{"id":"W4317584117","doi":"10.2514/6.2023-1201","title":"Detecting Missing Flow Separation using Supervised Machine Learning","year":2023,"lang":"en","type":"article","venue":"AIAA SCITECH 2023 Forum","topic":"Fluid Dynamics and Turbulent Flows","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Principal component analysis; Airfoil; Computer science; Computational fluid dynamics; Artificial intelligence; Missing data; Subspace topology; Classifier (UML); Flow separation; Machine learning; Flow (mathematics); Pattern recognition (psychology); Mathematics; Engineering","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":[0.0003304523,0.0002138362,0.0001916012,0.0003219863,0.0003733308,0.0001472824,0.0001516308,0.000122776,0.00008809205],"category_scores_gemma":[0.00006990095,0.0002338438,0.00009812758,0.001020199,0.00001752662,0.000241167,0.0000898752,0.0003414644,0.0002213148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000101644,"about_ca_system_score_gemma":0.00001744721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007349214,"about_ca_topic_score_gemma":0.00007948279,"domain_scores_codex":[0.9986154,0.00002739177,0.0002775163,0.0002566308,0.0002369919,0.0005860514],"domain_scores_gemma":[0.9995655,0.00006727386,0.00002995284,0.0002080001,0.00003563004,0.00009359514],"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":[0.000004211509,0.000004302774,0.001570912,0.00005146853,0.00002966322,0.00001997436,0.0001362269,0.8927016,0.08328211,0.0000378822,0.000561193,0.02160042],"study_design_scores_gemma":[0.0002431736,0.00002260569,0.0001788462,0.00006251148,0.00001384126,0.0000106944,0.00006127713,0.9927512,0.003038944,0.0002468837,0.003104604,0.000265458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483132,0.0004335972,0.04508524,0.0003667121,0.001326752,0.0002739507,0.00002632968,0.0024478,0.001726457],"genre_scores_gemma":[0.9945586,0.00006383014,0.004416021,0.00004836846,0.000132189,0.00001175237,0.0001125155,0.0001003873,0.000556316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1000495,"threshold_uncertainty_score":0.9535872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155595860637638,"score_gpt":0.2444810503845094,"score_spread":0.2289214643207456,"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."}}