{"id":"W2974296449","doi":"10.1007/s00477-019-01732-9","title":"A random forest model for inflow prediction at wastewater treatment plants","year":2019,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":121,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hydromantis Environmental Software Solutions (Canada); McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Water Consortium","keywords":"Inflow; Wastewater; Multilayer perceptron; Environmental science; Sewage treatment; Probabilistic logic; Random forest; Hydrology (agriculture); Computer science; Artificial neural network; Environmental engineering; Engineering; Machine learning; Artificial intelligence; Meteorology; Geotechnical engineering","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":[0.0006072077,0.0002292852,0.0002410296,0.00007382008,0.0007158319,0.00003068374,0.0001357247,0.00008627328,0.0004178756],"category_scores_gemma":[0.00001085894,0.0001652866,0.00006569157,0.00003933207,0.000440925,0.0001727558,0.0005642361,0.0001718889,0.0003654772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007714627,"about_ca_system_score_gemma":0.000008596547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000127368,"about_ca_topic_score_gemma":0.0003030595,"domain_scores_codex":[0.9979059,0.00009377365,0.0002246062,0.0006010967,0.000510213,0.0006643775],"domain_scores_gemma":[0.9992462,0.0002312095,0.00005983563,0.0002842594,0.000002500967,0.0001760136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001557003,0.0006762519,0.7098925,0.00002658856,0.0002869709,0.000006635593,0.001465786,0.2782386,0.003755795,0.00006848873,0.001097337,0.00292814],"study_design_scores_gemma":[0.00766244,0.002890307,0.1518667,0.00002154373,0.00008054014,0.000006868951,0.0005830762,0.8302972,0.0002731083,0.004451685,0.001562004,0.0003045488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898653,0.00006910921,0.006447528,0.0001881848,0.00008991455,0.002076156,0.0002418566,0.0000235381,0.0009983913],"genre_scores_gemma":[0.9861792,0.0009159574,0.0008057439,0.00002340279,0.00003161824,0.0006824437,0.0001163166,0.00002219527,0.01122311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5580258,"threshold_uncertainty_score":0.6740192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02152767620015074,"score_gpt":0.2917514941628741,"score_spread":0.2702238179627234,"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."}}