{"id":"W2465694013","doi":"10.2166/ws.2015.066","title":"Development of artificial neural networks based confidence intervals and response surfaces for the optimization of coagulation performance","year":2015,"lang":"en","type":"article","venue":"Water Science & Technology Water Supply","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Alum; Turbidity; Interval (graph theory); Artificial neural network; Mean squared error; Coagulation; Confidence interval; Statistics; Carbon dioxide; Response surface methodology; Mathematics; Environmental science; Computer science; Machine learning; Chemistry; Ecology","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":[0.002442143,0.0001105047,0.0001510061,0.0001397329,0.0002630052,0.00002993524,0.0004981679,0.00009305056,0.00003149259],"category_scores_gemma":[0.0001244666,0.00005681702,0.00001718796,0.0003531914,0.002350093,0.0002576403,0.0003436794,0.00008270322,0.000004250555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006173955,"about_ca_system_score_gemma":0.00002795775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001778529,"about_ca_topic_score_gemma":0.00001188703,"domain_scores_codex":[0.9986798,0.00004332334,0.0003511399,0.0003010881,0.0002724318,0.0003522747],"domain_scores_gemma":[0.9994982,0.00005593177,0.0000890934,0.000237798,0.00007148808,0.00004742767],"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":[0.0002043217,0.00001869466,0.01433775,0.000004060975,0.000001647782,2.985055e-7,0.00137697,0.8399258,0.1394861,0.000008522766,0.000004095129,0.004631774],"study_design_scores_gemma":[0.0001020908,0.0001433473,0.001450981,0.000007519606,0.000004255655,0.00000306183,0.00004131635,0.5821026,0.4159489,0.00007626913,0.00006519884,0.00005449469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9176775,0.000006774345,0.08064735,0.00124892,0.0001043201,0.0002687414,0.00000106904,0.00003955949,0.000005718838],"genre_scores_gemma":[0.9684078,5.207486e-7,0.03149593,0.0000427457,0.000004095989,0.00002520766,0.000003307807,0.000005528717,0.00001489546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2764628,"threshold_uncertainty_score":0.8659014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03179629015219974,"score_gpt":0.2476881616406878,"score_spread":0.2158918714884881,"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."}}