{"id":"W4386554020","doi":"10.2139/ssrn.4566064","title":"A Novel Formulation of Rnn-Based Neural Network with Real-Time Updating – an Application for Dynamic Hydraulic Fractured Shale Gas Production Forecasting","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hydraulic fracturing; Shale gas; Oil shale; Petroleum engineering; Production (economics); Artificial neural network; Computer science; Recurrent neural network; Geology; Artificial intelligence; Economics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009826608,0.000872953,0.0006546676,0.0002880064,0.0002491204,0.0008132446,0.001305357,0.001598284,0.002568508],"category_scores_gemma":[0.001601211,0.000338784,0.0005247786,0.0005820292,0.0004944397,0.00104017,0.0007157237,0.001101361,0.0005798026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005949277,"about_ca_system_score_gemma":0.0007320648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006754347,"about_ca_topic_score_gemma":0.007940274,"domain_scores_codex":[0.9997022,0.0000834798,0.00001998917,0.00008617016,0.00008449687,0.00002365191],"domain_scores_gemma":[0.9996112,0.0001349813,0.00003994158,0.00002619385,0.0001710964,0.00001656579],"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":[0.00003025418,0.00002510634,0.000201867,0.0001031193,0.00003176518,0.00009202972,0.00002556414,0.9336042,0.003182618,0.01173696,0.00147117,0.04949543],"study_design_scores_gemma":[0.000001184278,0.000005100926,0.00002628491,0.000002399225,0.000002513537,0.000007179306,8.654154e-7,0.9990602,0.0001249597,0.0004670759,0.0003002766,0.000001932901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003932952,0.0005620653,0.9923321,0.0001294161,0.0001634748,0.00002695065,0.00005405417,0.0001122986,0.002686603],"genre_scores_gemma":[0.474355,0.001891877,0.5049847,0.0003039046,0.0006059491,0.0003343034,0.0004238446,0.0002162484,0.01688413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006754347,"threshold_uncertainty_score":0.01343006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478735711742389,"score_gpt":0.2422514594550722,"score_spread":0.2274641023376484,"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."}}