{"id":"W2931813856","doi":"10.1016/j.jenvman.2019.03.137","title":"Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology","year":2019,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; University of Ottawa","funders":"","keywords":"Autoregressive integrated moving average; Biochemical oxygen demand; Effluent; Wastewater; Total suspended solids; Outlier; Nonlinear system; Chemical oxygen demand; Linear model; Environmental science; Mathematics; Environmental engineering; Engineering; Time series; 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":[0.001064484,0.0002020463,0.0003614199,0.0001584707,0.00007804878,0.00005377882,0.0004763867,0.00003551239,0.00005805422],"category_scores_gemma":[0.00001133744,0.0001535641,0.0001927675,0.00006231968,0.00003267799,0.0002675801,0.0003329916,0.0001610317,0.00004127529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002798426,"about_ca_system_score_gemma":0.00001129266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004840442,"about_ca_topic_score_gemma":8.285415e-7,"domain_scores_codex":[0.9981278,0.000250386,0.0006022635,0.0003012209,0.0004124411,0.0003059258],"domain_scores_gemma":[0.9988366,0.0001322074,0.0005148075,0.0003969225,0.00000485754,0.000114647],"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":[0.00101756,0.006346666,0.1768963,0.0004200582,0.00411046,0.001174542,0.005500638,0.4798252,0.1255342,0.002818268,0.0001500118,0.1962061],"study_design_scores_gemma":[0.009696054,0.004189235,0.06039191,0.0002807789,0.0004198476,0.001786689,0.001607853,0.8675532,0.018896,0.0005643093,0.0334773,0.001136825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9270971,0.00006833634,0.07157493,0.000246658,0.0005648332,0.0001859462,0.00001055858,0.00001940008,0.0002322255],"genre_scores_gemma":[0.6006159,0.00004913668,0.3986531,0.0001519816,0.00007850703,0.000001717628,0.000003459397,0.0000125173,0.0004336983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.387728,"threshold_uncertainty_score":0.6262162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06196688693450317,"score_gpt":0.3009898807168352,"score_spread":0.2390229937823321,"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."}}