{"id":"W4392197214","doi":"10.1111/jfr3.12975","title":"Automated first floor height estimation for flood vulnerability analysis using deep learning and Google Street View","year":2024,"lang":"en","type":"article","venue":"Journal of Flood Risk Management","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Stairs; Flood myth; Vulnerability (computing); Estimation; Computer science; Ground truth; Deep learning; Environmental science; Artificial intelligence; Machine learning; Civil engineering; Geography; Engineering; Computer security","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001663486,0.0002735539,0.0004471905,0.0003861542,0.000406933,0.0002790139,0.0002474955,0.00006481461,0.0003362999],"category_scores_gemma":[0.0000470447,0.0002206547,0.000321054,0.0009493462,0.00007303527,0.0006142795,0.0002867969,0.0002607115,0.00002475031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003208113,"about_ca_system_score_gemma":0.000009733882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001731374,"about_ca_topic_score_gemma":0.0003932728,"domain_scores_codex":[0.9977191,0.0001549234,0.0007514929,0.0004415784,0.0005802392,0.0003526332],"domain_scores_gemma":[0.9990985,0.0001002922,0.0004027773,0.0002236695,0.00003104096,0.0001437695],"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":[0.00005796365,0.0003616468,0.02987071,0.000613978,0.003525765,0.000094948,0.0004848426,0.803959,0.00003245168,0.0002545195,0.001342647,0.1594016],"study_design_scores_gemma":[0.0007355413,0.0002554848,0.03012095,0.0001153671,0.005312515,0.00000747638,0.0003675222,0.9492149,0.00004423514,0.0006301323,0.01293836,0.0002575144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6489038,0.00315853,0.3445843,0.0003443982,0.0006112214,0.001060051,0.00001500725,0.00024449,0.001078187],"genre_scores_gemma":[0.8920392,0.002217984,0.1053379,0.00002544215,0.00008923394,0.00002629776,0.00001493114,0.00003024648,0.0002188468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2431354,"threshold_uncertainty_score":0.8998038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008571301353629539,"score_gpt":0.2811201086109311,"score_spread":0.2725488072573016,"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."}}