{"id":"W4205343656","doi":"10.3390/w14010082","title":"Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery","year":2022,"lang":"en","type":"article","venue":"Water","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Space Agency; National Natural Science Foundation of China; European Space Agency","keywords":"Random forest; Remote sensing; Wetland; Support vector machine; Land cover; Cohen's kappa; Environmental science; Computer science; Polarimetry; Artificial intelligence; Pattern recognition (psychology); Land use; Geography; Machine learning; Ecology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006368807,0.0008598312,0.0005947063,0.001708794,0.0004333224,0.0003652173,0.0006882391,0.0004605613,0.001117388],"category_scores_gemma":[0.0005110828,0.0002328704,0.001021839,0.0008416701,0.000193646,0.0007665867,0.0003383149,0.0003979814,0.0002860975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003150279,"about_ca_system_score_gemma":0.0007080117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01025347,"about_ca_topic_score_gemma":0.01506646,"domain_scores_codex":[0.9996849,0.00003119942,0.000016763,0.00007581621,0.0001299826,0.00006126529],"domain_scores_gemma":[0.9998036,0.00004133111,0.00002165904,0.00001868077,0.00009685511,0.000017868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004018805,0.000235143,0.01050514,0.0001814049,0.0001443727,0.0002831233,0.0001528388,0.09966107,0.07021057,0.00194441,0.003511221,0.8127689],"study_design_scores_gemma":[0.00002102632,0.00006977108,0.006916401,0.00001211268,0.00004658121,0.0001371323,0.00004628523,0.9797922,0.01094943,0.0007804252,0.001208579,0.00001995502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1822492,0.000660376,0.812817,0.0001201658,0.00009538383,0.0001538958,0.0002913885,0.00141605,0.002196572],"genre_scores_gemma":[0.7165831,0.0003414468,0.2799839,0.00006829276,0.00005200936,0.00009080608,0.0008382103,0.0000623725,0.001979787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01025347,"threshold_uncertainty_score":0.02038753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02267863830653321,"score_gpt":0.2590195320321198,"score_spread":0.2363408937255866,"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."}}