{"id":"W4411967707","doi":"10.1016/j.geomat.2025.100061","title":"STURM-FloodDepth: A deep learning pipeline for mapping urban flood depth using street-level and oblique aerial imagery","year":2025,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; H2020 Marie Skłodowska-Curie Actions; European Commission","keywords":"Oblique case; Aerial imagery; Pipeline (software); Flood myth; Cartography; Aerial photos; Geography; Geology; Aerial survey; Artificial intelligence; Remote sensing; Computer science; Archaeology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004119151,0.0002102822,0.0002532045,0.0001011021,0.0003323017,0.0001171464,0.0001889263,0.00007105082,0.0001627023],"category_scores_gemma":[0.0001219628,0.0001986872,0.00007175291,0.0002497309,0.0000986809,0.0002290697,0.0004358793,0.0001316862,0.00002126397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009834704,"about_ca_system_score_gemma":0.00001965987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003783735,"about_ca_topic_score_gemma":0.0006800076,"domain_scores_codex":[0.9985659,0.00006656697,0.0003414384,0.0003945506,0.0002104359,0.0004211657],"domain_scores_gemma":[0.9994624,0.0001164725,0.0001069216,0.0002201094,0.00001277174,0.00008130208],"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":[0.0003203464,0.001272938,0.4010153,0.00168844,0.000849426,0.00006802182,0.005012383,0.02398064,0.05765455,0.009160812,0.03426293,0.4647142],"study_design_scores_gemma":[0.005012488,0.0002190648,0.1352947,0.0003581741,0.0005470589,0.000006709648,0.003798766,0.8027523,0.002581279,0.00581177,0.04246331,0.001154489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5238004,0.0001712757,0.4664641,0.0004196328,0.0003312592,0.001009004,0.000008353991,0.000123697,0.007672281],"genre_scores_gemma":[0.9021943,0.0000399627,0.09565765,0.0002567497,0.0001257296,0.00007609717,0.0000250239,0.00002384716,0.001600652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7787716,"threshold_uncertainty_score":0.8102227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02010225556721133,"score_gpt":0.2612305582811495,"score_spread":0.2411283027139382,"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."}}