{"id":"W2791829678","doi":"10.1109/jstars.2018.2806640","title":"Semiautomated Segmentation of Sentinel-1 SAR Imagery for Mapping Sea Ice in Labrador Coast","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Synthetic aperture radar; Workflow; Segmentation; Remote sensing; Geology; Image segmentation; Computer science; Sea ice; Satellite imagery; Artificial intelligence; Radar imaging; Radar; Oceanography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004600163,0.0001015382,0.0002323698,0.0002250232,0.0001071118,0.00002805554,0.00005813337,0.00007780607,0.00001006211],"category_scores_gemma":[0.00008275249,0.00009247327,0.00002964797,0.0006128263,0.00008295603,0.0001320113,0.000005423254,0.0001875756,5.867044e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001226022,"about_ca_system_score_gemma":0.0001256142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005046304,"about_ca_topic_score_gemma":0.001647566,"domain_scores_codex":[0.998917,0.00003938917,0.0005552592,0.0001195865,0.00017196,0.0001967628],"domain_scores_gemma":[0.9990299,0.0001709619,0.000334816,0.00006563921,0.0003533539,0.00004526535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000287491,0.0000572621,0.2518592,0.0003329049,0.00009533633,0.00003007184,0.004011004,0.00647091,0.05665658,0.00006487592,0.0001332814,0.6800011],"study_design_scores_gemma":[0.0009445998,0.00006436433,0.5287138,0.0002173183,0.00002136385,0.00006343671,0.0009248921,0.4654614,0.002506446,0.000696791,0.0002536566,0.000131931],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9704242,0.00002385124,0.02876273,0.0002725305,0.0001866268,0.0001554942,0.0000103068,0.000008557578,0.0001557364],"genre_scores_gemma":[0.8656753,0.00008335659,0.1338314,0.0001390309,0.0002112677,1.497235e-8,0.00002511744,0.000004561748,0.0000299388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6798692,"threshold_uncertainty_score":0.3770951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119549761048045,"score_gpt":0.2330528466136453,"score_spread":0.2118573490031648,"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."}}