{"id":"W3011767151","doi":"10.1016/j.scitotenv.2020.137964","title":"Using grey clustering to evaluate nitrogen pollution in estuaries with limited data","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Grey System Theory Applications","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"European Commission; National Water Commission; United States Agency for International Development","keywords":"Pollution; Cluster analysis; Environmental science; Water quality; Nutrient pollution; Computer science; Environmental resource management; Water resource management; Data mining; Ecology; Machine learning","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":[0.005087375,0.0001109188,0.000164322,0.00008820876,0.0003784642,0.0001229769,0.003600453,0.00001750609,0.00005076446],"category_scores_gemma":[0.0009601171,0.00005397952,0.00003018344,0.001558347,0.00099109,0.0004167583,0.002590704,0.0000908135,0.0001292384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202863,"about_ca_system_score_gemma":0.0001028841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000827282,"about_ca_topic_score_gemma":0.00001028319,"domain_scores_codex":[0.996693,0.0002585595,0.0004049004,0.0005406748,0.00185357,0.0002492943],"domain_scores_gemma":[0.9975273,0.000151578,0.0002428748,0.001936501,0.00003345063,0.0001082848],"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":[0.0000612569,0.00002706251,0.0005061029,0.000002105625,0.000005943931,4.134087e-7,0.002736444,0.8974346,0.097548,0.0005461299,0.00003444379,0.001097497],"study_design_scores_gemma":[0.0004709552,0.0001670981,0.05873851,0.00006553959,0.00005467844,0.00003883082,0.005202043,0.9026291,0.02416648,0.007959769,0.0002225398,0.0002845067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815193,0.00002206195,0.006548072,0.01094386,0.00005710229,0.0006461861,0.00002291402,0.000008466729,0.0002320056],"genre_scores_gemma":[0.9973693,7.2173e-7,0.002387866,0.0001531316,0.00002013551,0.00001152685,4.45406e-7,0.000006502245,0.00005040425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07338152,"threshold_uncertainty_score":0.6690597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1953649146470507,"score_gpt":0.3524820746439333,"score_spread":0.1571171599968826,"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."}}