{"id":"W3180819074","doi":"10.1016/j.jweia.2021.104696","title":"Comparison of neural network types and architectures for generating a surrogate aerodynamic wind turbine blade model","year":2021,"lang":"en","type":"article","venue":"Journal of Wind Engineering and Industrial Aerodynamics","topic":"Wind Energy Research and Development","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Aerodynamics; Artificial neural network; Aeroelasticity; Computer science; Computation; Turbine; Turbine blade; Surrogate model; Wind speed; Blade (archaeology); Convolutional neural network; Multilayer perceptron; Perceptron; Artificial intelligence; Engineering; Algorithm; Structural engineering; Machine learning; Aerospace engineering; Geology","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":[0.000347299,0.0002066213,0.0005023734,0.0001226316,0.00006288649,0.00005666451,0.00009766929,0.0001777576,0.000002026237],"category_scores_gemma":[0.000182516,0.0001887378,0.00008376396,0.0001826452,0.00003175578,0.00006377754,0.0000480606,0.0005467404,6.094286e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004765771,"about_ca_system_score_gemma":0.00009054454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003427597,"about_ca_topic_score_gemma":0.00001586022,"domain_scores_codex":[0.9987051,0.00002419126,0.0005823207,0.0001328443,0.0002092058,0.0003462615],"domain_scores_gemma":[0.9993236,0.0001638689,0.0001131068,0.00009524273,0.000123901,0.0001802486],"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":[0.0000539807,0.00001633322,0.001085186,0.00008599211,0.000154377,0.000007899445,0.0001819983,0.9835305,0.01039185,0.00004279113,0.0001553107,0.004293758],"study_design_scores_gemma":[0.001032115,0.0001385053,0.001175309,0.0001390048,0.00004493333,0.00007333019,0.00005757702,0.9959899,0.0009792643,0.0000502487,0.0001384434,0.0001813746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921514,0.001745942,0.005411652,0.0000762186,0.0004706524,0.00007932429,0.00001746016,0.00002424773,0.00002305289],"genre_scores_gemma":[0.9883887,0.0001150925,0.01077723,0.000008372246,0.0006297755,0.000001262913,0.00001217807,0.00003589671,0.00003144865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01245937,"threshold_uncertainty_score":0.7696503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02671607591460893,"score_gpt":0.2492409898133048,"score_spread":0.2225249138986958,"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."}}