{"id":"W4400881131","doi":"10.3390/rs16142673","title":"Wet-ConViT: A Hybrid Convolutional–Transformer Model for Efficient Wetland Classification Using Satellite Data","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Natural Resources Canada; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Convolutional neural network; Land cover; Deep learning; Multispectral image; Remote sensing; Artificial intelligence; Architecture; Transformer; Data mining; Machine learning; Land use","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":[0.0002325937,0.0008785496,0.0003495565,0.0004304765,0.0001823539,0.0005324411,0.001390632,0.0004476571,0.002092702],"category_scores_gemma":[0.0004371833,0.0002512591,0.0005980583,0.0004321058,0.0002716424,0.0009445021,0.0006132471,0.0007826944,0.0007152226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007890208,"about_ca_system_score_gemma":0.000986347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01504987,"about_ca_topic_score_gemma":0.02360096,"domain_scores_codex":[0.9999086,0.000007148718,0.00000487571,0.00002921762,0.00002790571,0.00002224929],"domain_scores_gemma":[0.9999243,0.00001640221,0.00001007655,0.00001278504,0.00002703994,0.000009351341],"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":[0.0003914226,0.0002677244,0.00413687,0.0002037701,0.0002226455,0.0002728328,0.00007331948,0.5801327,0.04190633,0.008633784,0.01780119,0.3459574],"study_design_scores_gemma":[0.000006910915,0.00003433426,0.0003106473,0.00000554232,0.00001433884,0.00003014315,0.000006066613,0.9921154,0.005287791,0.0008860565,0.001296072,0.000006642259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1420202,0.001228278,0.8330777,0.0004812408,0.0002522853,0.0001676174,0.001653997,0.0101377,0.01098087],"genre_scores_gemma":[0.8547948,0.0006457071,0.1243218,0.0004163722,0.00005677681,0.0001658065,0.00420767,0.0003275122,0.01506367],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01504987,"threshold_uncertainty_score":0.02992457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06701302281002353,"score_gpt":0.2943052537184527,"score_spread":0.2272922309084292,"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."}}