{"id":"W2912226897","doi":"10.1109/tgrs.2019.2892723","title":"Estimating Sea Ice Concentration From SAR: Training Convolutional Neural Networks With Passive Microwave Data","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Marine Environmental Observation Prediction and Response Network","keywords":"Synthetic aperture radar; Convolutional neural network; Computer science; Remote sensing; Microwave; Artificial intelligence; Microwave imaging; Data set; Artificial neural network; Deep learning; Test set; Test data; Sea ice; Radar; Pattern recognition (psychology); Meteorology; Geology; Telecommunications; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000171282,0.0001598927,0.0001633504,0.00003849436,0.0006051,0.0001191859,0.0001522181,0.00006883316,0.00006082244],"category_scores_gemma":[0.000006814256,0.0001266261,0.00002541738,0.0002072335,0.0003017696,0.0005381927,0.000002047213,0.0002940175,0.00001415608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001041371,"about_ca_system_score_gemma":0.00009783801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00399101,"about_ca_topic_score_gemma":0.001568692,"domain_scores_codex":[0.9986482,0.00005601686,0.0001833603,0.0004946791,0.0002694804,0.0003483258],"domain_scores_gemma":[0.9992068,0.0002807853,0.00009973435,0.0002473425,0.00004599418,0.0001193169],"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":[0.00005660932,0.000005456335,0.0008184405,0.000006448371,0.00001818195,0.00001507199,0.0006316358,0.189746,0.0001423042,0.000001523119,0.0000036064,0.8085547],"study_design_scores_gemma":[0.0003028438,0.00009428515,0.005340517,0.00009619464,0.000036256,0.0001287504,0.001009489,0.9926786,0.00004211794,0.00005967918,0.0000242309,0.0001870467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.406181,0.00001548821,0.5927423,0.0001703514,0.0005565286,0.00009991605,0.00007567058,0.00002441597,0.00013435],"genre_scores_gemma":[0.8750122,0.00001984308,0.1243188,0.0003810225,0.00009896544,9.718928e-9,0.0001154488,0.000004400925,0.0000493472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8083677,"threshold_uncertainty_score":0.6033239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191424714841998,"score_gpt":0.2172587548141061,"score_spread":0.1981162833299064,"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."}}