{"id":"W4412870374","doi":"10.1080/07038992.2025.2533460","title":"Automated Semantic Segmentation of Arctic Surface Water Features with Very-High Resolution Satellite X-Band Radar Imagery and U-Net Deep Learning","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Remote sensing; Satellite; Segmentation; Satellite imagery; Arctic; Radar; Deep learning; Geography; Artificial intelligence; Cartography; Computer science; Geology; Telecommunications; Physics; Oceanography; Astronomy","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":[0.0005313088,0.0008356837,0.0003411288,0.000720972,0.0003256826,0.0008023197,0.0008931525,0.0007171807,0.001144822],"category_scores_gemma":[0.000890999,0.000279841,0.0004450593,0.0005914248,0.0004322705,0.0009494486,0.0006787504,0.0006202866,0.0005104888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006892101,"about_ca_system_score_gemma":0.0007841834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01413633,"about_ca_topic_score_gemma":0.02170107,"domain_scores_codex":[0.9998233,0.00003161154,0.000007039825,0.00006196154,0.00004092112,0.00003525499],"domain_scores_gemma":[0.9997987,0.00006216504,0.00002948136,0.0000325198,0.00005948995,0.0000177217],"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":[0.0004044383,0.0003246422,0.007827682,0.0001661969,0.0001570032,0.0001907796,0.0001816176,0.4074259,0.04053119,0.005940517,0.008224903,0.5286252],"study_design_scores_gemma":[0.000005409467,0.00003697391,0.00119705,0.00000970765,0.00001109275,0.00002377196,0.0000321599,0.9882908,0.007902786,0.001457308,0.001026106,0.000006944211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3033185,0.0009114298,0.678868,0.000641664,0.0001708239,0.0001397484,0.0008844237,0.00561723,0.009448182],"genre_scores_gemma":[0.7139214,0.0002696871,0.277622,0.0003170129,0.00005069914,0.00008921608,0.001890422,0.0002141393,0.005625526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01413633,"threshold_uncertainty_score":0.02810806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004173725211850108,"score_gpt":0.185395164803646,"score_spread":0.1812214395917959,"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."}}