{"id":"W4367609892","doi":"10.1016/j.chemosphere.2023.138831","title":"Quantifying uncertainty of marine water quality forecasts for environmental management using a dynamic multi-factor analysis and multi-resolution ensemble approach","year":2023,"lang":"en","type":"article","venue":"Chemosphere","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Water quality; Interpretability; Computer science; Environmental science; Data mining; Uncertainty analysis; Sampling (signal processing); Machine learning; 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":[0.0004686624,0.0002163048,0.0003444775,0.00003574197,0.0001936249,0.00002344198,0.0001648976,0.0001147395,0.000301913],"category_scores_gemma":[0.00002658272,0.0001702728,0.0001658193,0.0003738116,0.0002252151,0.00009822341,0.0005469644,0.00009168666,0.00002552735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002580884,"about_ca_system_score_gemma":0.000002082116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004142202,"about_ca_topic_score_gemma":0.0002656891,"domain_scores_codex":[0.9982768,0.00006089493,0.0003719902,0.0005817936,0.0002495452,0.0004589885],"domain_scores_gemma":[0.9994327,0.00004863005,0.0001299113,0.0002914013,0.000005045114,0.00009226357],"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":[0.0001396819,0.0004736808,0.1796609,0.000297583,0.0004059481,0.000005462898,0.0007723877,0.6309183,0.135088,0.000006031629,0.00002427576,0.05220788],"study_design_scores_gemma":[0.0007164541,0.0000295398,0.09248438,0.000007875391,0.0001604296,0.000001601198,0.0001409284,0.9031743,0.002984546,0.00002983536,0.00006591343,0.0002041585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9186023,0.00001030521,0.08066199,0.00001998774,0.00004717232,0.0004358138,0.00003790886,0.00006762102,0.0001168323],"genre_scores_gemma":[0.8599221,0.00000925399,0.1392596,0.00001789174,0.00000876248,0.00002715765,0.0001607827,0.00002038669,0.0005740487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2722561,"threshold_uncertainty_score":0.6943525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08836164055998447,"score_gpt":0.3164523676236118,"score_spread":0.2280907270636274,"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."}}