{"id":"W2592903613","doi":"10.1016/j.envres.2017.01.035","title":"Very short-term reactive forecasting of the solar ultraviolet index using an extreme learning machine integrated with the solar zenith angle","year":2017,"lang":"en","type":"article","venue":"Environmental Research","topic":"Solar Radiation and Photovoltaics","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Solar zenith angle; Sigmoid function; Mean squared error; Extreme learning machine; Environmental science; Meteorology; Coefficient of determination; Spectroradiometer; Computer science; Statistics; Mathematics; Remote sensing; Machine learning; Physics; Geography","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00128679,0.0001475619,0.0001342715,0.00007598087,0.001770373,0.0003325108,0.00158149,0.00007016159,0.00003245774],"category_scores_gemma":[0.0001237653,0.00008677079,0.00005485849,0.0001709766,0.0005424092,0.000686553,0.0006060043,0.001020842,0.000005422482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000177119,"about_ca_system_score_gemma":0.00008766714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005325569,"about_ca_topic_score_gemma":0.0001595226,"domain_scores_codex":[0.9977337,0.000511755,0.00015696,0.0003509935,0.0008605959,0.000385973],"domain_scores_gemma":[0.9985498,0.0001937675,0.0001471618,0.0009761089,0.00003166189,0.0001015196],"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":[0.00009363263,0.0002847819,0.7097681,0.000009589003,0.00006221839,0.00003737333,0.004726741,0.001315847,0.1997222,0.00003942915,0.00001720066,0.0839229],"study_design_scores_gemma":[0.000447233,0.0003250119,0.3685823,0.00007157036,0.00001057072,0.00005563493,0.001651043,0.5615085,0.06654276,0.0001142963,0.0004842113,0.0002068796],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9833801,0.00005254985,0.01574956,0.0000855712,0.00005611095,0.0003072055,0.00001198518,0.00001573786,0.0003411201],"genre_scores_gemma":[0.999001,0.00001447939,0.0006850187,0.00002658422,0.0000432289,0.000009628126,0.000009057571,0.00002147135,0.0001895214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5601926,"threshold_uncertainty_score":0.9995292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1094993007312529,"score_gpt":0.3144338612665702,"score_spread":0.2049345605353174,"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."}}