{"id":"W4360955487","doi":"10.1016/j.geoen.2023.211644","title":"Evaluating reservoir performance using a transformer based proxy model","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Computer Modelling Group","keywords":"Computer science; Transformer; Recurrent neural network; Reservoir simulation; Proxy (statistics); Computation; Artificial neural network; Data mining; Artificial intelligence; Machine learning; Algorithm; Petroleum engineering; Geology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001475487,0.0001980204,0.0001682181,0.0005585107,0.0002231092,0.0001012367,0.0002361159,0.00006521468,0.000004298581],"category_scores_gemma":[0.0001420699,0.0001985894,0.00003435312,0.001830631,0.00006291555,0.0005834089,0.0000283886,0.0001655863,0.000004846953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000955067,"about_ca_system_score_gemma":0.00009519411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006500713,"about_ca_topic_score_gemma":4.807366e-7,"domain_scores_codex":[0.998314,0.000007895455,0.0002306281,0.0002762243,0.0005459916,0.000625272],"domain_scores_gemma":[0.9994156,0.00005685947,0.00001358784,0.0002410331,0.0001023852,0.0001705831],"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":[0.000002006755,0.000001498719,0.00006363576,0.0001054648,0.000003957857,0.000001107192,0.0001028207,0.8902415,0.1076475,0.00006739791,0.000007088389,0.00175598],"study_design_scores_gemma":[0.0002421089,0.00001975825,0.0006431286,0.00006700146,0.00000625852,0.000003550354,0.00001535015,0.9839103,0.01461926,0.00001788859,0.0002072375,0.0002481164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.869341,0.00006727726,0.1292561,0.0000210721,0.0002009115,0.0000864192,0.000001904735,0.0007638088,0.0002615143],"genre_scores_gemma":[0.9404994,0.0000463638,0.05925662,0.00001222903,0.00005249378,0.00002748877,0.000003054022,0.00004164752,0.00006072026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09366884,"threshold_uncertainty_score":0.8098242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07063252789397687,"score_gpt":0.3247334957162951,"score_spread":0.2541009678223182,"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."}}