{"id":"W2172078667","doi":"10.1109/tgrs.2006.885046","title":"Filament Preserving Model (FPM) Segmentation Applied to SAR Sea-Ice Imagery","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency","keywords":"Synthetic aperture radar; Segmentation; Markov random field; Artificial intelligence; Computer science; Image segmentation; Context (archaeology); Sea ice; Radar imaging; Geology; Remote sensing; Pattern recognition (psychology); Computer vision; Radar","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002181837,0.0001543081,0.0001297072,0.000133194,0.0006957113,0.0001151493,0.00009662934,0.00005253553,0.00003981062],"category_scores_gemma":[0.000002652018,0.0001354282,0.00004070796,0.000306949,0.0001146226,0.0002430907,0.000001633894,0.0001533747,0.00003827578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001761584,"about_ca_system_score_gemma":0.00005114696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004892189,"about_ca_topic_score_gemma":0.00102936,"domain_scores_codex":[0.9987242,0.0000251596,0.0002001756,0.0003799023,0.0003176703,0.0003528473],"domain_scores_gemma":[0.9995471,0.00008224804,0.00005045707,0.0001603593,0.00003378495,0.0001260623],"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":[0.00004057839,0.00001645187,0.00005109274,0.00001932729,0.000005569359,0.000007810986,0.0004828506,0.3712441,0.004804166,0.000004973697,0.00005953807,0.6232635],"study_design_scores_gemma":[0.0001484258,0.00004544673,0.002507616,0.00003913105,0.00002061797,0.00002687691,0.0004756513,0.9933817,0.002507446,0.0005617675,0.00008982114,0.0001955286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2578441,0.000006647394,0.7396473,0.0004216777,0.0001988913,0.0001648991,0.0000241359,0.00004291907,0.001649396],"genre_scores_gemma":[0.8336717,0.0000257637,0.164749,0.0007662201,0.00004309263,4.636092e-8,0.000009598833,0.000004738527,0.0007298707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.623068,"threshold_uncertainty_score":0.739556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01144879411424634,"score_gpt":0.2133418742631451,"score_spread":0.2018930801488988,"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."}}