{"id":"W4205572831","doi":"10.1109/bigdata52589.2021.9671347","title":"Forecasting Air Pollution using a Modified Compositional Learning Approach","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Random forest; Air quality index; Hyperparameter; Artificial intelligence; Set (abstract data type); Linear regression; Machine learning; Computer science; Air pollution; Mean squared error; Regression; Statistics; Mathematics; Meteorology; Chemistry; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007969019,0.0002539818,0.0002278862,0.00008131652,0.0004358286,0.0002353186,0.00169396,0.0001135513,0.0005155699],"category_scores_gemma":[0.0004370745,0.0002742148,0.00004734125,0.0002887965,0.000170432,0.0008461522,0.002176779,0.0005227692,0.0001368949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002294561,"about_ca_system_score_gemma":0.0001399308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00047264,"about_ca_topic_score_gemma":0.00006957231,"domain_scores_codex":[0.9967753,0.0002196367,0.0004464878,0.0011581,0.001022317,0.0003781344],"domain_scores_gemma":[0.9982205,0.0001090181,0.0002611732,0.001176568,0.00009261052,0.0001401149],"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":[0.0003296319,0.001235571,0.007860514,0.00008123138,0.0004134997,0.0002966192,0.0006839695,0.3117366,0.0660636,0.004411566,0.01248991,0.5943973],"study_design_scores_gemma":[0.0004450456,0.00003169195,0.0009991032,0.0001682039,0.00003114086,0.0001273538,0.0003960871,0.9895042,0.001146974,0.00031712,0.006474629,0.0003584399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4078127,0.00005584988,0.5022917,0.002567274,0.008432012,0.0003885622,0.008246078,0.0001867046,0.07001904],"genre_scores_gemma":[0.9694532,0.00002464599,0.01138282,0.0002101217,0.001753862,0.000006728765,0.01651225,0.00002464356,0.0006317879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6777676,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4993754370384956,"score_gpt":0.3612890250771909,"score_spread":0.1380864119613047,"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."}}