{"id":"W3034960737","doi":"10.1016/j.psep.2020.05.046","title":"A new methodology for kick detection during petroleum drilling using long short-term memory recurrent neural network","year":2020,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canada Research Chairs","keywords":"ALARM; False alarm; Recurrent neural network; Computer science; Artificial neural network; Constant false alarm rate; Term (time); Long short term memory; Artificial intelligence; Time series; Data mining; Exponent; Power (physics); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003953984,0.0008532498,0.0007433447,0.0008959259,0.0003419886,0.0005174172,0.001254876,0.000846054,0.001284304],"category_scores_gemma":[0.0006560364,0.0003523016,0.0005655689,0.0005718504,0.0002277539,0.0008563281,0.0006418732,0.0007104564,0.0006359648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003037349,"about_ca_system_score_gemma":0.0006525379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004827664,"about_ca_topic_score_gemma":0.007085554,"domain_scores_codex":[0.9996901,0.00003270411,0.00002275533,0.0001051841,0.0001044776,0.00004474728],"domain_scores_gemma":[0.9996698,0.00005515437,0.00004460893,0.00003044424,0.0001786571,0.00002143595],"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":[0.0002686712,0.0001962022,0.004087962,0.0002273814,0.0001925788,0.000244149,0.00009337784,0.08295457,0.1032032,0.002274679,0.003051869,0.8032053],"study_design_scores_gemma":[0.000009133814,0.00007850233,0.00141785,0.00001081511,0.00004691354,0.0000956403,0.00001456133,0.981989,0.01447397,0.0005989696,0.001244437,0.0000201793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01958091,0.0005396348,0.9774663,0.00007434362,0.0001366261,0.00004585147,0.00008668198,0.001090769,0.0009787888],"genre_scores_gemma":[0.5937251,0.000668161,0.3966182,0.0001723028,0.0001542517,0.0001455167,0.000498267,0.0001206507,0.007897708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004827664,"threshold_uncertainty_score":0.009599149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03243590100714277,"score_gpt":0.226611397274067,"score_spread":0.1941754962669242,"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."}}