{"id":"W4205395090","doi":"10.3390/w14020178","title":"Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery","year":2022,"lang":"en","type":"article","venue":"Water","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Wetland; Convolutional neural network; Artificial intelligence; Marsh; Classifier (UML); Computer science; Remote sensing; Transformer; Deep learning; Machine learning; Pattern recognition (psychology); Engineering; Geography; Ecology; Electrical engineering","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":[0.0003945149,0.0005762517,0.0002935416,0.001204306,0.0002305966,0.0004051087,0.0005350517,0.0003252076,0.001179126],"category_scores_gemma":[0.0004295667,0.0001628788,0.0004243566,0.0006308799,0.0001806167,0.0006523224,0.0005022986,0.0003504144,0.0005360224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004109864,"about_ca_system_score_gemma":0.0006807061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027941,"about_ca_topic_score_gemma":0.02138431,"domain_scores_codex":[0.9998499,0.00001299141,0.000008247691,0.00004085912,0.00005231037,0.00003561285],"domain_scores_gemma":[0.9998933,0.00001490026,0.00001673206,0.00001275044,0.00004932328,0.00001298001],"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":[0.0007312827,0.0004216082,0.0598914,0.0002256388,0.0001885712,0.0006199551,0.000237809,0.07004523,0.1272006,0.002461639,0.01888324,0.7190931],"study_design_scores_gemma":[0.00002562185,0.0001264191,0.02123288,0.00001824459,0.00005082536,0.0001766416,0.0002206385,0.9354905,0.03774021,0.001109916,0.003778328,0.00002984275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7305931,0.0004578817,0.24978,0.0003576976,0.0001999035,0.0002518238,0.002539401,0.00737991,0.008440292],"genre_scores_gemma":[0.8624192,0.0002261607,0.1287084,0.0001432554,0.00003187806,0.00007115952,0.004601121,0.0001451808,0.003653567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01027941,"threshold_uncertainty_score":0.02043915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0443567802820956,"score_gpt":0.2695831154589433,"score_spread":0.2252263351768476,"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."}}