{"id":"W2169569159","doi":"10.1109/cccrv.2004.1301420","title":"Unsupervised segmentation of synthetic aperture radar sea ice imagery using MRF models","year":2004,"lang":"en","type":"article","venue":"","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov random field; Synthetic aperture radar; Artificial intelligence; Sea ice; Segmentation; Image segmentation; Computer science; Radar imaging; Cluster analysis; Remote sensing; Pattern recognition (psychology); Geology; Computer vision; Radar","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0004946787,0.0005525205,0.0005507505,0.001629418,0.0002267533,0.0006800531,0.0005946012,0.0006031978,0.0003384123],"category_scores_gemma":[0.001081819,0.000405545,0.0007093516,0.0006100025,0.0004761447,0.0007940181,0.0003409298,0.0004271892,0.0003486591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000555713,"about_ca_system_score_gemma":0.0006271091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004423989,"about_ca_topic_score_gemma":0.006133864,"domain_scores_codex":[0.9996985,0.00007487659,0.00001800453,0.00007509763,0.00008327395,0.0000501787],"domain_scores_gemma":[0.9994665,0.000222489,0.0001071067,0.00006865137,0.0001116218,0.00002363874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002342211,0.0001310916,0.004370015,0.0001493901,0.0001016355,0.0002288486,0.0003830708,0.5800713,0.1440231,0.006386633,0.001887985,0.2620328],"study_design_scores_gemma":[0.000006830544,0.00002330026,0.002341469,0.000009721178,0.000009776105,0.00008430137,0.00004229563,0.9774191,0.01643068,0.002484953,0.001132368,0.00001517946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0638772,0.0001789962,0.9344578,0.00005941898,0.00001048406,0.00004665428,0.0001115768,0.0005814363,0.0006763652],"genre_scores_gemma":[0.3961191,0.000370804,0.6006937,0.00005894606,0.00003941722,0.0001110608,0.0009984158,0.0002894036,0.001319165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004423989,"threshold_uncertainty_score":0.008796453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01813454686888614,"score_gpt":0.2143230609814653,"score_spread":0.1961885141125792,"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."}}