EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Global Search of PKP Precursors With Graph Neural Network: Implications for Scatterers in the Lowermost Mantle

Shang Ma, Zefeng Li, Daoyuan Sun, Yulong Su, Jiewen Li, Xu Si, Jun Zhu

Geophysical Research Letters · 16.09.2025 · 52 (17)

DOI: 10.1029/2025gl115952 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 31.08.2025. Verfasst von Shang Ma und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, University of Science and Technology of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Seismic waves preceding the core phase PKIKP, known as PKP precursors, have been used to map small scatterers near the core‐mantle boundary (CMB). However, their low signal‐to‐noise ratio has required manual identification, hindering systematic and comprehensive analysis. Here, we develop GraphCursor, a model based on Graph Neural Networks (GNNs), to detect PKP precursors across multiple stations. Trained on manually picked precursors, GraphCursor identifies 37,512 precursor waveforms from 5,499 global earthquakes (2000–2024). We locate scatterers by stacking multistation probability functions and estimate their strengths relative to global averages. Our exhaustive search produces unprecedentedly abundant scatterers, including new discoveries of those beneath Antarctica. The distribution of most global scatterers largely correlates with ultra‐low velocity zones (ULVZs). GraphCursor's potential extends to identifying other deep seismic phases and aids in promoting the discovery of new deep Earth structures.

Förderung

  • National Natural Science Foundation of China
  • University of Science and Technology of China

Zitieren

APA

Ma, S., Li, Z., Sun, D., Su, Y., Li, J., Si, X., & Zhu, J. (2025). Global Search of PKP Precursors With Graph Neural Network: Implications for Scatterers in the Lowermost Mantle. Geophysical Research Letters, 52(17). https://doi.org/10.1029/2025gl115952

Vancouver

Ma S, Li Z, Sun D, Su Y, Li J, Si X, et al. Global Search of PKP Precursors With Graph Neural Network: Implications for Scatterers in the Lowermost Mantle. Geophysical Research Letters. 2025;52(17). doi:10.1029/2025gl115952

BibTeX
@article{Ma2025,
  author = {Ma, Shang and Li, Zefeng and Sun, Daoyuan and Su, Yulong and Li, Jiewen and Si, Xu and Zhu, Jun},
  title = {Global Search of PKP Precursors With Graph Neural Network: Implications for Scatterers in the Lowermost Mantle},
  journal = {Geophysical Research Letters},
  year = {2025},
  volume = {52},
  number = {17},
  doi = {10.1029/2025gl115952}
}
Kostenlos starten →