{"id":"W4406939387","doi":"10.2139/ssrn.5117066","title":"Evaluation of Deep Learning Methods for Forecasting Turbidity in River Networks Using Sentinel-2 Remote Sensing Data","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Turbidity; Remote sensing; Deep learning; Computer science; Artificial intelligence; Environmental science; Meteorology; Geology; Geography; Oceanography","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":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.04471084,0.0003486569,0.000579853,0.0001778347,0.0003263124,0.00006648903,0.0008410141,0.0004268801,0.0000355218],"category_scores_gemma":[0.004735972,0.00034438,0.0001851128,0.0004156697,0.0001704115,0.0001872101,0.002098516,0.004967398,9.688863e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003879345,"about_ca_system_score_gemma":0.0009353008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001098054,"about_ca_topic_score_gemma":0.001233244,"domain_scores_codex":[0.9932014,0.002255932,0.0009045511,0.0008444857,0.000729615,0.002064064],"domain_scores_gemma":[0.9975574,0.00055236,0.001077801,0.0005819204,0.0001580486,0.00007247805],"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":[0.00002229009,0.00001120902,0.0005429738,0.00001443967,0.00005876591,8.297596e-7,0.00008247493,0.5647572,0.0001628944,0.00000766438,0.000001907739,0.4343373],"study_design_scores_gemma":[0.0005058397,0.00004243664,0.0002033483,0.0002895212,0.0004533564,0.0001065754,0.00004983655,0.894375,0.00003573257,0.1036305,0.00005300963,0.0002548592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3403366,0.0008504743,0.6577824,0.00004220439,0.0003291251,0.0003815487,0.000002612361,0.00002088251,0.0002542024],"genre_scores_gemma":[0.7653046,0.0002508683,0.2340086,0.00002649644,0.0002615922,9.849567e-7,0.00005718971,0.00003532954,0.0000542873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4340825,"threshold_uncertainty_score":0.9999446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1322923738693999,"score_gpt":0.3932949073657629,"score_spread":0.261002533496363,"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."}}