{"id":"W4312999150","doi":"10.1109/jstars.2022.3215730","title":"Enhancement of Urban Floodwater Mapping From Aerial Imagery With Dense Shadows via Semisupervised Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; Western University","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Flood myth; Workflow; Deep learning; Exploit; Artificial intelligence; Aerial image; Change detection; Drone; Regularization (linguistics); Remote sensing; Machine learning; Image (mathematics); Database; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003480057,0.0001237251,0.0002331011,0.0001091393,0.0002170716,0.00003148704,0.00009358716,0.00003305126,0.0001215758],"category_scores_gemma":[0.000009804134,0.0001087273,0.00003082661,0.0004456789,0.00005219605,0.00009694821,0.00009295131,0.000365441,7.032774e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009778532,"about_ca_system_score_gemma":0.00003645909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004268259,"about_ca_topic_score_gemma":0.0002049905,"domain_scores_codex":[0.9986728,0.0000771514,0.0004506169,0.0001747858,0.0004310918,0.0001935981],"domain_scores_gemma":[0.9994635,0.00004055112,0.0003002672,0.0001043792,0.00004396645,0.00004731079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001937416,0.0001031869,0.01173143,0.00002588532,0.0001110131,0.00005394137,0.003096395,0.03931668,0.8659921,0.00001353651,0.0002176102,0.07914452],"study_design_scores_gemma":[0.009737005,0.001346647,0.3005409,0.0004633753,0.0003831921,0.0001448284,0.005416289,0.4617468,0.1825328,0.002142253,0.03409498,0.001451012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590176,0.00003464182,0.03998977,0.0001696986,0.0001533662,0.0001773834,0.000001286341,0.000008495091,0.0004477516],"genre_scores_gemma":[0.8913162,0.00006463252,0.1082317,0.00009020881,0.0001207798,3.464393e-7,0.000008388338,0.00001244991,0.0001552657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6834593,"threshold_uncertainty_score":0.4433771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01212660675003123,"score_gpt":0.1977713491195014,"score_spread":0.1856447423694702,"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."}}