{"id":"W3141345383","doi":"","title":"Land Cover Classification of RADARSAT-2 SAR Data Using Convolutional Neural Network","year":2016,"lang":"zh","type":"article","venue":"武汉大学学报：自然科学英文版","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Softmax function; Synthetic aperture radar; Computer science; Pattern recognition (psychology); Convolutional neural network; Artificial intelligence; Feature (linguistics); Land cover; Feature extraction; Backpropagation; Remote sensing; Contextual image classification; Deep learning; Artificial neural network; Geology; Image (mathematics); Land use; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004865567,0.000390569,0.0004919248,0.0001110567,0.0001768479,0.0000452075,0.0008172034,0.0003419531,0.0005615915],"category_scores_gemma":[0.00009998702,0.0003202166,0.000124055,0.0003666577,0.0002930023,0.0003597368,0.0002817807,0.0002356661,0.0001012224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002172156,"about_ca_system_score_gemma":0.0001445974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002490057,"about_ca_topic_score_gemma":0.00001487916,"domain_scores_codex":[0.9975187,0.00009930145,0.000752801,0.000643212,0.0004430216,0.0005429592],"domain_scores_gemma":[0.9972083,0.0004442384,0.0003011668,0.001752214,0.0001488374,0.0001452505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001334952,0.0004048644,0.0390279,0.0003531026,0.000659336,0.00001073765,0.0002094322,0.0009787487,0.02441665,0.1262503,0.0433073,0.7642481],"study_design_scores_gemma":[0.0009118173,0.00006179327,0.01822342,0.0004777757,0.0002650297,0.00005033396,0.0000237948,0.20663,0.001173605,0.004834251,0.7666621,0.0006861049],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03508599,0.005831978,0.9403594,0.001914701,0.001060704,0.001005117,0.001659562,0.0004864083,0.01259614],"genre_scores_gemma":[0.8321946,0.0006554013,0.1654672,0.0000834047,0.0009633719,0.000003705095,0.0002375773,0.00009431046,0.0003004116],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7971086,"threshold_uncertainty_score":0.999925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04894612145808064,"score_gpt":0.2722263767880394,"score_spread":0.2232802553299588,"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."}}