{"id":"W3158152196","doi":"10.1109/jstars.2021.3076109","title":"Sea Ice Concentration Estimation: Using Passive Microwave and SAR Data With a U-Net and Curriculum Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and 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":"Environment and Climate Change Canada; Universität Bremen; Marine Environmental Observation Prediction and Response Network","keywords":"Synthetic aperture radar; Computer science; Remote sensing; Microwave; Sea ice concentration; Sea ice; Convolutional neural network; Artificial neural network; Artificial intelligence; Sea ice thickness; Geology; Cryosphere; Telecommunications; 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":[0.0008679728,0.00115563,0.0004454224,0.0005792335,0.0002555599,0.0005810551,0.001184165,0.0008912155,0.001512394],"category_scores_gemma":[0.001931733,0.0003171031,0.0004566488,0.000506093,0.000356764,0.001315095,0.0009322424,0.00100311,0.0005752704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006417054,"about_ca_system_score_gemma":0.0008311737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01189509,"about_ca_topic_score_gemma":0.01132681,"domain_scores_codex":[0.9997638,0.00003505132,0.00001201151,0.00009454511,0.00004012197,0.00005441808],"domain_scores_gemma":[0.9995784,0.0001130563,0.00005736111,0.00005496959,0.0001514877,0.00004479292],"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":[0.0006030184,0.0006537517,0.01282231,0.0001409513,0.0001481881,0.0002040328,0.000108081,0.6055585,0.02043078,0.001485043,0.004814098,0.3530313],"study_design_scores_gemma":[0.00001316052,0.000107808,0.001463976,0.00001271075,0.00001223302,0.00001576152,0.00002391052,0.9879892,0.009211113,0.0005105946,0.0006309813,0.000008561457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6621848,0.0006679121,0.3205197,0.000610158,0.0002702999,0.0002264784,0.0006671437,0.006448982,0.008404547],"genre_scores_gemma":[0.8631942,0.0001764303,0.1295175,0.0002744481,0.00004598778,0.0001156181,0.001681359,0.0001501075,0.004844265],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01189509,"threshold_uncertainty_score":0.02365172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02166016948528849,"score_gpt":0.2267614432043732,"score_spread":0.2051012737190847,"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."}}