{"id":"W4388776014","doi":"10.1016/j.geoen.2023.212491","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":"article","venue":"Geoenergy Science and Engineering","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Mean squared error; Context (archaeology); Artificial neural network; Retraining; Data mining; Recurrent neural network; Production (economics); Reliability (semiconductor); Regression; Machine learning; Artificial intelligence; Statistics; Geology; Mathematics","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":[0.000514947,0.0001530509,0.0001753075,0.0002829155,0.0002088848,0.00004571402,0.0001388233,0.00005258443,9.589992e-7],"category_scores_gemma":[0.00007282411,0.0001364247,0.00003268239,0.0012814,0.00004098384,0.0004279117,0.00001930128,0.00007717832,5.542086e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005911278,"about_ca_system_score_gemma":0.00002937405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009101472,"about_ca_topic_score_gemma":0.00004530919,"domain_scores_codex":[0.9988195,0.000003900759,0.0002154567,0.0002987708,0.000258471,0.0004039046],"domain_scores_gemma":[0.9994653,0.00005145226,0.00006437894,0.0002190097,0.0001098038,0.00009005798],"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":[0.000006640852,0.000004871899,0.00007112179,0.00007641461,0.0000102255,2.886103e-7,0.00009840141,0.8847319,0.1091945,0.000009562331,0.000005013568,0.005791045],"study_design_scores_gemma":[0.0001613709,0.00004558431,0.003493166,0.00005330851,0.00002112735,0.000004858769,0.00003181274,0.9879264,0.008007914,0.00001349189,0.00007789263,0.0001630384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.861564,0.00002017171,0.1377126,0.00005549243,0.00008101604,0.0001693122,0.000002770202,0.0003530523,0.00004157547],"genre_scores_gemma":[0.991561,0.000008921879,0.008109867,0.000006513207,0.0001246226,0.00006865197,0.00007638984,0.00003208766,0.00001194844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.129997,"threshold_uncertainty_score":0.5563236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007860675787916799,"score_gpt":0.2060078087594926,"score_spread":0.1981471329715758,"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."}}