{"id":"W3015166318","doi":"10.1117/1.jrs.14.024502","title":"Supervised wetland classification using high spatial resolution optical, SAR, and LiDAR imagery","year":2020,"lang":"en","type":"article","venue":"Journal of Applied Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Parks Canada; Community Sector Council Newfoundland and Labrador","funders":"","keywords":"Lidar; Remote sensing; Wetland; Synthetic aperture radar; Computer science; Segmentation; Contextual image classification; Ranging; Environmental science; Random forest; Image resolution; Image segmentation; Classifier (UML); Artificial intelligence; Geography; Image (mathematics); Ecology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005545722,0.0005200273,0.0003388284,0.001079279,0.0002325161,0.0004282711,0.0003601266,0.0002965992,0.0005023726],"category_scores_gemma":[0.000758339,0.0001433674,0.0005058533,0.0004398784,0.0002283192,0.0004625178,0.0002918043,0.0002162111,0.0002230279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002561842,"about_ca_system_score_gemma":0.0004604475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005373865,"about_ca_topic_score_gemma":0.01340544,"domain_scores_codex":[0.9997106,0.00007875786,0.00001757149,0.00006133797,0.00008818284,0.00004359788],"domain_scores_gemma":[0.999492,0.0001638306,0.0000994466,0.0000551836,0.0001610562,0.00002831672],"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":[0.0006829686,0.0008840311,0.05101135,0.000313288,0.0002700682,0.0003349038,0.0002938089,0.1341398,0.1672709,0.0009811815,0.003842822,0.639975],"study_design_scores_gemma":[0.00002611052,0.0002071088,0.06467088,0.00002218496,0.00007861389,0.000152593,0.0002371379,0.8917634,0.04069527,0.0006648215,0.001444604,0.00003736937],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7475573,0.0002290308,0.247273,0.0001294855,0.00004136119,0.0001650755,0.0004473485,0.001319957,0.002837436],"genre_scores_gemma":[0.8839793,0.0001056288,0.1138617,0.00003463264,0.00002060359,0.00006195452,0.0007377231,0.00002726499,0.001171142],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005373865,"threshold_uncertainty_score":0.01068515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02280136071128773,"score_gpt":0.235951341518999,"score_spread":0.2131499808077113,"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."}}