{"id":"W2142026865","doi":"10.1109/tgrs.2004.839589","title":"Unsupervised segmentation of synthetic aperture Radar sea ice imagery using a novel Markov random field model","year":2005,"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":199,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency","keywords":"Markov random field; Synthetic aperture radar; Computer science; Artificial intelligence; Image segmentation; Segmentation; Sea ice; Cluster analysis; Pattern recognition (psychology); Radar imaging; Mixture model; Remote sensing; Hidden Markov model; Computer vision; Radar; Geology","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":[0.0002192743,0.0001500236,0.0001841473,0.0001259447,0.0004288736,0.00004246157,0.00008294931,0.00008000692,0.00005429018],"category_scores_gemma":[0.00001485512,0.0001237157,0.00007639563,0.0002475723,0.0001870047,0.0003382842,9.998547e-7,0.0001878584,0.000004039639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001158424,"about_ca_system_score_gemma":0.00008135143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001855839,"about_ca_topic_score_gemma":0.0004454335,"domain_scores_codex":[0.9989311,0.00003807105,0.0002374188,0.0002872701,0.0002452469,0.0002608582],"domain_scores_gemma":[0.9993056,0.0003268723,0.00007648746,0.000147481,0.00004692646,0.00009661289],"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":[0.0001781326,0.00003027368,0.00003804604,0.00003959591,0.00001597328,0.000003060484,0.0007476007,0.08457169,0.01951206,0.000001074547,0.000002954008,0.8948596],"study_design_scores_gemma":[0.0005264197,0.0000529161,0.0001023511,0.00009720475,0.00004926764,0.0001097018,0.0006214137,0.9945011,0.003711838,0.00005040451,0.0000226522,0.0001546937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2668914,0.00002238298,0.7320153,0.000603196,0.0001382873,0.0001082756,0.00003110317,0.00001807272,0.0001720249],"genre_scores_gemma":[0.7468848,0.0001046166,0.2521258,0.0007628285,0.00002449605,1.548624e-8,0.000003259614,0.000003889021,0.00009029935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9099295,"threshold_uncertainty_score":0.5044979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393163724121824,"score_gpt":0.2220112650174141,"score_spread":0.2080796277761959,"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."}}