{"id":"W2936571051","doi":"10.1016/j.petlm.2019.04.001","title":"Predicting the performance of steam assisted gravity drainage (SAGD) method utilizing artificial neural network (ANN)","year":2019,"lang":"en","type":"article","venue":"Petroleum","topic":"Enhanced Oil Recovery Techniques","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Mitacs; Petroleum Technology Research Centre; University of Regina","keywords":"Artificial neural network; Petroleum engineering; Steam-assisted gravity drainage; Oil viscosity; Steam injection; API gravity; Enhanced oil recovery; Permeability (electromagnetism); Recovery rate; Engineering; Drainage; Gravity separation; Oil sands; Computer science; Viscosity; Crude oil; Artificial intelligence; Environmental engineering; Materials science; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008140458,0.0002082166,0.0003244404,0.00006614262,0.00009884684,0.00003480716,0.0003270492,0.0001067221,0.00003562654],"category_scores_gemma":[0.00004382111,0.0001737097,0.0001261502,0.0002699581,0.00003944126,0.000229759,0.0000871004,0.0004619798,0.00001785917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007545188,"about_ca_system_score_gemma":0.00001532506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002457651,"about_ca_topic_score_gemma":0.00002740309,"domain_scores_codex":[0.9985609,0.0001085315,0.0003953804,0.0002218624,0.0002687072,0.0004446214],"domain_scores_gemma":[0.9990571,0.0002745215,0.0001238506,0.0004556023,0.00004357421,0.00004534406],"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":[0.0001070029,0.00005159159,0.05608685,0.0005562608,0.000149801,0.000004550713,0.0004682794,0.7314205,0.1114704,0.001026429,0.0004515542,0.09820676],"study_design_scores_gemma":[0.0001455351,0.0001509026,0.03785364,0.0001391487,0.00003580276,0.00001103223,0.0001402182,0.9114635,0.04867349,0.0003428223,0.0007974409,0.0002464978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784791,0.0002721575,0.005852109,0.00002712035,0.0007611245,0.0001904648,0.000008874245,0.0005972122,0.01381177],"genre_scores_gemma":[0.9943976,0.00002467219,0.005037203,0.00002997969,0.0002154087,0.00003036286,0.000006426593,0.00005109439,0.0002072479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.180043,"threshold_uncertainty_score":0.7083678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01179209100986524,"score_gpt":0.245353260389906,"score_spread":0.2335611693800407,"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."}}