{"id":"W4386308278","doi":"10.1029/2023gl103909","title":"Using Deep Learning for Flexible and Scalable Earthquake Forecasting","year":2023,"lang":"en","type":"article","venue":"Geophysical Research Letters","topic":"earthquake and tectonic studies","field":"Earth and Planetary Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Benchmark (surveying); Scalability; Earthquake prediction; Aftershock; Computer science; Data set; Earthquake simulation; Set (abstract data type); Scale (ratio); Artificial neural network; Seismology; Data mining; Machine learning; Artificial intelligence; Geology; Geography; Cartography; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006329586,0.0006163383,0.0004586247,0.000426881,0.0002260836,0.0006377493,0.0009864367,0.0006103744,0.00142441],"category_scores_gemma":[0.002143058,0.0004221958,0.00029084,0.0005410384,0.0003517165,0.001192945,0.0009270082,0.001029721,0.0004677887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007199113,"about_ca_system_score_gemma":0.0008366128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01638759,"about_ca_topic_score_gemma":0.01857511,"domain_scores_codex":[0.9998369,0.00003427492,0.00001215456,0.00004592794,0.00004067322,0.00003005899],"domain_scores_gemma":[0.9993927,0.0002691975,0.00006030422,0.0001115083,0.0001310138,0.00003521431],"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":[0.00007216987,0.00005190284,0.001723438,0.00002253296,0.00003294194,0.00003949675,0.00001850529,0.9196242,0.00373402,0.001405599,0.001871659,0.07140354],"study_design_scores_gemma":[0.00000165269,0.00000295935,0.00004330041,5.828541e-7,7.312036e-7,9.805678e-7,0.000001199558,0.9991884,0.0002489907,0.0004522444,0.00005821236,7.838657e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3158456,0.0006901785,0.6703923,0.001240134,0.0001429688,0.0000565727,0.0008667369,0.006497171,0.004268349],"genre_scores_gemma":[0.9113617,0.0001487196,0.08591078,0.0001189132,0.0000437402,0.00004012563,0.0007815983,0.00008003974,0.001514375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01638759,"threshold_uncertainty_score":0.03258437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1419134408815921,"score_gpt":0.3339464821916588,"score_spread":0.1920330413100667,"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."}}