← Back to Sessions

Implementation of a Machine Learning Classifier in the Real-Time EPIC Earthquake Early Warning Algorithm

Description: 

Machine Learning (ML) has been a hot topic in numerous research domains in recent years. In the field of seismology, researchers have developed ML classifiers that distinguish between different types of incoming signals with a high degree of accuracy when applied to testing datasets. But how well do these ML classifiers perform when implemented in a real-time Earthquake Early Warning (EEW) system?

ShakeAlert is the US West Coast EEW system, which now delivers alerts of impending shaking from earthquakes to users throughout California, Oregon, and Washington. The Earthquake Point-source Integrated Code (EPIC) (formerly ElarmS) algorithm is one of two algorithms currently running in the production ShakeAlert EEW System. EPIC is fast, usually the first ShakeAlert algorithm to alert, and can create accurate point-source estimates of earthquake magnitudes and locations using a minimum of 1 sec of data from one station, and 0.5 sec of data from three additional stations.

We implemented the Meier et al., 2019 ML classifier into the EPIC algorithm with the goal of reducing the number of false triggers coming into the system. This version of EPIC (“mEPIC”) has been running in real-time since April 2023. In this presentation, we give an overview of the real-time mEPIC algorithm and its performance over the past year.

Session: End-to-End Advancements in Earthquake Early Warning Systems [Poster Session]

Type: Poster

Date: 5/3/2024

Presentation Time: 08:00 AM (local time)

Presenting Author: Angie

Student Presenter: No

Invited Presentation: 

Authors