,5.249968e-7,0.0003684876,0.0001835702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7069969,0.0001474133,0.2922121,0.00004845935,0.0003317242,0.00004077004,0.00000198722,0.0001078135,0.0001127888],"genre_scores_gemma":[0.9897177,0.00006946876,0.009678074,0.00002111081,0.0004774664,0.000001732459,8.815875e-7,0.00003095485,0.000002565955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2827208,"threshold_uncertainty_score":0.6609989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685907976442619,"score_gpt":0.1950424954623171,"score_spread":0.1781834156978909,"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."}}