{"id":"W4285801284","doi":"10.3390/atmos13071144","title":"An Improved Air Quality Index Machine Learning-Based Forecasting with Multivariate Data Imputation Approach","year":2022,"lang":"en","type":"article","venue":"Atmosphere","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Missing data; Air quality index; Computer science; Artificial neural network; Random forest; Multivariate statistics; Predictive modelling; Data mining; Machine learning; Feature selection; Artificial intelligence; Meteorology","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":[0.001494623,0.0002056652,0.0001916681,0.00000359925,0.0009058039,0.00004543588,0.0006132863,0.00005099905,0.0004037561],"category_scores_gemma":[0.0001104961,0.0001859184,0.00003293407,0.0003507133,0.00009535072,0.0004069173,0.0005781905,0.0005257379,0.000009463874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002133441,"about_ca_system_score_gemma":0.00003520641,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009945372,"about_ca_topic_score_gemma":0.0002436825,"domain_scores_codex":[0.9976392,0.00047846,0.000306149,0.0007106395,0.0004940116,0.0003714883],"domain_scores_gemma":[0.9987667,0.0001238372,0.0002959337,0.0006754459,0.00001232768,0.0001258092],"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":[0.0001269942,0.0001687672,0.2363883,0.0000159274,0.00001255811,0.000004074584,0.0005737846,0.7313966,0.0001909293,0.000005718126,0.0000211219,0.03109521],"study_design_scores_gemma":[0.0007674388,0.000338999,0.04613061,0.000005475546,0.00001564841,0.000009042773,0.001246781,0.9502512,0.00004538328,0.00002928755,0.0008841851,0.0002759589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8459705,0.0000262452,0.1521284,0.00008317086,0.00009798907,0.0003275784,0.00005789745,0.0002596725,0.001048536],"genre_scores_gemma":[0.9601053,1.791048e-7,0.03889115,0.00009163832,0.00006616543,0.00004672087,0.0005246751,0.00004210884,0.0002320687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2188546,"threshold_uncertainty_score":0.9966475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04977443104511185,"score_gpt":0.2850346989494251,"score_spread":0.2352602679043132,"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."}}