{"id":"W2916737519","doi":"10.2118/194105-ms","title":"Prediction of Penetration Rate Ahead of the Bit through Real-Time Updated Machine Learning Models","year":2019,"lang":"en","type":"article","venue":"SPE/IADC International Drilling Conference and Exhibition","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Haliburton Forest & Wild Life Reserve","funders":"University of Southern California","keywords":"Drilling; Rate of penetration; Computer science; Artificial neural network; Idle; Process (computing); Maximization; Real-time computing; Simulation; Artificial intelligence; Engineering; Mechanical engineering; Mathematical optimization; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008857311,0.0008947256,0.0006448657,0.0008089145,0.0002435097,0.00092446,0.0007116595,0.001152848,0.001401718],"category_scores_gemma":[0.002694207,0.0003463992,0.0004823603,0.0005736962,0.0002932825,0.0008342544,0.00039032,0.001189256,0.0003090956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006598847,"about_ca_system_score_gemma":0.0006450358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01475331,"about_ca_topic_score_gemma":0.006857465,"domain_scores_codex":[0.9997303,0.00005805704,0.00002403644,0.00007375612,0.00006209645,0.00005173075],"domain_scores_gemma":[0.9986818,0.0007603241,0.0001586718,0.00005181957,0.0003020043,0.00004527898],"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":[0.00006694462,0.00007554335,0.002752919,0.0000233941,0.00002031402,0.00004061167,0.000008802503,0.9794282,0.00048653,0.0002282528,0.0003867294,0.01648177],"study_design_scores_gemma":[6.987815e-7,0.000005775965,0.0001402406,0.000001185873,0.000001170976,0.000001106656,9.605836e-7,0.9997031,0.00007676979,0.00005064407,0.00001712946,0.000001147814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6503098,0.00132282,0.3403591,0.000844963,0.0003657254,0.00008777753,0.0006835713,0.001068931,0.004957301],"genre_scores_gemma":[0.9917845,0.0001293305,0.006757504,0.0000337206,0.00001886999,0.00002976928,0.0002263467,0.000008566948,0.001011449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01475331,"threshold_uncertainty_score":0.0293349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01946503261162046,"score_gpt":0.2037019117441636,"score_spread":0.1842368791325431,"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."}}