{"id":"W3203024476","doi":"10.4236/ars.2021.103007","title":"Fully Polarimetric Land Cover Classification Based on Hidden Markov Models Trained with Multiple Observations","year":2021,"lang":"en","type":"article","venue":"Advances in Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Polarimetry; Land cover; Hidden Markov model; Remote sensing; Computer science; Pixel; Pattern recognition (psychology); Scattering; Cover (algebra); Artificial intelligence; Novelty; Contextual image classification; Set (abstract data type); Geography; Land use; Image (mathematics); Physics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00009011033,0.0001500381,0.0001637256,0.0001592462,0.00006702838,0.00002937433,0.00006833475,0.00008091139,0.000005523523],"category_scores_gemma":[0.00007784374,0.00014122,0.00003324253,0.0007425804,0.00003028536,0.0001880611,0.000008496361,0.0001658458,0.000002912034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199997,"about_ca_system_score_gemma":0.00003763953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005346456,"about_ca_topic_score_gemma":0.0001733459,"domain_scores_codex":[0.9991713,0.00003105142,0.0002022879,0.0002459399,0.0001680975,0.0001813677],"domain_scores_gemma":[0.9991668,0.0003093593,0.00004272644,0.0003616755,0.0000806643,0.00003875732],"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":[0.00001773901,0.00002232307,0.0004554485,0.00002885504,0.000008519284,0.00001182009,0.00004169006,0.01111187,0.001687261,0.0003406863,0.00002082778,0.986253],"study_design_scores_gemma":[0.000327084,0.00001683601,0.002755608,0.0001340135,0.00001159572,0.00001146682,0.00003575936,0.9562317,0.00434347,0.001202121,0.03474488,0.0001854631],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009907688,0.0005722242,0.9789072,0.0003569298,0.00005571794,0.0002065903,0.00001168365,0.000271837,0.009710117],"genre_scores_gemma":[0.4626876,0.0001210929,0.5369937,0.00009120147,0.00002164292,4.637686e-7,0.00003400094,0.00002344187,0.0000268901],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860675,"threshold_uncertainty_score":0.5758783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0190872784223218,"score_gpt":0.2357569041813538,"score_spread":0.216669625759032,"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."}}