{"id":"W4200611051","doi":"10.1016/j.petrol.2021.109937","title":"Data-driven deep-learning forecasting for oil production and pressure","year":2021,"lang":"en","type":"article","venue":"Journal of Petroleum Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":72,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Agência Nacional do Petróleo, Gás Natural e Biocombustíveis; Computer Modelling Group; Shell Brasil; Schlumberger Foundation","keywords":"Computer science; Deep learning; Artificial intelligence; Production (economics); Oil production; Sliding window protocol; Stacking; Machine learning; Field (mathematics); Data mining; Petroleum engineering; Window (computing); Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006187179,0.0006568456,0.0007937953,0.0004834021,0.0002753849,0.0005864059,0.0009392679,0.001058683,0.001697245],"category_scores_gemma":[0.002827157,0.0005620905,0.0004795833,0.0006997121,0.0003354221,0.001146479,0.0006151426,0.001797479,0.0003735046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009280965,"about_ca_system_score_gemma":0.001208653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.023101,"about_ca_topic_score_gemma":0.02150608,"domain_scores_codex":[0.9998834,0.00002134023,0.000008632723,0.00003556849,0.00002381553,0.00002718367],"domain_scores_gemma":[0.9989256,0.0006606361,0.00006547315,0.0000714431,0.0002225275,0.00005419391],"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":[0.00007153454,0.00006402489,0.001520803,0.00002412005,0.00002482809,0.00002361647,0.0000106477,0.9684701,0.0006125736,0.001218758,0.001287648,0.02667126],"study_design_scores_gemma":[8.781148e-7,0.000001327973,0.00004507574,4.651089e-7,6.078389e-7,5.140114e-7,4.650584e-7,0.9995725,0.00007846346,0.0002797644,0.00001937872,5.721925e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4447913,0.001517507,0.5439137,0.001624711,0.000449492,0.00004402739,0.001957642,0.002408369,0.003293328],"genre_scores_gemma":[0.9741216,0.0001900776,0.02280824,0.00007453166,0.0000529659,0.00002824191,0.0008797256,0.00004670784,0.001797932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.023101,"threshold_uncertainty_score":0.04593307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03265832660809116,"score_gpt":0.2693699349733069,"score_spread":0.2367116083652157,"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."}}