{"id":"W4403217079","doi":"10.2139/ssrn.4980387","title":"Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel-2 Satellite Remote Sensing Data: A Generalizability Analysis","year":2024,"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 Guelph; University of Waterloo","funders":"","keywords":"Generalizability theory; Turbidity; Remote sensing; Satellite; Environmental science; Computer science; Geology; Engineering; Oceanography; Mathematics; Statistics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01144584,0.0004629346,0.0006145766,0.0002356756,0.0005131524,0.0003935859,0.0007627931,0.0003029811,0.00003792445],"category_scores_gemma":[0.0004011544,0.0003373881,0.0002537778,0.0008815197,0.0002130443,0.0001523878,0.002895584,0.008758832,0.00001099953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001716259,"about_ca_system_score_gemma":0.0003474322,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009866222,"about_ca_topic_score_gemma":0.01030823,"domain_scores_codex":[0.9941701,0.001153095,0.0007906425,0.001205085,0.0006641967,0.00201684],"domain_scores_gemma":[0.9986572,0.0001394433,0.0003547948,0.0007039701,0.0000219894,0.0001225705],"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":[0.00003117239,0.00003023374,0.01017046,0.00005392491,0.0005176981,0.00008430507,0.001301006,0.9591947,0.00253061,0.00001419437,0.000001732484,0.02607],"study_design_scores_gemma":[0.0001136786,0.00001879676,0.0002084592,0.0001015597,0.0008570033,0.0004094989,0.0001041356,0.925992,0.00001987488,0.07174839,0.00009942881,0.0003272014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9377946,0.005162864,0.05601703,0.0005582461,0.0001318124,0.0001717656,0.000007083798,0.00005409677,0.0001025517],"genre_scores_gemma":[0.988924,0.002575828,0.00797864,0.0001178059,0.0002307428,2.448714e-7,0.0000499908,0.00004197034,0.00008077027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0717342,"threshold_uncertainty_score":0.9999078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05008717008496576,"score_gpt":0.2969469195873025,"score_spread":0.2468597495023367,"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."}}