{"id":"W4402690865","doi":"10.2139/ssrn.4962388","title":"A Novel Spatio-Temporal Vision Transformer Model for Improving Wetland Mapping Using Multi-Seasonal Sentinel Data","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Wetland; Remote sensing; Transformer; Environmental science; Computer vision; Cartography; Artificial intelligence; Geography; Engineering; Ecology; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005536049,0.0005322169,0.0006038052,0.0004990223,0.0002345586,0.0007139661,0.001524991,0.0007570938,0.001767401],"category_scores_gemma":[0.001072532,0.0003886731,0.0006683777,0.0006375226,0.0002251412,0.0009826655,0.0006541428,0.0008259336,0.0005217984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006969718,"about_ca_system_score_gemma":0.00126934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02298687,"about_ca_topic_score_gemma":0.02141858,"domain_scores_codex":[0.9998488,0.00001792642,0.000007707792,0.00005603051,0.00003738093,0.00003197412],"domain_scores_gemma":[0.9997724,0.00006579466,0.00002087114,0.00002508363,0.00009203844,0.00002384948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001813059,0.0001277936,0.001496668,0.00005325716,0.0000866896,0.00005929084,0.00002640731,0.7985795,0.01118397,0.003041412,0.00241114,0.1827526],"study_design_scores_gemma":[0.000002322593,0.000004603535,0.00006923955,7.111328e-7,0.000003970009,0.000005752735,9.896027e-7,0.9991838,0.0003775432,0.0002581165,0.00009149824,0.000001414363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02359685,0.0001557321,0.9741052,0.0001196982,0.00006492925,0.00002893317,0.0001714247,0.001007376,0.0007499337],"genre_scores_gemma":[0.8136531,0.0002904404,0.1814515,0.0001786359,0.00007144853,0.00009561089,0.00068498,0.0001764127,0.003397874],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02298687,"threshold_uncertainty_score":0.04570609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04498877828944463,"score_gpt":0.2873198638289297,"score_spread":0.2423310855394851,"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."}}