{"id":"W3083696742","doi":"10.2166/ws.2020.205","title":"A framework for the use of artificial neural networks for water treatment: development and application","year":2020,"lang":"en","type":"article","venue":"Water Science & Technology Water Supply","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial neural network; Water treatment; Water quality; Computer science; Water disinfection; Water supply; Environmental science; Process engineering; Environmental engineering; Engineering; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003374229,0.0009612733,0.000525525,0.001134331,0.0004161175,0.00117493,0.001698984,0.00110055,0.001730857],"category_scores_gemma":[0.003871678,0.0004928401,0.0009739079,0.000730188,0.0008527166,0.0009398253,0.001427258,0.001175074,0.0004685893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001155595,"about_ca_system_score_gemma":0.0017359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009309964,"about_ca_topic_score_gemma":0.007126991,"domain_scores_codex":[0.9988883,0.0005806012,0.0000907057,0.0001292714,0.0002660721,0.00004511419],"domain_scores_gemma":[0.9987514,0.0006326772,0.00009487801,0.00006986626,0.0004091238,0.00004208841],"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":[0.00001977404,0.0000921106,0.0007208564,0.0001825548,0.00007720888,0.0001763534,0.0001138281,0.8003183,0.001975824,0.1425365,0.001222613,0.05256414],"study_design_scores_gemma":[0.000006097318,0.00002112814,0.00009299566,0.00005164992,0.000007317619,0.0000141237,0.00001333669,0.9685674,0.0005423851,0.02685648,0.003817676,0.000009398509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001972835,0.00028838,0.9948316,0.0002297141,0.00003104706,0.00007995326,0.00004105668,0.0001764319,0.002348907],"genre_scores_gemma":[0.09784223,0.0009661495,0.8975172,0.000102093,0.00006658461,0.0006810135,0.0001457204,0.00006943965,0.002609613],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009309964,"threshold_uncertainty_score":0.01851159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05987658030042212,"score_gpt":0.2703078935797187,"score_spread":0.2104313132792966,"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."}}