{"id":"W4319865064","doi":"10.2139/ssrn.4329633","title":"Long-Term Evaluation of Machine Learning Based Methods for Air Emission Monitoring","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Overfitting; Mean squared error; Machine learning; Artificial neural network; Term (time); Computer science; Artificial intelligence; Audit; Algorithm; Gradient boosting; Statistics; Mathematics; Accounting; Random forest","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":[0.01366042,0.0001138893,0.0001455564,0.00008061598,0.0003384116,0.00001462548,0.000175662,0.00006287759,0.00004477188],"category_scores_gemma":[0.0006565564,0.0001023542,0.0001115294,0.0003024121,0.00003454398,0.00013164,0.00005408693,0.0007427887,0.00001192649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009952469,"about_ca_system_score_gemma":0.0002195464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003894466,"about_ca_topic_score_gemma":0.000009599471,"domain_scores_codex":[0.9975936,0.0004055966,0.000295309,0.0001859911,0.0004828052,0.001036739],"domain_scores_gemma":[0.9993012,0.00023909,0.0002377998,0.0001080977,0.00004485508,0.00006894363],"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":[0.00004483265,0.00002822751,0.2302392,0.00001681598,0.00003066489,3.449377e-7,0.0002058898,0.03932287,0.01974984,0.00005227208,0.000006864118,0.7103021],"study_design_scores_gemma":[0.002703746,0.0009695208,0.1675618,0.0002581216,0.0002642196,0.00005857087,0.001159769,0.7207116,0.08021008,0.02523356,0.0003672772,0.0005016837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8442296,0.0004467386,0.1545611,0.0001320015,0.0003100858,0.0001674623,7.090853e-7,0.0000578671,0.00009447029],"genre_scores_gemma":[0.9953141,0.0001408031,0.003643076,0.000003071387,0.000228501,0.0000149153,0.000007062332,0.00002333935,0.0006251304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7098004,"threshold_uncertainty_score":0.4734456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06030866881905409,"score_gpt":0.3916659271384849,"score_spread":0.3313572583194307,"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."}}