{"id":"W2994959657","doi":"10.1080/07038992.2019.1697222","title":"A Novel PolSAR Image Classification Method Based on Optimal Polarimetric Features and Contextual Information","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Polarimetry; Land cover; Computer science; Pattern recognition (psychology); Artificial intelligence; Contextual image classification; Entropy (arrow of time); Synthetic aperture radar; Remote sensing; Speckle noise; Covariance matrix; Pixel; Data mining; Speckle pattern; Geography; Image (mathematics); Land use; Algorithm; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002725521,0.0001121817,0.0001603612,0.0005937556,0.00006257881,0.00009234051,0.00007254568,0.00009997637,0.000008789275],"category_scores_gemma":[0.0001059363,0.000105326,0.0000490587,0.0002398215,0.00002712511,0.0002024457,0.000002835308,0.000254383,0.000005616218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001682099,"about_ca_system_score_gemma":0.0001619946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001611414,"about_ca_topic_score_gemma":0.0002473766,"domain_scores_codex":[0.9993969,0.00001894742,0.0002372748,0.0000676816,0.0001186587,0.00016053],"domain_scores_gemma":[0.9992985,0.000106278,0.0001070802,0.0001503563,0.0001402695,0.0001975821],"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":[0.000006627522,0.000001356463,0.00001045376,0.00001434463,0.00001409274,0.000003575219,0.0001318647,0.00007460941,0.003531696,0.0002330565,0.000436564,0.9955418],"study_design_scores_gemma":[0.0005414294,0.0001027947,0.005218159,0.0001870917,0.00004013075,0.0009527814,0.0004023331,0.710436,0.01016527,0.00008820367,0.2716079,0.0002578303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0116044,0.0001361211,0.9835066,0.0005071156,0.0001152093,0.000135094,0.00001338389,0.00003011915,0.003951999],"genre_scores_gemma":[0.3451662,0.000004930519,0.6546039,0.0001660697,0.00003490825,1.435913e-8,0.000004089423,0.00001180265,0.000008018287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9952839,"threshold_uncertainty_score":0.4295071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009404661758408452,"score_gpt":0.2288453634237607,"score_spread":0.2194407016653522,"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."}}