{"id":"W1970821085","doi":"10.1016/j.ast.2015.02.019","title":"Surrogate models and mixtures of experts in aerodynamic performance prediction for aircraft mission analysis","year":2015,"lang":"en","type":"article","venue":"Aerospace Science and Technology","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":134,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Surrogate model; Kriging; Aerodynamics; Computer science; Interpolation (computer graphics); Lift (data mining); Mathematical optimization; Transonic; Sampling (signal processing); Function (biology); Algorithm; Mathematics; Machine learning; Aerospace engineering; Artificial intelligence; Engineering","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":[0.002378349,0.00009446873,0.0002629395,0.00114192,0.0001021911,0.00004350628,0.0003615637,0.00011945,0.000001098862],"category_scores_gemma":[0.001743546,0.00006660665,0.00002073421,0.003524676,0.000832097,0.0004505209,0.0001295763,0.00006687964,4.127639e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003797803,"about_ca_system_score_gemma":0.0001256278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002236805,"about_ca_topic_score_gemma":0.00003356912,"domain_scores_codex":[0.9985167,0.00001647517,0.0002765609,0.0004496395,0.0005036276,0.0002370311],"domain_scores_gemma":[0.9989101,0.0001376358,0.00009472984,0.000316266,0.0004507722,0.00009047792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002206884,0.0002476228,0.4332832,0.00007911204,0.00008283195,0.000005873741,0.004884861,0.3433581,0.1118739,0.03480628,0.001703312,0.06945418],"study_design_scores_gemma":[0.0004357381,0.0002369178,0.007425198,0.00002054965,0.00002541155,0.000008088346,0.0009595534,0.9606201,0.004060431,0.02600991,0.00009038322,0.0001077121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9432135,0.0005353204,0.05507999,0.0008049973,0.00008662727,0.000173405,0.000004650453,0.00004140771,0.00006011395],"genre_scores_gemma":[0.9941015,0.00007194994,0.005693889,0.00001077534,0.000004524063,0.00001223075,6.600658e-7,0.000003249979,0.0001012543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.617262,"threshold_uncertainty_score":0.3065896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07051560220608662,"score_gpt":0.323149665249358,"score_spread":0.2526340630432714,"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."}}