{"id":"W2971752124","doi":"10.1109/tgrs.2019.2933251","title":"Novel Spectra-Derived Features for Empirical Retrieval of Water Quality Parameters: Demonstrations for OLI, MSI, and OLCI Sensors","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Environment and Climate Change Canada; European Space Agency","keywords":"Colored dissolved organic matter; Remote sensing; Satellite; Environmental science; Feature (linguistics); Radiative transfer; Computer science; Atmospheric correction; Satellite imagery; Water quality; Atmospheric radiative transfer codes; Feature vector; Empirical modelling; Artificial intelligence; Phytoplankton; Geology; Physics; Chemistry; Optics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003802382,0.0001341773,0.0002305533,0.0001016962,0.0003110776,0.00007540043,0.00005729565,0.00008735539,0.00001560287],"category_scores_gemma":[0.00001610627,0.00009529519,0.00008819332,0.000135433,0.0001669542,0.0001710574,9.44734e-7,0.0001086769,0.000002298208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003985784,"about_ca_system_score_gemma":0.00004022862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001996709,"about_ca_topic_score_gemma":0.002486255,"domain_scores_codex":[0.9988955,0.00003660113,0.0002612571,0.0003511468,0.0001692577,0.0002862154],"domain_scores_gemma":[0.9992945,0.0003321425,0.0000649545,0.0001416964,0.00006562232,0.0001010898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001514379,0.0001158124,0.00106053,0.000618803,0.0001177471,0.000004009898,0.002901242,0.006896851,0.2275682,0.00003078918,0.00004167102,0.7591299],"study_design_scores_gemma":[0.002121158,0.001421334,0.03187414,0.0001756348,0.0001250476,0.0002963931,0.002537821,0.7198817,0.2391457,0.001131437,0.0005572561,0.0007324527],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.704128,0.0000140766,0.294588,0.0002988045,0.0002889091,0.00037081,0.0001116753,0.00001572421,0.0001840961],"genre_scores_gemma":[0.9590072,0.00002508344,0.04039828,0.0001111628,0.0000264916,8.271313e-8,0.000008997543,0.000003866105,0.0004188041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7583975,"threshold_uncertainty_score":0.3886025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03267326755958314,"score_gpt":0.2675870278951301,"score_spread":0.2349137603355469,"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."}}