{"id":"W2948659326","doi":"10.1109/tgrs.2019.2913796","title":"Contextual Classification of Sea-Ice Types Using Compact Polarimetric SAR Data","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Environment Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Synthetic aperture radar; Remote sensing; Polarimetry; Computer science; Sea ice; Artificial intelligence; Segmentation; Contextual image classification; Pattern recognition (psychology); Geology; Geography; Meteorology; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003697972,0.0001137092,0.00015939,0.0001178564,0.0002119995,0.00003103635,0.000184895,0.00007478558,0.0001059755],"category_scores_gemma":[0.000007580894,0.00009193821,0.00002974855,0.0006980976,0.0002582771,0.0003032909,0.000007077548,0.0001845868,0.00007359305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005033542,"about_ca_system_score_gemma":0.00002351626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00656528,"about_ca_topic_score_gemma":0.00006810638,"domain_scores_codex":[0.9988548,0.00006662298,0.0002030607,0.0003880336,0.0002802034,0.0002072613],"domain_scores_gemma":[0.9992781,0.00009080483,0.000107834,0.0004244191,0.00001459265,0.00008419564],"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":[0.00005131503,0.000078897,0.0004169516,0.00002348029,0.0000287681,0.000003519147,0.000419355,0.01470965,0.3749793,0.000006169855,0.00001734243,0.6092653],"study_design_scores_gemma":[0.0002494452,0.00008961228,0.006388206,0.00005802252,0.00004461334,0.00004714498,0.0002371,0.9832078,0.008888405,0.00004396752,0.000578136,0.0001675451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8408645,0.00006209513,0.1570888,0.00006784533,0.0003260659,0.0001498121,0.00002041613,0.0000172871,0.001403176],"genre_scores_gemma":[0.9863786,0.00006961125,0.01307742,0.00005842859,0.000009811443,2.406295e-9,0.000003140219,0.000008467583,0.0003944902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9684982,"threshold_uncertainty_score":0.9924783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0459545627512121,"score_gpt":0.2748204509119431,"score_spread":0.228865888160731,"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."}}