{"id":"W3041189004","doi":"10.1016/j.eti.2020.101028","title":"Development of a predictive emissions model using a gradient boosting machine learning method","year":2020,"lang":"en","type":"article","venue":"Environmental Technology & Innovation","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"Tetra Tech (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gradient boosting; Artificial neural network; Decision tree; NOx; Boosting (machine learning); Machine learning; Random forest; Hyperparameter; Computer science; Mean squared error; Artificial intelligence; Predictive modelling; Combustion; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003570119,0.0001625791,0.0001809883,0.0001199766,0.0003205087,0.000005071708,0.0001687837,0.0001428031,0.0001006754],"category_scores_gemma":[0.0001488478,0.0001687936,0.0000280372,0.000797494,0.0001757694,0.0001298081,0.0004381349,0.0003800067,0.00001532544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003044123,"about_ca_system_score_gemma":0.00001169392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009628607,"about_ca_topic_score_gemma":5.446973e-7,"domain_scores_codex":[0.9985765,0.0000369629,0.0005173415,0.0003618592,0.0002695134,0.0002377798],"domain_scores_gemma":[0.9994681,0.0000231637,0.0003350724,0.0001220996,0.000004501584,0.00004700078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001654921,0.00005857433,0.06030906,0.000007985592,0.00001788792,0.000001327925,0.002576786,0.06666615,0.8453147,0.00008466525,0.000005311814,0.02494095],"study_design_scores_gemma":[0.0002861032,0.0001076108,0.001063281,0.00003851124,0.00001995554,0.000008838406,0.001462485,0.6239437,0.3719041,0.0004209796,0.0005256785,0.0002187614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7498155,0.00001557607,0.2495562,0.0001670302,0.00001931768,0.0001248114,0.000005331091,0.00010906,0.0001871534],"genre_scores_gemma":[0.7334304,0.000001633909,0.266432,0.00004398741,0.00001275322,0.00001122068,0.00002163875,0.00001583307,0.00003056214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5572776,"threshold_uncertainty_score":0.6883204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05091584222706592,"score_gpt":0.2850678887541995,"score_spread":0.2341520465271336,"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."}}