{"id":"W4409359484","doi":"10.1016/j.compfluid.2025.106626","title":"Shape optimization for fluid flow with parametric level set method and deep neural networks","year":2025,"lang":"en","type":"article","venue":"Computers & Fluids","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Artificial neural network; Level set (data structures); Flow (mathematics); Level set method; Shape optimization; Set (abstract data type); Parametric statistics; Computer science; Computational fluid dynamics; Mathematics; Mathematical optimization; Artificial intelligence; Geometry; Mechanics; Physics; Finite element method; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004115995,0.000262835,0.0003002349,0.0005704816,0.0002611324,0.0005196415,0.0007425571,0.0001158123,0.000002643816],"category_scores_gemma":[0.00002449193,0.0002428007,0.00008409434,0.001772742,0.00005669627,0.0003021821,0.0004527983,0.0001166166,1.933832e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000308869,"about_ca_system_score_gemma":0.00004332105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006092881,"about_ca_topic_score_gemma":0.000001951962,"domain_scores_codex":[0.9983768,0.0001139063,0.0003249755,0.0006706937,0.0001811774,0.0003323756],"domain_scores_gemma":[0.9986731,0.0003552758,0.00007874221,0.0005195275,0.0002658256,0.0001075297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003170113,0.00005936583,0.0005052881,0.00005887339,0.00007970317,0.000003858858,0.0001932795,0.3657535,0.000009214542,0.1070353,0.004079215,0.5221907],"study_design_scores_gemma":[0.0006170268,0.0003246042,0.0004976543,0.00004339141,0.00002222021,0.0000152135,0.000003312015,0.9955717,0.0001096119,0.001524839,0.0009964522,0.0002740073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004663769,0.0006473645,0.9970751,0.0003380496,0.0004962629,0.0005401981,0.000004307773,0.000406235,0.00002604467],"genre_scores_gemma":[0.09655075,0.00009152525,0.9015045,0.001631177,0.00008060003,0.00006508185,0.00003922965,0.00001930865,0.00001779932],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6298182,"threshold_uncertainty_score":0.9901124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02939235261466876,"score_gpt":0.3090849773915667,"score_spread":0.2796926247768979,"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."}}