{"id":"W2106574947","doi":"10.5589/m12-028","title":"Feature extraction of dual-pol SAR imagery for sea ice image segmentation","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Australian Government","keywords":"Synthetic aperture radar; Artificial intelligence; Segmentation; Feature extraction; Computer science; Image segmentation; Computer vision; Feature vector; Remote sensing; Sea ice; Pattern recognition (psychology); Geology; Oceanography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005401114,0.0005147135,0.0005250173,0.001570049,0.0002007552,0.0005285169,0.0003563247,0.000290929,0.0008000946],"category_scores_gemma":[0.001261505,0.0002384862,0.0005026401,0.001327866,0.0001865547,0.0006290972,0.0003514651,0.0003337175,0.0005585816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228263,"about_ca_system_score_gemma":0.0003473067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001041413,"about_ca_topic_score_gemma":0.001509508,"domain_scores_codex":[0.9997535,0.00003698337,0.00002497358,0.00005670514,0.00009444915,0.00003337302],"domain_scores_gemma":[0.9995552,0.0001043894,0.0000473384,0.00006340326,0.0002148571,0.00001491299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002926367,0.0001139529,0.006000861,0.0001970737,0.00005702666,0.0001395107,0.0001550067,0.01961335,0.5416841,0.001166589,0.001379266,0.4292006],"study_design_scores_gemma":[0.00003416307,0.0002432952,0.03802511,0.00002329684,0.0001330622,0.0003312941,0.0001387521,0.4698148,0.4810384,0.001613483,0.008540374,0.00006391602],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1946975,0.0003052839,0.8014231,0.00008967452,0.00004381312,0.0001254925,0.0005749309,0.0014561,0.001284127],"genre_scores_gemma":[0.3728807,0.0002376415,0.6245418,0.00003085737,0.00002129672,0.0001154367,0.001334988,0.000143667,0.0006937578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001570049,"threshold_uncertainty_score":0.002856374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01294914162768733,"score_gpt":0.2341875180843805,"score_spread":0.2212383764566931,"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."}}