SEMIPARAMETRIC BAYESIAN FORECASTING OF SPATIOTEMPORAL EARTHQUAKE OCCURRENCES

• 成果类型: Article
• 署名作者: Ross, Gordon J.; Kolev, Aleksandar A.
• 署名单位: University of Edinburgh
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/21-AOAS1554
• 发表日期: 2022
• 页码: 2083-2100
• 关键词: point-process models; etas models; term

摘要

The Epidemic Type Aftershock Sequence (ETAS) model is a self -exciting point process which is used to model and forecast the occurrence of earthquakes in a geographical region. The ETAS model assumes that the oc-currence of mainshock earthquakes follows an inhomogeneous spatial point process, with their aftershock earthquakes modelled via a separate triggering kernel. Most previous studies of the ETAS model have relied on point esti-mates of the model parameters, due to the complexity of the likelihood func-tion and the difficulty in estimating an appropriate spatial mainshock distribu-tion. In order to take estimation uncertainty into account, we instead propose a fully Bayesian formulation of the ETAS model, which uses a nonparametric Dirichlet process mixture prior to capture the spatial mainshock process, and show how efficient parameter inference can be carried out using auxiliary la-tent variables. We demonstrate how our model can be used for medium-term earthquake forecasts in a number of geographical regions.