EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Flexible Seismicity Modeling With Neural Modulated Renewal Processes

Chengxiang Zhan, Jiancang Zhuang, Stephen Wu

Earth's Future · 2026-04 · 14 (4)

DOI: 10.1029/2025ef007342 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Earth's Future, online erschienen am 24.04.2026. Verfasst von Chengxiang Zhan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural point processes (NPPs) have recently been applied to seismicity modeling, but their theoretical connections to classical point processes models remain elusive. Moreover, two fundamental questions remain unresolved: (a) how much historical information is sufficient for NPPs to effectively model seismicity, and (b) what is the differential impact between inter‐event times and magnitudes on the model predictive performance? To answer these questions, we reinterpret a class of NPPs within the framework of neural modulated renewal processes (NMRPs), which generalize conventional modulated renewal processes by integrating deep learning architectures. We develop and analyze four variants: the unmodulated neural renewal process (NRP), the inter‐event times modulated NMRP (I‐NMRP), the magnitude modulated NMRP (M‐NMRP), and the jointly modulated NMRP (J‐NMRP). Their performance is systematically evaluated against the epidemic‐type aftershock sequence (ETAS) model using the EarthquakeNPP benchmark. Results demonstrate that I‐NMRP and J‐NMRP not only match, but in some cases surpass, ETAS in terms of log‐likelihood, while requiring substantially less historical input. Furthermore, the analysis reveals that inter‐event times play a more critical role than magnitudes in enhancing predictive performance. These findings establish NMRP as a flexible and efficient framework for seismicity modeling, with strong potential to incorporate diverse contextual information and to deepen our understanding of earthquake triggering processes.

Förderung

  • China Scholarship Council

Zitieren

APA

Zhan, C., Zhuang, J., & Wu, S. (2026). Flexible Seismicity Modeling With Neural Modulated Renewal Processes. Earth's Future, 14(4). https://doi.org/10.1029/2025ef007342

Vancouver

Zhan C, Zhuang J, Wu S. Flexible Seismicity Modeling With Neural Modulated Renewal Processes. Earth's Future. 2026;14(4). doi:10.1029/2025ef007342

BibTeX
@article{Zhan2026,
  author = {Zhan, Chengxiang and Zhuang, Jiancang and Wu, Stephen},
  title = {Flexible Seismicity Modeling With Neural Modulated Renewal Processes},
  journal = {Earth's Future},
  year = {2026},
  volume = {14},
  number = {4},
  doi = {10.1029/2025ef007342}
}
Kostenlos starten →