{"id":"W4407181252","doi":"10.3389/frsen.2025.1488565","title":"Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation","year":2025,"lang":"en","type":"article","venue":"Frontiers in Remote Sensing","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences; Universitetet i Bergen; Universitat de València; Chinese Academy of Sciences; NASA Headquarters; Deutsches Zentrum für Luft- und Raumfahrt; University of Stirling; University of Minnesota; Commonwealth Scientific and Industrial Research Organisation; Wake Forest University; National Aeronautics and Space Administration","keywords":"Ocean color; Oceanography; Environmental science; Geology; Engineering; Satellite","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":[0.0003342762,0.0001155034,0.0002032669,0.000108443,0.0001473932,0.00008805029,0.00002994032,0.0001079818,8.582904e-7],"category_scores_gemma":[0.000114155,0.0001067369,0.00001708643,0.0001585412,0.00004286276,0.0001675368,0.00001727932,0.0001310891,9.738996e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002337056,"about_ca_system_score_gemma":0.00003384074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002053389,"about_ca_topic_score_gemma":0.00188517,"domain_scores_codex":[0.9991375,0.0000703325,0.0002180859,0.0002983266,0.00007499337,0.0002008019],"domain_scores_gemma":[0.999679,0.00007394805,0.00007647233,0.00008355504,0.0000440109,0.00004299107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001096789,0.000002114554,0.5592947,0.0001036934,0.00001587551,0.000006792656,0.0001373168,0.0004146774,0.00004020468,0.000004007985,0.003758002,0.4361129],"study_design_scores_gemma":[0.0007169864,0.00006576844,0.0546384,0.0001451605,0.00004382936,0.00004898075,0.0006124454,0.9386345,0.000286974,0.001194825,0.003381813,0.0002303446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8992811,0.0003880295,0.09744957,0.0004282595,0.001499797,0.0003615761,0.000005968648,0.00002333452,0.0005623492],"genre_scores_gemma":[0.9487069,0.00004073699,0.05073104,0.00006634534,0.0001387395,2.616381e-8,0.00006434935,0.000003131875,0.0002486857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9382198,"threshold_uncertainty_score":0.4352604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007728692575981641,"score_gpt":0.193611954704785,"score_spread":0.1858832621288033,"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."}}