{"id":"W4366503425","doi":"10.1016/j.apr.2023.101752","title":"Multi-step ahead hourly forecasting of air quality indices in Australia: Application of an optimal time-varying decomposition-based ensemble deep learning algorithm","year":2023,"lang":"en","type":"article","venue":"Atmospheric Pollution Research","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Hilbert–Huang transform; Mean squared error; Artificial neural network; Feature selection; Computer science; Discriminative model; Artificial intelligence; Feature (linguistics); Data mining; Mode (computer interface); Algorithm; Random forest; Principal component analysis; Filter (signal processing); Pattern recognition (psychology); Machine learning; Mathematics; Statistics","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":[0.004217089,0.0001450671,0.0002637706,0.00004550267,0.000321811,0.00002015618,0.0002975521,0.0001441499,0.0001023355],"category_scores_gemma":[0.000306889,0.0001577683,0.00006853606,0.001979467,0.0003189041,0.0002874055,0.0001639469,0.0004482407,0.0001066366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000317244,"about_ca_system_score_gemma":0.00003727989,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01377217,"about_ca_topic_score_gemma":0.0001783794,"domain_scores_codex":[0.9967327,0.0007713227,0.0006100176,0.0004307452,0.0008620696,0.0005931132],"domain_scores_gemma":[0.9987823,0.0004663708,0.0002899586,0.0002620533,0.00006621862,0.0001331387],"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":[0.00007753327,0.000219524,0.0580117,0.00006921904,0.00001047326,0.000005761995,0.001119073,0.6242251,0.0370083,0.000004090533,0.00001119233,0.279238],"study_design_scores_gemma":[0.0004418133,0.0001829736,0.1954783,0.000056332,0.000003752929,0.000001529993,0.0007908735,0.7972512,0.005623682,0.00002294845,0.00002512884,0.0001215099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9263674,0.00001780681,0.07301626,0.00005373621,0.00003150143,0.0003057308,0.00001117802,0.00007510409,0.0001213029],"genre_scores_gemma":[0.8677166,0.000002811581,0.1319637,0.000004819815,0.00003582175,0.0000491736,0.00004920291,0.0000188963,0.0001589581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2791165,"threshold_uncertainty_score":0.9927952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09192673908280491,"score_gpt":0.3965964832192423,"score_spread":0.3046697441364374,"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."}}