The Value of Hyperparameter Optimization in Phase-Picking Neural Networks
The Seismic Record · 01.07.2024 · 4 (3) · 231-239
DOI: 10.1785/0320240025 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Seismic Record, online erschienen am 26.09.2024. Verfasst von Yongsoo Park und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 2.0).
Abstract (Originalsprache)
The effectiveness of neural networks for picking seismic phase arrival times has been demonstrated through several case studies, and seismic monitoring programs are starting to adopt the technology into their workflows. However, published models were designed and trained using rather arbitrary choices of hyperparameters, limiting their performance. In this study, we use phase picks from both routine and template-matching analyses from multiple regions (Ridgecrest, California; Kīlauea, Hawaii; Yellowstone, Wyoming–Montana–Idaho) to test a hyperparameter optimization scheme for phase-picking neural networks and to evaluate their performance. We show that a published model, namely PhaseNet (Zhu and Beroza, 2019), can be simplified and improved with reasonable effort and there are preferred choices of hyperparameters that increase the performance. We also show that models optimized based on the arrival times reported in routine event catalogs consistently perform well when picking arrival times of smaller events, which is crucial for many tasks from microseismicity to explosion monitoring.
Zitieren
APA
Park, Y., & Shelly, D. R. (2024). The Value of Hyperparameter Optimization in Phase-Picking Neural Networks. The Seismic Record, 4(3), 231-239. https://doi.org/10.1785/0320240025
Vancouver
Park Y, Shelly DR. The Value of Hyperparameter Optimization in Phase-Picking Neural Networks. The Seismic Record. 2024;4(3):231-239. doi:10.1785/0320240025
BibTeX
@article{Park2024,
author = {Park, Yongsoo and Shelly, David R.},
title = {The Value of Hyperparameter Optimization in Phase-Picking Neural Networks},
journal = {The Seismic Record},
year = {2024},
volume = {4},
number = {3},
pages = {231--239},
doi = {10.1785/0320240025}
}
EUVIMED