{"id":"W4283455497","doi":"10.1063/5.0097480","title":"A generalized framework for unsupervised learning and data recovery in computational fluid dynamics using discretized loss functions","year":2022,"lang":"en","type":"article","venue":"Physics of Fluids","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computational fluid dynamics; Discretization; Solver; Artificial neural network; Unsupervised learning; Artificial intelligence; Leverage (statistics); Automatic differentiation; Computer science; Fluid dynamics; Machine learning; Computational science; Applied mathematics; Algorithm; Physics; Mathematics; Mathematical analysis; Computation; Mechanics","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":[0.0001542234,0.0001169622,0.0002180849,0.00004639062,0.000257215,0.0000265688,0.0001539788,0.00002140889,0.0001142253],"category_scores_gemma":[0.00000803663,0.0001321983,0.00007140501,0.0002312015,0.00004940592,0.0001690023,0.0002421449,0.0002328472,3.547061e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003600303,"about_ca_system_score_gemma":0.00005869022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009119822,"about_ca_topic_score_gemma":0.000001265891,"domain_scores_codex":[0.9990809,0.00008600993,0.0002379544,0.0002870227,0.0001452907,0.0001628413],"domain_scores_gemma":[0.9994767,0.0001632867,0.00008369818,0.0001947687,0.00004203395,0.00003952695],"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":[0.0002464486,0.0002003971,0.007472852,0.00002470182,0.00009617765,3.551479e-7,0.0001918751,0.8168726,0.001375899,0.1575553,0.0001552062,0.01580821],"study_design_scores_gemma":[0.0007956285,0.00004545401,0.00008183454,0.00001473676,0.00002941386,7.782425e-7,0.000302005,0.9112539,0.00003184724,0.0870222,0.0002948942,0.0001272475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4151771,0.00005308686,0.5839099,0.0001369096,0.0001496587,0.0001622149,0.0003576653,0.0000106853,0.00004270087],"genre_scores_gemma":[0.9739039,0.000007309908,0.02383545,0.00002811088,0.0002445158,0.00004104177,0.001848345,0.00002320602,0.00006811263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5600744,"threshold_uncertainty_score":0.5390888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04293082644481701,"score_gpt":0.3138325861413614,"score_spread":0.2709017596965445,"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."}}