skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A Distributed Multi-Sensor Machine Learning Approach to Earthquake Early Warning
Our research aims to improve the accuracy of Earthquake Early Warning (EEW) systems by means of machine learning. EEW systems are designed to detect and characterize medium and large earthquakes before their damaging effects reach a certain location. Traditional EEW methods based on seismometers fail to accurately identify large earthquakes due to their sensitivity to the ground motion velocity. The recently introduced high-precision GPS stations, on the other hand, are ineffective to identify medium earthquakes due to its propensity to produce noisy data. In addition, GPS stations and seismometers may be deployed in large numbers across different locations and may produce a significant volume of data consequently, affecting the response time and the robustness of EEW systems.In practice, EEW can be seen as a typical classification problem in the machine learning field: multi-sensor data are given in input, and earthquake severity is the classification result. In this paper, we introduce the Distributed Multi-Sensor Earthquake Early Warning (DMSEEW) system, a novel machine learning-based approach that combines data from both types of sensors (GPS stations and seismometers) to detect medium and large earthquakes. DMSEEW is based on a new stacking ensemble method which has been evaluated on a real-world dataset validated with geoscientists. The system builds on a geographically distributed infrastructure, ensuring an efficient computation in terms of response time and robustness to partial infrastructure failures. Our experiments show that DMSEEW is more accurate than the traditional seismometer-only approach and the combined-sensors (GPS and seismometers) approach that adopts the rule of relative strength.  more » « less
Award ID(s):
1640834 1835692 1745246
PAR ID:
10187422
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the AAAI Conference on Artificial Intelligence
Volume:
34
Issue:
01
ISSN:
2159-5399
Page Range / eLocation ID:
403 to 411
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Bulletin of the Seismological Society of America)
    Mai, P M (Ed.)
    ABSTRACT Detecting offshore earthquakes in real time is challenging for traditional land-based seismic networks due to insufficient station coverage. Application of distributed acoustic sensing (DAS) to submarine cables has the potential to extend the reach of seismic networks and thereby improve real-time earthquake detection and earthquake early warning (EEW). We present a complete workflow of a modified point-source EEW algorithm, which includes a machine-learning-based model for P- and S-wave phase picking, a grid-search location method, and a locally calibrated empirical magnitude estimation equation. Examples are shown with offshore earthquakes from the SeaFOAM DAS project using a 52-km-long submarine cable in Monterey Bay, California, demonstrating the robustness of the proposed workflow. When comparing to the current onshore network, we can expect up to 6 s additional warning time for earthquakes in the offshore San Gregorio fault zone, representing a substantial improvement to the existing ShakeAlert EEW system. 
    more » « less
  2. ; ; ; ; (, Journal of Geophysical Research: Solid Earth)
    Abstract Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real‐time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR‐GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine‐Learning Assessed Rapid Geodetic Earthquake model (M‐LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M‐LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real‐time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes. 
    more » « less
  3. ; ; ; (, Bulletin of the Seismological Society of America)
    ABSTRACT Earthquake ground motions in the vicinity of receivers couple with the atmosphere to generate pressure perturbations that are detectable by infrasound sensors. These so-called local infrasound signals traverse very short source-to-receiver paths, so that they often exhibit a remarkable correlation with seismic velocity waveforms at collocated seismic stations, and there exists a simple relationship between vertical seismic velocity and pressure time series. This study leverages the large regional network of infrasound sensors in Alaska to examine local infrasound from several light to great Alaska earthquakes. We estimate seismic velocity time series from infrasound pressure records and use these converted infrasound recordings to compute earthquake magnitudes. This technique has potential utility beyond the novelty of recording seismic velocities on pressure sensors. Because local infrasound amplitudes from ground motions are small, it is possible to recover seismic velocities at collocated sites where the broadband seismometers have clipped. Infrasound-derived earthquake magnitudes exhibit good agreement with seismically derived values. This proof-of-concept demonstration of computing seismic magnitudes from infrasound sensors illustrates that infrasound sensors may be utilized as proxy vertical-component seismometers, making a new data set available for existing seismic techniques. Because single-sensor infrasound stations are relatively inexpensive and are becoming ubiquitous, this technique could be used to augment existing regional seismic networks using a readily available sensor platform. 
    more » « less
  4. ; ; ; ; ; ; (, The Seismic Record)
    Abstract We present a real-data test for offshore earthquake early warning (EEW) with distributed acoustic sensing (DAS) by transforming submarine fiber-optic cable into a dense seismic array. First, we constrain earthquake locations using the arrival-time information recorded by the DAS array. Second, with site effects along the cable calibrated using an independent earthquake, we estimate earthquake magnitudes directly from strain rate amplitudes by applying a scaling relation transferred from onshore DAS arrays. Our results indicate that using this single 50 km offshore DAS array can offer ∼3 s improvement in the alert time of EEW compared to onshore seismic stations. Furthermore, we simulate and demonstrate that multiple DAS arrays extending toward the trench placed along the coast can uniformly improve alert times along a subduction zone by more than 5 s. 
    more » « less
  5. ; ; ; ; (, Seismological Research Letters)
    Colombia and Ecuador sit at one of the most diverse tectonic regimes in the world, located at the intersection of five tectonic plates (Bird, 2003) encompassing many geophysical hazard regimes, multiple subduction zones, and broad diffuse areas of significant deformation. Notably, the subduction of the Nazca plate under South America has produced at least seven large (Mw 7) and damaging earthquakes since 1900—the largest being the 1906 Mw 8.8 event. Both Colombia and Ecuador have made significant investments in Global Navigation Satellite System (GNSS) networks to study tectonic and volcanic deformation. Earthquake early warning (EEW) systems like the U.S.-operated ShakeAlert system (Murray et al., 2018, 2023) utilize real-time Global Navigation Satellite System (RT-GNSS) to rapidly characterize the largest, most damaging earthquakes in situations where seismic networks alone saturate (Melgar et al., 2015, 2016; Allen and Melgar, 2019; Ruhl et al., 2019). Both Colombia and Ecuador have large vulnerable populations proximal to the coast that may sustain significant damage in these large subduction events (Pulido et al., 2020) and yet farther enough away that an RT-GNSS EEW system could offer significant warning times to these populations and associated infrastructure. We examine the status of the Servicio Geológico Colombiano Geodesia: Red de Estudios de Deformación GNSS network in Colombia and the Escuela Politécnica Nacional GNSS network in Ecuador, their spatial distribution, and the current status of their data streams to determine what augmentations are required to support the real-time detection and modeling of large destructive earthquakes in and near Colombia and Ecuador. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email