{"id":"W4388296459","doi":"10.1017/aer.2023.103","title":"Ensemble approaches for leveraging machine learning models in load estimation","year":2023,"lang":"en","type":"article","venue":"The Aeronautical Journal","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Ensemble learning; Machine learning; Leverage (statistics); Ensemble forecasting; Artificial intelligence; Mean squared error; Model selection; Range (aeronautics); Feature selection; Mathematics; Statistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002228344,0.001219097,0.001288344,0.001409599,0.000410532,0.0008636741,0.0009386762,0.0007196214,0.0008382961],"category_scores_gemma":[0.004178104,0.0004848239,0.0009123015,0.001213532,0.0002412425,0.001449255,0.0009587557,0.001241219,0.0003562358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003891538,"about_ca_system_score_gemma":0.0005140888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006636871,"about_ca_topic_score_gemma":0.008517973,"domain_scores_codex":[0.9993661,0.0002382339,0.00004292575,0.0001116808,0.0001828248,0.00005827471],"domain_scores_gemma":[0.9980561,0.001067109,0.0001532148,0.000257647,0.0004175037,0.00004847483],"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":[0.00004117581,0.00005739923,0.001724515,0.00002288291,0.0001782112,0.00004107118,0.00004683851,0.910431,0.001896679,0.001036534,0.0004390675,0.08408465],"study_design_scores_gemma":[8.466496e-7,0.00001474512,0.0002018826,0.000003107537,0.000009974149,0.000005203202,0.000004032915,0.9984797,0.0003175059,0.0008212767,0.0001376863,0.0000041071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06119728,0.0007927119,0.9355269,0.0002026218,0.00007053447,0.00003702715,0.0001054424,0.0008553172,0.001212247],"genre_scores_gemma":[0.8369465,0.0006499622,0.1601011,0.00009642845,0.0001366546,0.00009124622,0.0004085628,0.00009525032,0.00147427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006636871,"threshold_uncertainty_score":0.01319647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1197286019235123,"score_gpt":0.3055620781485286,"score_spread":0.1858334762250164,"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."}}