{"id":"W2460954196","doi":"10.1007/s11869-016-0414-3","title":"Evaluating hourly air quality forecasting in Canada with nonlinear updatable machine learning methods","year":2016,"lang":"en","type":"article","venue":"Air Quality Atmosphere & Health","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"Environment and Climate Change Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Perceptron; Artificial neural network; Air quality index; Benchmark (surveying); Extreme learning machine; Computer science; Machine learning; Meteorology; Artificial intelligence; Econometrics; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01534674,0.0004865864,0.0008951517,0.00001117085,0.0007575019,0.00003089975,0.0005029592,0.0001240038,0.0005507061],"category_scores_gemma":[0.00180204,0.0003618726,0.00009347909,0.0007279926,0.0001953732,0.0005492448,0.0003734477,0.0007970467,0.00004695321],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004210178,"about_ca_system_score_gemma":0.0014302,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9762645,"about_ca_topic_score_gemma":0.9338162,"domain_scores_codex":[0.9903116,0.00413017,0.001686621,0.00110772,0.001271905,0.001491934],"domain_scores_gemma":[0.9954494,0.002118428,0.001097434,0.0007454471,0.00005677998,0.0005325665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001263614,0.00007628529,0.5866256,0.0001463548,0.0000202776,0.000009091616,0.0009028371,0.02324129,0.0001848496,0.00006831789,0.0001282675,0.3884704],"study_design_scores_gemma":[0.005335062,0.001616714,0.8252559,0.001659797,0.00004220814,0.00006599046,0.008079671,0.1309263,0.001415328,0.0007828592,0.02229844,0.002521711],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9678919,0.0002284235,0.02578947,0.004011334,0.0002504264,0.0005135783,0.00007301963,0.0001685302,0.001073294],"genre_scores_gemma":[0.7633145,0.00002537427,0.2347086,0.001031863,0.0001424827,0.00003629346,0.00003113478,0.00006650474,0.0006432738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3859487,"threshold_uncertainty_score":0.9998834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1095687087678308,"score_gpt":0.3947621673624881,"score_spread":0.2851934585946573,"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."}}