{"id":"W2789444861","doi":"10.1109/lgrs.2018.2806189","title":"Adaptive Probability Thresholding in Automated Ice and Open Water Detection From RADARSAT-2 Images","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Canadian Space Agency","keywords":"Thresholding; Remote sensing; Environmental science; Synthetic aperture radar; Fraction (chemistry); Open water; Computer science; Meteorology; Geology; Artificial intelligence; Image (mathematics); Chemistry; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000523561,0.0001375947,0.0001644267,0.00007225467,0.000449965,0.0002158709,0.0001531227,0.00005523346,0.00001651732],"category_scores_gemma":[0.00002743235,0.00008735543,0.00001576546,0.0001691517,0.0007609606,0.0005479929,0.0000515732,0.0001480079,0.00001245859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001244677,"about_ca_system_score_gemma":0.00002057445,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06114713,"about_ca_topic_score_gemma":0.007174605,"domain_scores_codex":[0.998733,0.00008847462,0.0001732232,0.000474165,0.000162282,0.0003688227],"domain_scores_gemma":[0.9996048,0.00009090312,0.00004961884,0.0001414354,0.00002825877,0.00008498361],"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":[0.0001730985,0.000009418327,0.02428428,0.00001794652,0.00001515529,0.00007683718,0.004938037,0.0002827622,0.06814285,8.235745e-7,0.00006382755,0.9019949],"study_design_scores_gemma":[0.0003401235,0.0001100486,0.2203462,0.00008942228,0.00001380223,0.0000720907,0.0005010181,0.770576,0.006224818,0.00128248,0.0001870934,0.0002569554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868106,0.00001162163,0.01081817,0.001525106,0.000400145,0.0001966757,0.000009477662,0.0000576711,0.0001705965],"genre_scores_gemma":[0.9662297,0.00001982191,0.03208736,0.001536862,0.00009242422,1.278639e-8,0.000005729165,0.000003177726,0.00002495712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.901738,"threshold_uncertainty_score":0.9451048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167745403756085,"score_gpt":0.2246019479031547,"score_spread":0.2078274075275462,"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."}}