{"id":"W4313031989","doi":"10.2139/ssrn.4234605","title":"Multi-Step Forecast of Pm2.5 and Pm10 Concentrations Using Convolutional Neural Network Integrated with Spatial-Temporal Attention and Residual Learning","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Nuclear Physics and Applications","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Residual; Convolutional neural network; Computer science; Artificial intelligence; Spatial learning; Machine learning; Artificial neural network; Deep learning; Environmental science; Algorithm; Psychology; Cognition","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":[0.0002815524,0.0001026848,0.0001318929,0.00003181826,0.0007453805,0.00004223738,0.00006194843,0.00001348492,0.00004626307],"category_scores_gemma":[0.000001384249,0.0000956585,0.00003613902,0.0001399126,0.00008603806,0.0001057383,0.00005063153,0.0008678712,3.532752e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007959776,"about_ca_system_score_gemma":0.0004463082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006504128,"about_ca_topic_score_gemma":0.000247744,"domain_scores_codex":[0.9989114,0.00009007673,0.0001924363,0.0001450084,0.0001370543,0.0005239903],"domain_scores_gemma":[0.9995744,0.00002223822,0.0002263313,0.0000547965,0.00007394666,0.00004823783],"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":[0.0002080415,0.0002927505,0.5911469,0.000008584813,0.000492459,0.000001303818,0.0003456172,0.06095646,0.007804327,0.3102672,0.0001004505,0.02837594],"study_design_scores_gemma":[0.006643243,0.001746172,0.06381876,0.00007772836,0.0004068161,0.0003942887,0.02631915,0.842323,0.00009791153,0.05418749,0.003145057,0.0008403607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9068665,0.000189063,0.0926069,0.000111131,0.0000301101,0.0001271866,0.00002652463,0.000007484378,0.00003508706],"genre_scores_gemma":[0.9983833,0.00001388142,0.001166558,0.000007047649,0.0001799629,0.000008382143,0.0001054635,0.00001641269,0.000118938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7813666,"threshold_uncertainty_score":0.573294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109498735186342,"score_gpt":0.2310707084472538,"score_spread":0.2201208349286196,"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."}}