ETAS-Inspired Spatio-Temporal Convolutional (STC) Model for Next-Day Earthquake Forecasting

被引:0
|
作者
Zhan, Chengxiang [1 ]
Gao, Shichen [1 ]
Zhang, Ying [2 ]
Li, Jiawei [3 ]
Meng, Qingyan [4 ]
机构
[1] China Univ Geosci Beijing, Sch Sci, Beijing 100083, Peoples R China
[2] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
[3] Southern Univ Sci & Technol SUSTech, Inst Risk Anal Predict & Management Risks X, Acad Adv Interdisciplinary Studies, Shenzhen 518055, Peoples R China
[4] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100049, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2024年 / 62卷
基金
中国国家自然科学基金;
关键词
Earthquakes; Predictive models; Forecasting; Data models; Deep learning; Training; Seismology; earthquake forecasting; statistical seismology; NETWORK;
D O I
10.1109/TGRS.2024.3424881
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Research on integrating statistical knowledge into deep learning models for earthquake forecasting has been limited. Traditional deep learning models require extensive parameter learning from scratch. This study proposes a spatio-temporal convolutional (STC) model that incorporates spatio-temporal decay prior knowledge derived from the epidemic-type aftershock sequence (ETAS) into a convolutional kernel. This allows the STC model to have the prototype to learn the pattern of mainshocks to trigger aftershocks at the beginning of training, with only four neurons to fine-tune it. In California, the STC and the ETAS model are conducted for forecasting next-day earthquakes with magnitudes of M >= 3 , M >= 4 , and M >= 5 . Both performances were assessed using the receiver operating characteristic (ROC) curve, the precision-recall (PR) curve, and the parimutuel gambling score (PGS). The evaluation results indicate that the STC model surpasses ETAS in forecasting next-day earthquakes not accidental. Furthermore, our analysis suggests that including earthquakes below the complete magnitudes can enhance the STC model's classification performance, as small earthquakes also contain information about future earthquakes.
引用
收藏
页码:1 / 1
页数:14
相关论文
共 50 条
  • [1] Next-day earthquake forecasts for the Japan region generated by the ETAS model
    Zhuang, Jiancang
    EARTH PLANETS AND SPACE, 2011, 63 (03): : 207 - 216
  • [2] Next-day earthquake forecasts for the Japan region generated by the ETAS model
    Jiancang Zhuang
    Earth, Planets and Space, 2011, 63 : 207 - 216
  • [3] Improvements to seismicity forecasting based on a Bayesian spatio-temporal ETAS model
    Hossein Ebrahimian
    Fatemeh Jalayer
    Behnam Maleki Asayesh
    Sebastian Hainzl
    Hamid Zafarani
    Scientific Reports, 12
  • [4] Spatio-temporal characterization of earthquake sequence parameters and forecasting of strong aftershocks in Xinjiang based on the ETAS model
    Li, Ke
    Wang, Maofa
    Zhang, Huiguo
    Hu, Xijian
    PLOS ONE, 2024, 19 (05):
  • [5] Improvements to seismicity forecasting based on a Bayesian spatio-temporal ETAS model
    Ebrahimian, Hossein
    Jalayer, Fatemeh
    Asayesh, Behnam Maleki
    Hainzl, Sebastian
    Zafarani, Hamid
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [6] U-Convolutional model for spatio-temporal wind speed forecasting
    Bastos, Bruno Quaresma
    Cyrino Oliveira, Fernando Luiz
    Milidiu, Ruy Luiz
    INTERNATIONAL JOURNAL OF FORECASTING, 2021, 37 (02) : 949 - 970
  • [7] Probabilistic spatio-temporal graph convolutional network for traffic forecasting
    Karim, Atkia Akila
    Nower, Naushin
    APPLIED INTELLIGENCE, 2024, : 7070 - 7085
  • [8] Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
    Zheng, Chuanpan
    Fan, Xiaoliang
    Pan, Shirui
    Jin, Haibing
    Peng, Zhaopeng
    Wu, Zonghan
    Wang, Cheng
    Yu, Philip S.
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (01) : 372 - 385
  • [9] Spatio-temporal model for crop yield forecasting
    Saengseedam, Panudet
    Kantanantha, Nantachai
    JOURNAL OF APPLIED STATISTICS, 2017, 44 (03) : 427 - 440
  • [10] Spatio-temporal fusion graph convolutional network for traffic flow forecasting
    Ma, Ying
    Lou, Haijie
    Yan, Ming
    Sun, Fanghui
    Li, Guoqi
    INFORMATION FUSION, 2024, 104