Scientific Reports· 2025Q1
Integrating fiber-optic seismic arrays into earthquake early warning systems with the dEPIC framework
- 5citations
- Q1SCImago
- 2025year
Short summary
The dEPIC framework, the first operational system integrating Distributed Acoustic Sensing (DAS) fiber-optic cables into earthquake early warning (EEW), has been deployed and tested on a submarine cable, achieving sub-second processing for accurate earthquake detection.
AI-generated from the title and abstract; the full text is not read.
Key points
- dEPIC is the first operational framework integrating DAS fiber-optic cables into earthquake early warning (EEW).
- The system was deployed on a submarine cable in Monterey Bay, California.
- It uses GPU-accelerated machine learning for rapid seismic event detection (sub-second processing).
- dEPIC accurately detected both onshore and offshore earthquakes in tests.
- The framework is modular and designed for adaptation to future DAS deployments.
AI-generated from the title and abstract; the full text is not read.
Abstract
Distributed Acoustic Sensing (DAS) can enhance earthquake early warning (EEW) by transforming existing fiber-optic cables into dense seismic arrays, including in offshore areas with sparse instrumentation. We present dEPIC (DAS-Earthquake Point-source Integrated Code), the first operational DAS-integrated EEW framework, deployed on a submarine cable in Monterey Bay, California, and designed to operate independently or jointly with ShakeAlert's EPIC algorithm. dEPIC combines GPU-accelerated machine-learning phase picking, grid-search location, and empirical magnitude estimation, with real-time quality metrics to suppress unstable solutions. In event replays and continuous data tests, dEPIC detected both onshore and offshore earthquakes accurately with sub-second processing time. The modular, edge-computing design enables adaptation to future DAS deployments to improve existing EEW systems like ShakeAlert.
The authors' abstract, as published at the source. Scientific Reports, 2025 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science