{"id":"W4293069258","doi":"10.5194/isprs-archives-xliii-b3-2022-951-2022","title":"EFFECT OF TEXTURAL FEATURES FOR LANDCOVER CLASSIFICATION OF UAV MULTISPECTRAL IMAGERY OF A SALT MARSH RESTORATION SITE","year":2022,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; University of New Brunswick","funders":"Fisheries and Oceans Canada; Natural Sciences and Engineering Research Council of Canada; Mount Allison University; Mitacs; U.S. Department of Transportation","keywords":"Salt marsh; Marsh; Multispectral image; Environmental science; Estuary; Remote sensing; Intertidal zone; Restoration ecology; Bay; Vegetation (pathology); Hydrology (agriculture); Wetland; Geography; Geology; Oceanography; Ecology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009165127,0.0004237553,0.0002432628,0.000828432,0.0002544056,0.000658807,0.0002740238,0.0002881369,0.0004815659],"category_scores_gemma":[0.00231366,0.0001186918,0.0003477819,0.0003568062,0.0002178419,0.0004432041,0.000214102,0.0002830502,0.0002376711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003504734,"about_ca_system_score_gemma":0.0002613552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01940057,"about_ca_topic_score_gemma":0.03208503,"domain_scores_codex":[0.9997055,0.00007492561,0.00002943496,0.00006965597,0.00007140301,0.00004909273],"domain_scores_gemma":[0.998233,0.0007712094,0.0001914951,0.0001152739,0.0005608223,0.0001282325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003054347,0.0007687244,0.5100264,0.0002564883,0.0003416084,0.0003266807,0.0004135729,0.077955,0.135482,0.0001123161,0.002661044,0.2686019],"study_design_scores_gemma":[0.00003183368,0.0003384387,0.5602437,0.00004652957,0.0001700921,0.0001416953,0.0004523751,0.407997,0.02976019,0.00006385613,0.0007163585,0.00003793401],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963412,0.00006675014,0.002752274,0.00002887651,0.00001709412,0.00001719605,0.0002197997,0.0001157698,0.0004410348],"genre_scores_gemma":[0.9949003,0.0000280078,0.004333661,0.00001763102,0.000005095115,0.000008361882,0.0004775498,0.00001330358,0.0002162454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01940057,"threshold_uncertainty_score":0.03857529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01121106889553346,"score_gpt":0.2579925516988346,"score_spread":0.2467814828033011,"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."}}