{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001924851,0.00009900484,0.0001755531,0.00004736197,0.0002453789,0.0001083993,0.00003996999,0.00006038317,0.00000400586],"category_scores_gemma":[0.00008281902,0.00008291784,0.000007519811,0.0003146164,0.00008656411,0.0002309,0.00001372553,0.0003124958,1.168701e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000779231,"about_ca_system_score_gemma":0.0001926517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003006242,"about_ca_topic_score_gemma":0.0009557249,"domain_scores_codex":[0.9991964,0.00005534283,0.0002644226,0.0001708863,0.0001647716,0.0001481914],"domain_scores_gemma":[0.9993023,0.0001069861,0.000204272,0.00008201283,0.0002354976,0.00006888301],"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":[0.00006307962,0.00001979157,0.1642039,0.0001201436,0.0000985529,0.0001905934,0.001658503,0.04499355,0.005522902,0.0001133982,0.00001401479,0.7830015],"study_design_scores_gemma":[0.0004316405,0.00004237332,0.08116354,0.0001474199,0.00005042713,0.0008497167,0.0008988251,0.9155689,0.000153724,0.0003055136,0.0002778124,0.0001100844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960145,0.0002207135,0.03900154,0.0003829305,0.00006777096,0.0000694685,0.000006837434,0.000005340515,0.0001004347],"genre_scores_gemma":[0.76112,0.0005063965,0.2381177,0.00009496333,0.00009713648,1.917083e-9,0.00005039894,0.000003038071,0.00001037237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8705754,"threshold_uncertainty_score":0.3381291,"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."}}