{"id":"W4390607656","doi":"10.1016/j.isprsjprs.2023.12.009","title":"An efficient urban flood mapping framework towards disaster response driven by weakly supervised semantic segmentation with decoupled training samples","year":2024,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada; Western University","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; National Oceanic and Atmospheric Administration","keywords":"Flood myth; Disaster response; Segmentation; Training (meteorology); Computer science; Emergency response; Artificial intelligence; Machine learning; Geography; Emergency management; Medical emergency; Meteorology","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":[0.0004020289,0.0008738363,0.0009847629,0.0008460347,0.0003808293,0.0008281103,0.00153307,0.0008835912,0.002180688],"category_scores_gemma":[0.0006850878,0.0004832566,0.0008843809,0.0008429259,0.0004311524,0.0008478428,0.001309901,0.0007192296,0.001001602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003344048,"about_ca_system_score_gemma":0.001238803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006602257,"about_ca_topic_score_gemma":0.01245648,"domain_scores_codex":[0.9997082,0.00003993685,0.00001160383,0.0001090826,0.00007273933,0.00005849933],"domain_scores_gemma":[0.9998355,0.00004597806,0.00001472031,0.00003429861,0.00005162569,0.00001783816],"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":[0.0004915619,0.0002871655,0.001745518,0.0001707718,0.000138168,0.0002255098,0.0001564027,0.4889631,0.04418565,0.006134423,0.007390606,0.4501111],"study_design_scores_gemma":[0.000006371082,0.0000192118,0.0002276106,0.000003194304,0.000008857172,0.00002119866,0.0000142047,0.9949737,0.002266658,0.001711459,0.0007419802,0.000005619277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02248154,0.0001397133,0.973834,0.00008318869,0.0000321793,0.00006123849,0.0002739255,0.002164317,0.00092983],"genre_scores_gemma":[0.4389719,0.0001904173,0.5526658,0.0001959621,0.00008610929,0.0002165382,0.002491502,0.0004435806,0.00473815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006602257,"threshold_uncertainty_score":0.01312768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0139528418521287,"score_gpt":0.2597149869701075,"score_spread":0.2457621451179788,"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."}}