{"id":"W2803892188","doi":"10.1080/10962247.2018.1459956","title":"Forecasting air quality time series using deep learning","year":2018,"lang":"en","type":"article","venue":"Journal of the Air & Waste Management Association","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":310,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Air quality index; Series (stratigraphy); Environmental science; Time series; Meteorology; Artificial intelligence; Computer science; Machine learning; Geography; Geology","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":[0.003286718,0.0001239271,0.0001895059,0.00004739239,0.0005971382,0.0000495043,0.0003157012,0.00005977184,0.00008604603],"category_scores_gemma":[0.0004745638,0.00009639959,0.0001559605,0.000309271,0.0000615223,0.0005325658,0.0003765335,0.0002553318,0.00005637744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035469,"about_ca_system_score_gemma":0.000005461928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003604094,"about_ca_topic_score_gemma":0.0000113401,"domain_scores_codex":[0.9978959,0.0003672659,0.0005362714,0.0001382217,0.0007758906,0.0002864401],"domain_scores_gemma":[0.998139,0.0001069649,0.00149574,0.0001464985,0.00006319222,0.00004861917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001189326,0.00009470253,0.7730055,0.00006101355,0.00036175,0.000009165245,0.004377068,0.163017,0.003456196,0.00008754131,0.002423356,0.0529878],"study_design_scores_gemma":[0.002655094,0.0009387447,0.7085542,0.0009389856,0.0008796788,0.00008499015,0.01427707,0.225731,0.01009481,0.004522443,0.03002495,0.001298002],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890556,0.000009709688,0.002020393,0.000809979,0.0007144747,0.0001070491,5.417141e-7,0.00002292218,0.007259371],"genre_scores_gemma":[0.9863253,0.000004078255,0.005069681,0.0001046516,0.0007438769,8.482817e-7,5.085511e-7,0.00001589522,0.007735159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06445132,"threshold_uncertainty_score":0.4592765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02609765870339577,"score_gpt":0.261275470576689,"score_spread":0.2351778118732932,"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."}}