{"id":"W2937448533","doi":"10.1016/j.petrol.2019.04.016","title":"Applicability of deep neural networks on production forecasting in Bakken shale reservoirs","year":2019,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":126,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Alberta Innovates - Technology Futures","keywords":"Oil shale; Artificial neural network; Tight oil; Petroleum engineering; Geology; Deep learning; Hydraulic fracturing; Reservoir modeling; Normalization (sociology); Computer science; Artificial intelligence","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":[0.001192594,0.0001019711,0.0002432321,0.000418718,0.00002989253,0.00002855585,0.0002067377,0.00004228984,0.000004969895],"category_scores_gemma":[0.0001800557,0.00008355387,0.00005570191,0.0005766787,0.00004725416,0.0003361276,0.0000303073,0.0003354009,5.099459e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001029345,"about_ca_system_score_gemma":0.00001258155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006767135,"about_ca_topic_score_gemma":0.000005627418,"domain_scores_codex":[0.9988881,0.00000856234,0.0003512612,0.0001369019,0.0003649149,0.0002502165],"domain_scores_gemma":[0.9995379,0.00005587286,0.00007700513,0.0001563843,0.00008441443,0.00008844301],"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":[0.00000958329,0.00001051497,0.006333706,0.00007368747,0.000008464708,0.000003226649,0.0001135065,0.9842746,0.006920139,0.000002845135,0.000003837608,0.002245913],"study_design_scores_gemma":[0.0001481144,0.00007077395,0.01585836,0.00007656672,0.0000068966,0.00002622978,0.0001181175,0.9818229,0.001751181,0.000006049578,0.00003530628,0.00007946586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949922,0.0002129232,0.00406561,0.00006574557,0.0003275114,0.00004079904,1.865578e-7,0.00001574657,0.0002792987],"genre_scores_gemma":[0.9994622,0.00003067768,0.0003655439,0.000003765725,0.0001200155,0.000001356681,1.359115e-7,0.000009872591,0.000006452178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009524656,"threshold_uncertainty_score":0.3407228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007168811232038851,"score_gpt":0.1973393952243767,"score_spread":0.1901705839923378,"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."}}