{"id":"W6948047919","doi":"10.48448/6mp7-bz37","title":"RADARSAT-2 Synthetic-Aperture Radar Land Cover Segmentation using Deep Convolutional Neural Networks","year":2022,"lang":"en","type":"other","venue":"Open MIND","topic":"Planarian Biology and Electrostimulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec; École de Technologie Supérieure","funders":"","keywords":"Convolutional neural network; Segmentation; Artificial neural network; Pattern recognition (psychology); Land cover; Image segmentation","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000121951,0.0002029332,0.0001869791,0.00004540929,0.0001392391,0.00004146766,0.0002564869,0.0004050788,0.01418468],"category_scores_gemma":[0.00002352001,0.0002007439,0.00005768588,0.00005604034,0.00005935103,0.000004502302,0.0001758971,0.000183265,0.0000357949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004131545,"about_ca_system_score_gemma":0.00008198922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006785796,"about_ca_topic_score_gemma":0.0001417842,"domain_scores_codex":[0.9989902,0.0001289982,0.0001453176,0.0004220222,0.00009642036,0.0002170483],"domain_scores_gemma":[0.9995443,0.00002073401,0.0001610408,0.0002129907,0.00001462347,0.0000463628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001994569,0.0003297082,0.01713033,0.00003724259,0.001508098,0.00009843632,0.00009077314,0.04070773,0.07755135,0.00003411014,0.8270086,0.03350904],"study_design_scores_gemma":[0.0006353532,0.0001093942,0.0001290659,0.00001089868,0.00006960289,0.00006657876,0.000007920555,0.01668127,0.0003286011,0.00000366429,0.9816788,0.0002788655],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0924305,0.03425476,0.1234474,0.003827209,0.006057794,0.008829704,0.006160832,0.00005171023,0.7249401],"genre_scores_gemma":[0.1037728,0.0007557318,0.03633969,0.006455519,0.003182312,0.0000655671,0.1111375,0.0009804879,0.7373104],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1546702,"threshold_uncertainty_score":0.9867165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507798197932617,"score_gpt":0.2677006626883346,"score_spread":0.2526226807090084,"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."}}