{"id":"W3115103108","doi":"10.1016/j.eswa.2020.114513","title":"Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering","year":2020,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":446,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Cluster analysis; Beijing; Convolutional neural network; Artificial intelligence; Air quality index; Artificial neural network; Deep learning; Data mining; Machine learning; Pattern recognition (psychology); Meteorology","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":[],"consensus_categories":[],"category_scores_codex":[0.0005124046,0.0002513318,0.0003286575,0.00005269317,0.000443043,0.00009067116,0.0001457261,0.0001114787,0.000005528415],"category_scores_gemma":[0.00006420948,0.0002384459,0.00002787827,0.0003542336,0.0001600494,0.0003123344,0.0002675053,0.0002343215,0.00001069098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001772846,"about_ca_system_score_gemma":0.00001616311,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007246937,"about_ca_topic_score_gemma":0.0005024284,"domain_scores_codex":[0.99802,0.0001308478,0.0005672036,0.0006504914,0.0002686527,0.0003627933],"domain_scores_gemma":[0.9990758,0.0001119927,0.0002880273,0.0002559953,0.0000192679,0.0002489586],"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":[0.00002808053,0.00006510099,0.9561329,0.000154334,0.00001471874,0.000005228994,0.01005737,0.01959059,0.008909456,0.00001418925,0.00001184304,0.005016142],"study_design_scores_gemma":[0.000888177,0.00003591851,0.08747242,0.0002034295,0.000007761537,0.00002657246,0.004040325,0.9060913,0.0001105392,0.00000230445,0.0007417086,0.0003795042],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6887224,0.00028785,0.3098295,0.0001837228,0.00004327553,0.0007396857,0.000009519325,0.0001005619,0.00008342812],"genre_scores_gemma":[0.9496843,0.000008290284,0.04970864,0.0001058078,0.0001798505,0.0002268668,0.000008367551,0.00003819871,0.00003967998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8865008,"threshold_uncertainty_score":0.9993639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1115916191243101,"score_gpt":0.3171298078202858,"score_spread":0.2055381886959757,"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."}}