{"id":"W4392808101","doi":"10.1016/j.jenvman.2024.120510","title":"Genetic programming expressions for effluent quality prediction: Towards AI-driven monitoring and management of wastewater treatment plants","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Effluent; Wastewater; Sewage treatment; Chemical oxygen demand; Genetic programming; Water quality; Environmental science; Process (computing); Biochemical engineering; Environmental engineering; Process engineering; Computer science; Engineering; Machine learning; Ecology; Biology","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":[0.0003349842,0.0002438235,0.0002868236,0.0001231613,0.0001048963,0.00006712478,0.000282311,0.00006732265,0.00004493938],"category_scores_gemma":[0.000002180398,0.0001872731,0.0001570702,0.00007433821,0.0001737566,0.00024614,0.0005152933,0.0001083011,0.00001120438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006268038,"about_ca_system_score_gemma":0.000002806312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001669909,"about_ca_topic_score_gemma":4.465281e-7,"domain_scores_codex":[0.9980246,0.00005348789,0.0007158446,0.0003532567,0.0005580088,0.0002947813],"domain_scores_gemma":[0.99935,0.00003208925,0.0002054455,0.0003060749,0.000002552365,0.0001039037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004517374,0.001988122,0.1755113,0.002346156,0.002725986,0.0006419528,0.002847172,0.008517609,0.08773652,0.000325859,0.0007871624,0.7161204],"study_design_scores_gemma":[0.002287077,0.001869663,0.8477157,0.001510381,0.0006803279,0.0000847149,0.004550444,0.0003360668,0.09977461,0.001146398,0.03952729,0.0005173765],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959825,0.0007741028,0.00128908,0.0002853972,0.0006133211,0.0008300621,0.00004850425,0.00005558889,0.0001214446],"genre_scores_gemma":[0.9553402,0.00206729,0.04194369,0.000004987951,0.00009583268,0.0001230096,0.000002932044,0.00002573381,0.000396333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7156031,"threshold_uncertainty_score":0.7636775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0339840695778516,"score_gpt":0.2937172924410996,"score_spread":0.259733222863248,"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."}}