{"id":"W7099590015","doi":"","title":"Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel Markov random field models","year":2005,"lang":"en","type":"article","venue":"","topic":"Water Resources and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Markov random field; Synthetic aperture radar; Segmentation; Sea ice; Image segmentation; Pattern recognition (psychology); Radar imaging; Mixture model; Bayesian probability","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333293,0.0004777532,0.0007548849,0.001187119,0.0003222838,0.0007800511,0.001188534,0.0007759243,0.0006374846],"category_scores_gemma":[0.002286455,0.0004881085,0.001146244,0.0006673778,0.0007817839,0.001014799,0.0004301424,0.0007075115,0.0002941298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001250547,"about_ca_system_score_gemma":0.0007981395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007883712,"about_ca_topic_score_gemma":0.007580487,"domain_scores_codex":[0.9994826,0.0001782344,0.0000254743,0.0001604095,0.00009463144,0.00005864077],"domain_scores_gemma":[0.9987711,0.0007695138,0.0001744529,0.00007970555,0.0001677358,0.00003744462],"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":[0.0001126181,0.00006804823,0.00245173,0.00005026001,0.00007184297,0.00007342753,0.0001463571,0.923283,0.00624256,0.01366376,0.0007539773,0.05308239],"study_design_scores_gemma":[0.000002545786,0.000005591357,0.0002597481,0.000002571517,0.000003330696,0.00001249343,0.000003731423,0.9973868,0.0004687757,0.001741399,0.0001091658,0.000003999741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02716612,0.00007245973,0.9721035,0.00007891365,0.000009214206,0.00003216246,0.0000492482,0.0001674893,0.0003208579],"genre_scores_gemma":[0.6402955,0.0002132113,0.3564369,0.0001046323,0.00006233954,0.0002072386,0.0005538894,0.0001045491,0.002021668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007883712,"threshold_uncertainty_score":0.0156756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02676218042210113,"score_gpt":0.2732926070971295,"score_spread":0.2465304266750284,"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."}}