{"id":"W3175980437","doi":"10.3390/rs13132460","title":"RUF: Effective Sea Ice Floe Segmentation Using End-to-End RES-UNET-CRF with Dual Loss","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"ArcticNet","keywords":"Segmentation; Sea ice; Computer science; Artificial intelligence; Synthetic aperture radar; Geology; Conditional random field; Sea ice concentration; Arctic ice pack; Remote sensing; Sea ice thickness; Climatology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006464312,0.00138222,0.001021475,0.0008611222,0.0005679441,0.0006559623,0.001950276,0.001140648,0.004154373],"category_scores_gemma":[0.001164913,0.0006171986,0.001072073,0.0005779722,0.0004156243,0.001344568,0.0008866074,0.001397047,0.001977002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009797921,"about_ca_system_score_gemma":0.001673777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02563149,"about_ca_topic_score_gemma":0.03460761,"domain_scores_codex":[0.9997489,0.00002409971,0.0000102956,0.0001036165,0.00005494244,0.00005817346],"domain_scores_gemma":[0.9996921,0.00008584383,0.00003566096,0.00007655888,0.00007748831,0.00003245344],"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":[0.0005261572,0.0003186208,0.002601973,0.0001502261,0.0001804211,0.0003366666,0.0001142922,0.3753734,0.0140562,0.002390489,0.03130956,0.572642],"study_design_scores_gemma":[0.00001934983,0.00003817593,0.0004182524,0.000007514842,0.00001097509,0.00005474236,0.00001072533,0.9935921,0.003388169,0.0009517755,0.001497069,0.00001118705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07872481,0.001104683,0.8676811,0.0005792508,0.0003191568,0.0003124061,0.00283047,0.04311597,0.005332094],"genre_scores_gemma":[0.4998205,0.0003873499,0.4732341,0.0006081747,0.0001534828,0.000304112,0.01224996,0.001815664,0.01142676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02563149,"threshold_uncertainty_score":0.05096459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01086140988049485,"score_gpt":0.2294899465140868,"score_spread":0.2186285366335919,"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."}}