{"id":"W4322011334","doi":"10.5194/egusphere-egu23-9091","title":"Improving near real-time flood extraction pipeline from SAR data using deep learning","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Deep learning; Computer science; Pipeline (software); Context (archaeology); Artificial intelligence; Convolutional neural network; Flood myth; Remote sensing; Real-time computing; Machine learning; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004395561,0.001689745,0.0006902865,0.001320154,0.0004340385,0.001047342,0.001335664,0.0007384954,0.006892937],"category_scores_gemma":[0.001432599,0.0005869335,0.001202151,0.001059681,0.0002653601,0.001675162,0.001304111,0.001493671,0.005219237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007269079,"about_ca_system_score_gemma":0.001622395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01748949,"about_ca_topic_score_gemma":0.02893256,"domain_scores_codex":[0.9997163,0.00002179922,0.00001773336,0.00009485942,0.00007028819,0.00007892703],"domain_scores_gemma":[0.9997118,0.00005881829,0.00002387402,0.00005952121,0.0001201767,0.00002583831],"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":[0.0005849906,0.0004159011,0.00733139,0.0004203671,0.0003087845,0.0005660258,0.0002280289,0.1755762,0.04163499,0.001978254,0.08006072,0.6908943],"study_design_scores_gemma":[0.0000478142,0.00008663112,0.002851879,0.00004254589,0.00004535349,0.0001030549,0.0001013072,0.964079,0.0189256,0.003144512,0.01053434,0.00003797461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1578532,0.001745846,0.7064603,0.001387864,0.0005304053,0.0003170546,0.01557423,0.1057834,0.01034769],"genre_scores_gemma":[0.4530264,0.0009162404,0.4614897,0.0009698372,0.0001337425,0.0003340843,0.0595295,0.002835903,0.02076466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01748949,"threshold_uncertainty_score":0.03477538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04437273172786834,"score_gpt":0.3034020968826239,"score_spread":0.2590293651547556,"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."}}