EUVIMEDOpdag EUVIMED
Crossref

Variability in Performance of a Machine Learning Seismicity Catalog: Central Italy, 2016–2017

Jaehong Chung, Yifan Yu, Lauro Chiaraluce, Maddalena Michele, Gregory C. Beroza

Seismological Research Letters · 2026-11-01 · 97 (6) · 3638-3646

DOI: 10.1785/0220250453 ↗

At a glance

Journal article in Seismological Research Letters, published online on 2026-04-17. Written by Jaehong Chung and 4 co-authors. Cited 2 times so far (Crossref); 34 references.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Machine learning (ML) catalogs contain many more earthquakes than routine catalogs, but their performance in phase picking and earthquake detection has not been fully evaluated. We develop station-level detection probabilities using logistic regression and combine them across a seismic network to compute spatial magnitude-of-completeness fields. We apply this approach to two catalogs from the 2016–2017 Central Italy sequence that were constructed from the same seismic network, one routine and one ML-based. At the station level, the ML picker increases detection sensitivity by identifying smaller magnitude events and detecting earthquakes at greater distances. Spatially, the magnitude of completeness decreases substantially, with median values shifting from 1.6 to 0.5 for P waves and from 1.7 to 0.5 for S waves. However, the ML catalog also shows greater variability in station-level performance than the routine catalog. These results demonstrate that ML-based improvements in detectability are widespread but spatially nonuniform, highlighting their benefits, their limitations, and the potential for further improvements.

Cite

APA

Chung, J., Yu, Y., Chiaraluce, L., Michele, M., & Beroza, G. C. (2026). Variability in Performance of a Machine Learning Seismicity Catalog: Central Italy, 2016–2017. Seismological Research Letters, 97(6), 3638-3646. https://doi.org/10.1785/0220250453

Vancouver

Chung J, Yu Y, Chiaraluce L, Michele M, Beroza GC. Variability in Performance of a Machine Learning Seismicity Catalog: Central Italy, 2016–2017. Seismological Research Letters. 2026;97(6):3638-3646. doi:10.1785/0220250453

BibTeX
@article{Chung2026,
  author = {Chung, Jaehong and Yu, Yifan and Chiaraluce, Lauro and Michele, Maddalena and Beroza, Gregory C.},
  title = {Variability in Performance of a Machine Learning Seismicity Catalog: Central Italy, 2016–2017},
  journal = {Seismological Research Letters},
  year = {2026},
  volume = {97},
  number = {6},
  pages = {3638--3646},
  doi = {10.1785/0220250453}
}
Start for free →