{"id":"W4393932440","doi":"10.3390/w16071042","title":"Applying Recurrent Neural Networks and Blocked Cross-Validation to Model Conventional Drinking Water Treatment Processes","year":2024,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recurrent neural network; Computer science; Test set; Artificial intelligence; Artificial neural network; Process (computing); Perceptron; Multilayer perceptron; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004621393,0.001314877,0.0006656722,0.0007051737,0.0003119427,0.0006524567,0.001332125,0.0009851402,0.0007999875],"category_scores_gemma":[0.00712266,0.0005259991,0.0008364401,0.0004412167,0.0004473533,0.0008687948,0.0006169275,0.001303867,0.000244868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001093099,"about_ca_system_score_gemma":0.001194029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02525847,"about_ca_topic_score_gemma":0.01961196,"domain_scores_codex":[0.9990232,0.0004328217,0.00009298244,0.0002228596,0.0001411949,0.00008689253],"domain_scores_gemma":[0.9967204,0.002276189,0.0002334515,0.0001976695,0.0005135059,0.00005871134],"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":[0.00007434658,0.00007151368,0.002143049,0.00004208493,0.00009639144,0.00002587429,0.00002316322,0.976159,0.002093434,0.0003722102,0.0001893738,0.01870951],"study_design_scores_gemma":[0.000002173704,0.00002341861,0.0002574653,0.000001606744,0.000003622017,0.000002026546,0.000001534868,0.9989325,0.0006298983,0.0001016414,0.00004118137,0.000002948363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4793641,0.0009103151,0.5150082,0.0001871187,0.00009119196,0.0001594019,0.0003736892,0.002110081,0.001795875],"genre_scores_gemma":[0.9374565,0.0001005545,0.06067327,0.0000571055,0.00001337504,0.000137654,0.00051083,0.00007528745,0.0009753628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02525847,"threshold_uncertainty_score":0.05022293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03068634901375678,"score_gpt":0.2796954021824327,"score_spread":0.2490090531686759,"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."}}