{"id":"W3008799350","doi":"10.1002/eqe.3258","title":"Pre‐ and post‐earthquake regional loss assessment using deep learning","year":2020,"lang":"en","type":"article","venue":"Earthquake Engineering & Structural Dynamics","topic":"Seismic Performance and Analysis","field":"Engineering","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ministry of Land, Infrastructure and Transport; Natural Sciences and Engineering Research Council of Canada; Seoul National University","keywords":"Vulnerability (computing); Computer science; Seismic hazard; Seismic risk; Probabilistic logic; Artificial neural network; Vulnerability assessment; Hazard; Deep learning; Fragility; Earthquake scenario; Seismology; Machine learning; Geology; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000714314,0.0003503698,0.0003437017,0.0001196672,0.0001395762,0.0001102669,0.0001604845,0.0001199338,0.00003661156],"category_scores_gemma":[0.00002628265,0.0003644322,0.0001167581,0.0003399101,0.00004200258,0.0003426003,0.00006322786,0.0005994352,0.000007607984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009660159,"about_ca_system_score_gemma":0.00001989991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002648114,"about_ca_topic_score_gemma":0.00001404471,"domain_scores_codex":[0.9986167,0.00001634505,0.0003264949,0.0003128496,0.0002719962,0.0004556155],"domain_scores_gemma":[0.9994746,0.00004235107,0.0000485936,0.0001602334,0.00005069989,0.0002235069],"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":[0.000007167167,0.000001711114,0.007397249,0.0001262841,0.0001260966,0.00001997358,0.0004479289,0.8781981,0.001407336,0.00029587,0.000004895314,0.1119673],"study_design_scores_gemma":[0.000170405,0.00003032362,0.4085011,0.00002089522,0.00003155302,0.00004399919,0.00007468206,0.5905548,0.0000102018,0.000007447726,0.0002961155,0.0002584122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730315,0.000372302,0.0255781,0.0001481482,0.0002008196,0.000100224,0.00001594808,0.0005055767,0.00004733501],"genre_scores_gemma":[0.9943549,0.0001312949,0.004914092,0.0001219346,0.0002667565,0.000004053499,0.0001056798,0.00007264423,0.00002867019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4011039,"threshold_uncertainty_score":0.9998808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006424572563301091,"score_gpt":0.211222412951424,"score_spread":0.204797840388123,"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."}}