{"id":"W2020534029","doi":"10.1109/igarss.2014.6947354","title":"Automatic feature learning of SAR images for sea ice concentration estimation using feed-forward neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial neural network; Preprocessor; Computer science; Artificial intelligence; Sea ice; Feature (linguistics); Feedforward neural network; Synthetic aperture radar; Pattern recognition (psychology); Feature extraction; Image (mathematics); Deep learning; Computer vision; Geology; Oceanography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004359754,0.0008148798,0.0003990326,0.0006091023,0.0002202037,0.0004189191,0.0004496957,0.000460393,0.0009343046],"category_scores_gemma":[0.001257535,0.0003188371,0.0004013341,0.0005864107,0.0001534977,0.0006288847,0.000270635,0.0005586766,0.0002770625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003600569,"about_ca_system_score_gemma":0.0004009333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004617096,"about_ca_topic_score_gemma":0.005432657,"domain_scores_codex":[0.9998323,0.00002738586,0.00001091595,0.00004947499,0.00005416659,0.00002581145],"domain_scores_gemma":[0.9996182,0.0001431652,0.00003853474,0.00003402839,0.000154486,0.00001172936],"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":[0.0003245552,0.0002748531,0.004060995,0.0001152264,0.00008054108,0.0001343397,0.00006514384,0.2668504,0.08330077,0.0007554206,0.002437609,0.6416001],"study_design_scores_gemma":[0.000009122489,0.00003204203,0.001663372,0.000003613371,0.00001195336,0.00001678564,0.000006976242,0.9801431,0.01759266,0.0002567824,0.0002565724,0.000006876618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1563296,0.0002580938,0.8385875,0.0001070573,0.00007767383,0.00008438002,0.0001883815,0.002707304,0.001660067],"genre_scores_gemma":[0.8043795,0.0001483395,0.1929725,0.00005802862,0.00003124909,0.0001328862,0.0005495155,0.0000721773,0.0016557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004617096,"threshold_uncertainty_score":0.009180427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00848077135575659,"score_gpt":0.224236411243427,"score_spread":0.2157556398876704,"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."}}