{"id":"W2944550430","doi":"10.1016/j.jhydrol.2019.05.016","title":"Towards a time and cost effective approach to water quality index class prediction","year":2019,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":131,"is_retracted":false,"has_abstract":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Institut Pengurusan dan Pemantauan Penyelidikan, Universiti Malaya; Universiti Kebangsaan Malaysia; Universiti Malaya","keywords":"Water quality; Biochemical oxygen demand; Decision tree; Index (typography); Quality (philosophy); Chemical oxygen demand; Environmental science; Computer science; Suspended solids; Hydrology (agriculture); Data mining; Environmental engineering; Engineering; 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":[0.001316429,0.0001127678,0.0003029357,0.00006087673,0.00004896344,0.00001543356,0.0001597529,0.0001464082,0.0004782221],"category_scores_gemma":[0.0001038491,0.00007065579,0.00005787224,0.00008780698,0.0001300794,0.0001307762,0.0001854269,0.0003121551,0.0004797519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001354321,"about_ca_system_score_gemma":0.000006168386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147375,"about_ca_topic_score_gemma":0.000003032709,"domain_scores_codex":[0.9986641,0.0002741383,0.0003221334,0.0002179094,0.0002507507,0.000270933],"domain_scores_gemma":[0.9994962,0.00007389975,0.0001342439,0.0001248001,0.00001628548,0.0001545649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001600547,0.0005873894,0.284494,0.0000289625,0.0001446432,0.00003848992,0.002408209,0.4770592,0.2079786,0.00005950475,0.00248255,0.02311789],"study_design_scores_gemma":[0.003875551,0.006686315,0.698904,0.00003332689,0.0000978266,0.002007774,0.00002549175,0.2287918,0.005970051,0.003174806,0.04989104,0.0005420001],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863014,0.000006070487,0.0007883786,0.0007873067,0.0001688879,0.0003666118,0.000003079501,0.00001448266,0.01156376],"genre_scores_gemma":[0.9983937,0.000001135543,0.0005262767,0.0007640891,0.00006790633,0.000007204639,0.000001666585,0.000008584373,0.000229447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.41441,"threshold_uncertainty_score":0.6166401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154889388782263,"score_gpt":0.2465894769892087,"score_spread":0.2350405831013861,"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."}}