{"id":"W3200616406","doi":"10.1080/15481603.2021.1965399","title":"Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data","year":2021,"lang":"en","type":"article","venue":"GIScience & Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Random forest; Gradient boosting; Artificial intelligence; Classifier (UML); Boosting (machine learning); Decision tree; Computer science; Wetland; Machine learning; Naive Bayes classifier; Convolutional neural network; Remote sensing; Deep learning; Statistical classification; Pattern recognition (psychology); Support vector machine; Geography; Ecology; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0007230039,0.0001109553,0.0001328141,0.00003738861,0.0003955213,0.0001188514,0.0002497682,0.00003180114,0.000010839],"category_scores_gemma":[0.00009751893,0.0000858857,0.00003262335,0.000394602,0.0003157325,0.0003579693,0.0008490187,0.00006990481,0.000002513741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004064373,"about_ca_system_score_gemma":0.00002099925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002264377,"about_ca_topic_score_gemma":0.0004640949,"domain_scores_codex":[0.9986683,0.00005418831,0.0002284002,0.0004384246,0.0003339567,0.0002767135],"domain_scores_gemma":[0.9991831,0.00008321011,0.0001550413,0.0005029109,0.00003044517,0.00004531458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002565447,0.0001268631,0.06847382,0.0001886347,0.00005885453,0.00004471042,0.002120476,0.01347804,0.6819972,0.000720706,0.002253447,0.2305115],"study_design_scores_gemma":[0.0002994906,0.000005993434,0.02576791,0.00004073701,0.00003701322,0.00002221398,0.0008348735,0.9676474,0.001478334,0.0008884262,0.002860989,0.0001165771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.589298,0.00004721876,0.4078848,0.001064828,0.0001628608,0.0002138151,0.00000158325,0.00001352765,0.00131332],"genre_scores_gemma":[0.9452814,0.00003830817,0.05417999,0.0002130756,0.00004177518,9.699578e-8,0.00002622829,0.00001022835,0.0002089304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9541694,"threshold_uncertainty_score":0.3502317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05014478185543613,"score_gpt":0.2854319821997577,"score_spread":0.2352872003443216,"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."}}