{"id":"W4313856275","doi":"10.1016/j.geoen.2022.211365","title":"Improving history matching performance in a 3D field-scale case study by combining tracer and production data","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Norges Forskningsråd; Réseau de cancérologie Rossy; Aker BP; Schlumberger Foundation","keywords":"Workflow; Computer science; Data mining; Matching (statistics); TRACER; Benchmark (surveying); Field (mathematics); Reliability (semiconductor); Synthetic data; Production (economics); Data quality; Scale (ratio); Artificial intelligence; Database; Statistics; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001286006,0.0001377754,0.000141161,0.0003423159,0.0001055611,0.00006124173,0.0001745166,0.00004059932,0.000001851719],"category_scores_gemma":[0.0001157545,0.0001476937,0.000006273615,0.0005941749,0.00003008596,0.0008366786,0.0001446842,0.0001940899,7.547274e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009325186,"about_ca_system_score_gemma":0.00002016077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002649688,"about_ca_topic_score_gemma":0.00003870923,"domain_scores_codex":[0.9989148,0.00001072909,0.0001893934,0.0003506057,0.0002035727,0.0003309052],"domain_scores_gemma":[0.9995014,0.00006334364,0.00001503505,0.0003103965,0.00002205785,0.00008775182],"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":[0.000001320414,0.000006534294,0.001282731,0.00008230273,0.000003576898,0.0000417477,0.001576652,0.9698662,0.01234764,0.000002627068,0.00005736711,0.0147313],"study_design_scores_gemma":[0.0001955674,0.00002684183,0.002889472,0.00003050698,0.000004373509,0.0001061471,0.0007589595,0.9946097,0.000453215,0.000001119602,0.0007493873,0.0001747138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935337,0.0004235796,0.005034171,0.00001888955,0.0005200014,0.00009681345,0.00000103182,0.0003262337,0.00004563839],"genre_scores_gemma":[0.9967487,0.000125115,0.00297339,0.000005282465,0.00004482394,0.00001722784,0.000003165115,0.0000214348,0.00006086371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0247435,"threshold_uncertainty_score":0.6022775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02269374034142624,"score_gpt":0.2482001040305697,"score_spread":0.2255063636891435,"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."}}