{"id":"W2078180904","doi":"10.1016/j.rse.2007.02.014","title":"Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification","year":2007,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":232,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Parks Canada; Clayoquot Biosphere Trust; Ministry of Forests, Lands and Natural Resource Operations; University of Queensland","keywords":"Remote sensing; Riparian zone; Vegetation (pathology); Image resolution; Spatial analysis; Pixel; Contextual image classification; Environmental science; Satellite imagery; Image texture; Vegetation classification; Image segmentation; Geology; Segmentation; Computer science; Artificial intelligence; Ecology; 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":[0.0006485951,0.0001620742,0.0002360193,0.0000480803,0.00008584163,0.000009121812,0.00007740297,0.0001415016,0.000004487321],"category_scores_gemma":[0.00003931819,0.0001483503,0.00006569656,0.00009321771,0.0001978048,0.00007404853,0.00006701785,0.00007930987,0.000014679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002758739,"about_ca_system_score_gemma":0.000004213402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001075969,"about_ca_topic_score_gemma":0.0005939376,"domain_scores_codex":[0.9984804,0.00004882504,0.0005124156,0.0003890836,0.0003272195,0.000241997],"domain_scores_gemma":[0.9989678,0.0001105511,0.0004591544,0.0003704489,0.00001318696,0.00007880925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008710067,0.00004028695,0.001669306,0.00006698655,0.00001408739,0.000001140157,0.0001503245,0.003798392,0.4789118,0.0000890199,0.00004858332,0.515123],"study_design_scores_gemma":[0.0005827709,0.000142462,0.7007939,0.00009239381,0.00007190371,0.00003205309,0.0001052614,0.221726,0.06711914,0.001195732,0.007862848,0.0002755035],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.50706,0.00003470782,0.491526,0.0001335647,0.00007007422,0.0005088092,0.000006877784,0.00001561811,0.0006443475],"genre_scores_gemma":[0.8885112,0.00008277044,0.1112125,0.00001537759,0.0000705314,1.084496e-7,0.00004148891,0.00001775569,0.00004816102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6991246,"threshold_uncertainty_score":0.6049549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009260019439390978,"score_gpt":0.2081799651654975,"score_spread":0.1989199457261065,"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."}}