{"id":"W4220748003","doi":"10.2118/208962-ms","title":"A Machine Learning Approach to Real-Time Uncertainty Assessment of SAGD Forecasts and the Optimization of Steam Allocation","year":2022,"lang":"en","type":"article","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cenovus Energy (Canada); University of Alberta","funders":"","keywords":"Computer science; Reservoir simulation; Monte Carlo method; Uncertainty quantification; Field (mathematics); Data mining; Workflow; Bayesian probability; Machine learning; Artificial intelligence; Mathematical optimization; Engineering; Petroleum engineering; Statistics","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":[0.002226635,0.0006066429,0.0009385041,0.001156081,0.0004279883,0.001002082,0.001018829,0.001049411,0.001495598],"category_scores_gemma":[0.005619932,0.0004571011,0.0005471459,0.0008302444,0.0006238887,0.0008554119,0.0007419201,0.001212999,0.0001825637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001320097,"about_ca_system_score_gemma":0.001195012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01270567,"about_ca_topic_score_gemma":0.008141087,"domain_scores_codex":[0.9994185,0.0002571107,0.00003618018,0.0001072948,0.0001194667,0.00006145328],"domain_scores_gemma":[0.9969193,0.002136208,0.0002644629,0.0000956711,0.0004992026,0.00008518453],"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":[0.00001195407,0.00001720952,0.0003203353,0.000007662884,0.00001188189,0.00001206086,0.000008728725,0.9865391,0.0001289945,0.001516498,0.0001159121,0.0113097],"study_design_scores_gemma":[4.138046e-7,0.000002073948,0.00002406652,6.986214e-7,5.03117e-7,5.855533e-7,7.356926e-7,0.9995027,0.0000304079,0.0004186775,0.00001859837,6.261793e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04673956,0.0001795472,0.9502608,0.0003739348,0.00002794973,0.00005102406,0.00008327253,0.0003794212,0.001904504],"genre_scores_gemma":[0.8799832,0.0001324669,0.1178359,0.0000795414,0.00006680839,0.0001218789,0.0001394468,0.0000427738,0.00159784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01270567,"threshold_uncertainty_score":0.02526343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01388264948298953,"score_gpt":0.2620165204110455,"score_spread":0.248133870928056,"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."}}