{"id":"W4322503029","doi":"10.3390/rs15051253","title":"Water Body Extraction from Sentinel-2 Imagery with Deep Convolutional Networks and Pixelwise Category Transplantation","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Multispectral image; Pattern recognition (psychology); Segmentation; RGB color model; Field (mathematics); Remote sensing; Geology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004632143,0.001164214,0.0004651436,0.001280298,0.0003089996,0.0006067086,0.001101873,0.0008061216,0.001243897],"category_scores_gemma":[0.0009990913,0.0003347863,0.0008227528,0.001079738,0.0004261112,0.001286637,0.001074729,0.001028875,0.001079556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006098976,"about_ca_system_score_gemma":0.0007701908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01462138,"about_ca_topic_score_gemma":0.02781838,"domain_scores_codex":[0.9997863,0.00001993031,0.000008325065,0.00007669092,0.00005565343,0.00005309181],"domain_scores_gemma":[0.9997596,0.000055173,0.00003223742,0.0000634486,0.00007380176,0.00001580781],"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":[0.0005279008,0.0003997665,0.0117903,0.0002147714,0.0002542663,0.0002463499,0.0001607712,0.2407158,0.04704573,0.002632458,0.01898559,0.6770263],"study_design_scores_gemma":[0.00001204218,0.00005617216,0.002198169,0.00001855317,0.00003213745,0.0000473156,0.00004412794,0.9782569,0.01415204,0.002614477,0.002548003,0.00002008366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3995128,0.001865258,0.5607356,0.000818934,0.0005152127,0.0002070898,0.004269025,0.0226283,0.009447639],"genre_scores_gemma":[0.7375549,0.0006049258,0.2376734,0.0005646361,0.00009954896,0.0001322874,0.01510882,0.0004625245,0.007798984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01462138,"threshold_uncertainty_score":0.02907252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006771845960404652,"score_gpt":0.2167335015733782,"score_spread":0.2099616556129736,"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."}}