{"id":"W3084086717","doi":"10.1063/5.0030137","title":"Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models","year":2021,"lang":"en","type":"preprint","venue":"Physics of Fluids","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation Singapore","keywords":"Computer science; Algorithm; Autoencoder; Flow (mathematics); Recurrent neural network; Solver; Deep learning; Applied mathematics; Mathematics; Artificial intelligence; Artificial neural network; Mathematical optimization; Geometry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001556392,0.0003623449,0.0006893093,0.00008557613,0.0001322446,0.00005491161,0.0002579431,0.00009983216,0.0002085615],"category_scores_gemma":[0.000003949997,0.0004052803,0.0004572396,0.0002444596,0.0001001799,0.0001890253,0.0003172444,0.0009350633,5.649362e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006399615,"about_ca_system_score_gemma":0.0005390393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001916381,"about_ca_topic_score_gemma":4.695016e-7,"domain_scores_codex":[0.9979444,0.0001656379,0.0006224503,0.00054189,0.0004360261,0.0002896657],"domain_scores_gemma":[0.9982278,0.0000611762,0.0004447838,0.0006031887,0.0005572109,0.000105862],"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":[0.000007134833,0.0003472116,0.000437082,0.0001337163,0.0002526094,5.897778e-7,0.0001157516,0.9813186,0.007090297,0.002420561,0.0000418514,0.007834578],"study_design_scores_gemma":[0.0003272736,0.00003417437,0.00005757952,0.0003137975,0.0002177423,4.067395e-7,0.0001247202,0.9842955,0.008979613,0.005335124,0.00002586719,0.0002881582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1419452,0.000114833,0.8529788,0.00002692877,0.0006192672,0.0002623297,0.000118002,0.00003805397,0.003896547],"genre_scores_gemma":[0.9693987,0.00002651444,0.02895017,0.00001046995,0.0006956406,0.00004022341,0.000755519,0.00005841421,0.00006439624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8274534,"threshold_uncertainty_score":0.9998399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03852439192367674,"score_gpt":0.3011030588610863,"score_spread":0.2625786669374096,"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."}}