{"id":"W2072169628","doi":"10.2118/162783-ms","title":"Integration of Production Data for Estimation of Natural Fracture Properties in Tight Gas Reservoirs Using Ensemble Kalman Filter","year":2012,"lang":"en","type":"article","venue":"SPE Canadian Unconventional Resources Conference","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Ensemble Kalman filter; Monte Carlo method; Kalman filter; Data assimilation; Principal component analysis; Reservoir simulation; Computer science; Permeability (electromagnetism); Channelized; Uncertainty quantification; Well logging; Hydrogeology; Geology; Algorithm; Petroleum engineering; Statistics; Mathematics; Extended Kalman filter; Geotechnical engineering; Artificial intelligence; Machine learning; Meteorology","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":[0.000435109,0.0001137618,0.0001673468,0.0002923922,0.00003429329,0.00001807421,0.000196639,0.00007963966,0.00004619511],"category_scores_gemma":[0.000562505,0.0001078843,0.0000360268,0.0001862614,0.00004036724,0.0004292434,0.00001696168,0.0001302052,9.330215e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119102,"about_ca_system_score_gemma":0.0001000929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003286811,"about_ca_topic_score_gemma":0.008079015,"domain_scores_codex":[0.9991144,0.00004396346,0.0003148915,0.0001414094,0.000172229,0.0002130873],"domain_scores_gemma":[0.9993294,0.00007281595,0.00007046399,0.0002875111,0.0001494921,0.00009027685],"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":[0.00001998507,0.00001042507,0.0007430151,0.0002069369,0.00001900687,2.296859e-7,0.000583174,0.9829555,0.01307242,0.0003701992,0.0001974567,0.001821619],"study_design_scores_gemma":[0.0001778795,0.00001234735,0.00362054,0.0003102363,0.00001276825,0.000002680903,0.0001399506,0.9784955,0.01450649,0.0004273221,0.002174867,0.000119371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483076,0.0004860901,0.05019453,0.0001235856,0.0003342149,0.000265526,0.00005759415,0.00002028336,0.0002105925],"genre_scores_gemma":[0.9769514,0.00001026654,0.02251129,0.000005456069,0.0000950591,0.00001007062,0.0002557891,0.0000161506,0.0001445337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02864381,"threshold_uncertainty_score":0.4968697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08403453094916458,"score_gpt":0.2945887019733971,"score_spread":0.2105541710242326,"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."}}