{"id":"W4224273000","doi":"10.1016/j.scitotenv.2022.155324","title":"An integrated 3D CNN-GRU deep learning method for short-term prediction of PM2.5 concentration in urban environment","year":2022,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":141,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique; Carleton University","funders":"","keywords":"Convolutional neural network; Autoregressive integrated moving average; Deep learning; Air quality index; Computer science; Term (time); Artificial intelligence; Artificial neural network; Time series; Machine learning; Environmental science; Pattern recognition (psychology); Data mining; Meteorology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002976314,0.001003869,0.0008100013,0.0006168848,0.0002872674,0.0004986324,0.00135585,0.0009568777,0.002271359],"category_scores_gemma":[0.0004902434,0.0004846627,0.0007857819,0.0006837242,0.0001784323,0.0006198635,0.0007557732,0.000864268,0.0008077333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000577568,"about_ca_system_score_gemma":0.001040858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04014548,"about_ca_topic_score_gemma":0.04396183,"domain_scores_codex":[0.9998475,0.00001458274,0.000006661635,0.00004805901,0.00003957451,0.0000436063],"domain_scores_gemma":[0.9998906,0.00002334977,0.000008877596,0.00001113704,0.00005304698,0.00001303023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003117909,0.0003102482,0.005996596,0.0001274492,0.0002663805,0.000199367,0.0000463958,0.4355198,0.01354655,0.001544519,0.0155309,0.5266001],"study_design_scores_gemma":[0.000003741883,0.00001176884,0.0003625738,0.000003362944,0.00001094035,0.000007522847,0.000002761024,0.998455,0.0006764306,0.0001767013,0.0002847245,0.000004331117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2190575,0.006311952,0.7536213,0.001025977,0.001080975,0.000115644,0.002572273,0.008239406,0.007975072],"genre_scores_gemma":[0.8697848,0.001532313,0.1113079,0.0005841215,0.0001964066,0.0001263829,0.003312428,0.0002048145,0.01295081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04014548,"threshold_uncertainty_score":0.07982361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02077895611289331,"score_gpt":0.2551189607768146,"score_spread":0.2343400046639213,"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."}}