{"id":"W2974195150","doi":"10.2118/196190-ms","title":"Waterflooding Optimization under Geological Uncertainties by Using Deep Reinforcement Learning Algorithms","year":2019,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Particle swarm optimization; Reinforcement learning; Artificial neural network; Reservoir simulation; Computer science; Mathematical optimization; Set (abstract data type); Water cut; Algorithm; Artificial intelligence; Mathematics; Petroleum engineering; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002052283,0.0001518227,0.0001782773,0.00007183687,0.00007330145,0.00007083633,0.00006540654,0.0001671021,0.0002049771],"category_scores_gemma":[0.00002723244,0.0001386699,0.00003407024,0.0001139218,0.00003710407,0.0002870628,0.00004371474,0.0002514753,0.00001101355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005363551,"about_ca_system_score_gemma":0.00000677442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001545103,"about_ca_topic_score_gemma":6.788111e-7,"domain_scores_codex":[0.9991484,0.00003629175,0.0002284927,0.0001940974,0.0001578936,0.0002348248],"domain_scores_gemma":[0.999683,0.00004732032,0.00002736057,0.0001031071,0.00007144635,0.00006777617],"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":[0.000006971288,0.000004560428,0.0001458952,0.00002918765,0.000007444014,6.420869e-7,0.00006491131,0.9893409,0.008978853,0.000514422,0.00003939536,0.0008668347],"study_design_scores_gemma":[0.0002756279,0.00009183134,0.00007914469,0.00004796934,0.000009327467,0.000005546381,0.0002596862,0.9960601,0.002327272,0.0003923766,0.0002525311,0.0001986074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2629511,0.00008217673,0.7355649,0.00003955509,0.00006864175,0.0001120172,0.000001564273,0.0002821678,0.0008978601],"genre_scores_gemma":[0.982234,0.0002094475,0.01723679,0.00002243488,0.00003957319,0.00000677905,0.00007512076,0.00001717306,0.000158664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7192829,"threshold_uncertainty_score":0.5654796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02553818368314833,"score_gpt":0.2701560822010741,"score_spread":0.2446178985179258,"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."}}