{"id":"W146776107","doi":"10.1007/s11589-012-0843-5","title":"Observations on the application of artificial neural network to predicting ground motion measures","year":2012,"lang":"en","type":"article","venue":"Earthquake Science","topic":"Seismic Performance and Analysis","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Artificial neural network; Residual; Ground motion; Parametric statistics; Similarity (geometry); Acceleration; Mean squared error; Computer science; Backpropagation; Regression; Motion (physics); Mathematics; Statistics; Artificial intelligence; Algorithm; Geology; Seismology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.001127092,0.0003648999,0.0001980214,0.0004709822,0.0003245246,0.0004197577,0.0004142488,0.0007122848,0.0032281],"category_scores_gemma":[0.006846945,0.0001131873,0.000168636,0.0009088078,0.0004325311,0.0005674463,0.0002636829,0.0008604881,0.0005644915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003433272,"about_ca_system_score_gemma":0.0002017294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008705189,"about_ca_topic_score_gemma":0.007264243,"domain_scores_codex":[0.9996523,0.00007303392,0.00002863095,0.00004845152,0.0001779612,0.00001976963],"domain_scores_gemma":[0.9962984,0.002462458,0.0001619786,0.000179508,0.000852631,0.00004506511],"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":[0.002136714,0.001312659,0.1030405,0.001546709,0.0003024157,0.002223813,0.002190365,0.2587374,0.1349132,0.01680509,0.01853663,0.4582545],"study_design_scores_gemma":[0.0000897657,0.001267967,0.3046447,0.00047425,0.0002281404,0.001071788,0.001350971,0.4649387,0.1393323,0.02546188,0.06098795,0.0001516788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8771114,0.003223678,0.06719791,0.004113173,0.0003828529,0.00007439447,0.001859917,0.0002172863,0.0458194],"genre_scores_gemma":[0.9812619,0.002146067,0.006824857,0.0002310232,0.0001509483,0.00001287754,0.000566288,0.00002958079,0.008776521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008705189,"threshold_uncertainty_score":0.01730907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04139585731268426,"score_gpt":0.242928059838349,"score_spread":0.2015322025256647,"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."}}