{"id":"W2319040573","doi":"10.1109/tgrs.2016.2543660","title":"Sea Ice Concentration Estimation During Melt From Dual-Pol SAR Scenes Using Deep Convolutional Neural Networks: A Case Study","year":2016,"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":220,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Synthetic aperture radar; Sea ice; Geology; Remote sensing; Segmentation; Sea ice concentration; Feature (linguistics); Artificial intelligence; Arctic ice pack; Satellite; Sea ice thickness; Computer science; Climatology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000202273,0.0001798434,0.0001598285,0.00007727574,0.001275123,0.0001029439,0.00005588126,0.00006978786,0.00004682921],"category_scores_gemma":[0.00001238604,0.0001318927,0.00004630267,0.0002537743,0.0002911292,0.0006104451,0.000001528431,0.0001471657,0.00000667911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003117458,"about_ca_system_score_gemma":0.00005355708,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.017299,"about_ca_topic_score_gemma":0.005418913,"domain_scores_codex":[0.9985517,0.0001216952,0.0002610422,0.0004167458,0.0002958788,0.0003529704],"domain_scores_gemma":[0.9992935,0.0002456766,0.0001010259,0.0001484568,0.00006454259,0.0001467707],"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":[0.0000935621,0.00004061393,0.003577422,0.000008236703,0.00003093081,0.0005806328,0.001277574,0.1960671,0.0008911703,7.691803e-7,3.877647e-7,0.7974316],"study_design_scores_gemma":[0.0005201497,0.00009124948,0.01018092,0.00006645869,0.0000626257,0.001779746,0.001906815,0.9849332,0.0002134212,0.00004785777,0.000001098119,0.0001964686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5412014,0.00001719529,0.4581326,0.00007439427,0.0003937442,0.0001284788,0.0000174399,0.00002911475,0.000005694652],"genre_scores_gemma":[0.9842393,0.00004290374,0.01550013,0.00008215352,0.0001016947,3.214909e-8,0.000005123972,0.000005322864,0.00002330757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7972351,"threshold_uncertainty_score":0.9892449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01573743801682053,"score_gpt":0.2309925904803006,"score_spread":0.21525515246348,"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."}}