{"id":"W3016919356","doi":"10.1016/j.petrol.2020.107291","title":"Log data-driven model and feature ranking for water saturation prediction using machine learning approach","year":2020,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Support vector machine; Artificial neural network; Machine learning; Artificial intelligence; Least squares support vector machine; Reservoir modeling; Ranking SVM; Computer science; Simulated annealing; Data mining; Engineering; Petroleum 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":[0.0008745315,0.0007270915,0.001467181,0.0008026988,0.0003989177,0.0008772648,0.001204991,0.0008948458,0.001540483],"category_scores_gemma":[0.001954761,0.000442008,0.000907864,0.0008004939,0.0002561727,0.0009638292,0.0005942474,0.00117548,0.0005575311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005829103,"about_ca_system_score_gemma":0.001237982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01352712,"about_ca_topic_score_gemma":0.01020783,"domain_scores_codex":[0.999698,0.00007650255,0.00002492496,0.00008285257,0.00006684174,0.00005080975],"domain_scores_gemma":[0.9990865,0.0005213703,0.00005656856,0.00006880798,0.0002378035,0.00002892329],"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":[0.0002046282,0.0002336043,0.002021733,0.00007934726,0.000097736,0.00008483502,0.00002842691,0.8581557,0.00293107,0.001276867,0.002200884,0.1326853],"study_design_scores_gemma":[0.000001352777,0.000006608424,0.00007494809,5.984701e-7,0.000002385025,0.000002239093,9.550619e-7,0.9995202,0.0001654799,0.0001911975,0.0000322747,0.000001766801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07499966,0.0005798455,0.920045,0.0002677477,0.0001083042,0.00006252579,0.0004269814,0.002454716,0.001055205],"genre_scores_gemma":[0.9416001,0.0001755368,0.05443781,0.0001067062,0.0000726256,0.000142934,0.0008138772,0.0000819828,0.002568461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01352712,"threshold_uncertainty_score":0.02689677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04162849255083427,"score_gpt":0.2617986372963934,"score_spread":0.2201701447455591,"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."}}