{"id":"W2901670282","doi":"10.1016/j.flowmeasinst.2018.11.017","title":"Artificial intelligence models for prediction of the aeration efficiency of the stepped weir","year":2018,"lang":"en","type":"article","venue":"Flow Measurement and Instrumentation","topic":"Hydraulic flow and structures","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Weir; Mean squared error; Reynolds number; Aeration; Flow (mathematics); Mathematics; Coefficient of determination; Root mean square; Statistics; Mechanics; Engineering; Physics; Geometry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005594168,0.0004969159,0.0006821143,0.0004935112,0.0004553022,0.001077189,0.0006954166,0.0008656217,0.001025502],"category_scores_gemma":[0.001984478,0.0003464864,0.0004698173,0.0004473543,0.0006192456,0.0006276832,0.0003545436,0.0008442538,0.0001501074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055403,"about_ca_system_score_gemma":0.0007998777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02479164,"about_ca_topic_score_gemma":0.01226071,"domain_scores_codex":[0.9998797,0.00003938182,0.000006889254,0.00003121255,0.00001950449,0.00002315636],"domain_scores_gemma":[0.999121,0.0006376682,0.00008179182,0.00002477232,0.0001036856,0.00003102292],"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":[0.000009805799,0.000008189677,0.0003881342,0.000003082288,0.000007363869,0.000005860545,0.000004480765,0.9981982,0.00007300716,0.0003561752,0.00003245459,0.0009132465],"study_design_scores_gemma":[7.631041e-7,0.000002458099,0.00008906052,3.189798e-7,0.000001096275,5.051965e-7,0.000001127027,0.9997439,0.00002085453,0.0001322798,0.000006846089,7.082033e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8879942,0.0003541904,0.1064941,0.0003758414,0.0000456901,0.00002610715,0.0001521212,0.0002400206,0.004317724],"genre_scores_gemma":[0.9956887,0.00007128967,0.00288213,0.00001450285,0.000007556238,0.00001423282,0.00005290705,0.000005908479,0.001262786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02479164,"threshold_uncertainty_score":0.04929465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04388821042871217,"score_gpt":0.2230292099834384,"score_spread":0.1791409995547263,"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."}}