{"id":"W4386999101","doi":"10.1016/j.watres.2023.120667","title":"Machine learning for modeling N2O emissions from wastewater treatment plants: Aligning model performance, complexity, and interpretability","year":2023,"lang":"en","type":"article","venue":"Water Research","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":96,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; University of Alberta","funders":"Canada Research Chairs","keywords":"Interpretability; Machine learning; Computer science; Artificial intelligence; Feature selection; Process (computing); Feature (linguistics); Artificial neural network; Model selection; Data mining","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":[0.001425649,0.000146052,0.0001771377,0.00008111264,0.000865737,0.00008566095,0.0001784652,0.00006542285,0.0001081491],"category_scores_gemma":[0.0000485471,0.00009613459,0.00004595817,0.00009607536,0.0001733182,0.0001765495,0.0006647827,0.000261912,0.0001495732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853258,"about_ca_system_score_gemma":0.000007484934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001796575,"about_ca_topic_score_gemma":0.00003491582,"domain_scores_codex":[0.9981057,0.0001530415,0.0002317968,0.0004593885,0.0003789781,0.0006710713],"domain_scores_gemma":[0.9994933,0.00009723296,0.00001678271,0.0002205345,0.00001442798,0.0001577201],"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":[0.0002839539,0.0001103884,0.1294692,0.00008418728,0.00004846758,0.000006331239,0.02623658,0.7082117,0.1124229,0.00001118874,0.000145363,0.02296972],"study_design_scores_gemma":[0.0003152862,0.0001431891,0.0004431578,0.00005216022,0.00000493809,0.000001211159,0.0005348352,0.9770343,0.01890827,0.001989305,0.0004458697,0.0001275039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973958,0.00001566341,0.001324389,0.000266914,0.00004367625,0.000281557,0.00003650146,0.000109242,0.0005262194],"genre_scores_gemma":[0.9961082,0.0000485556,0.001581824,0.000005412182,0.00006059142,0.00009016704,0.0001510095,0.00002506434,0.001929158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2688226,"threshold_uncertainty_score":0.6658636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2353114245475959,"score_gpt":0.377125246212714,"score_spread":0.1418138216651181,"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."}}