Using LSTM Neural Networks for Onsite Earthquake Early Warning

Wang, Chia-Yu; Huang, Ting‐Chung; Wu, Yih‐Min

doi:10.1785/0220210197

Cited by 27 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Onsite prediction of the final ground-motion intensity at a target site using the first few seconds of its observations is a major topic of EEW (Nakamura 1988;Wu and Kanamori 2005;Spallarossa et al 2018). Recently, this has been approached using ML techniques, such as random forest (Hu et al 2023), CNN (Jozinović et al 2020;Zhang et al 2022b), support vector machine , Graph Neural Network (Bloemheuvel et al 2022), and LSTM (Wang et al 2022b(Wang et al , 2023a. Additionally, ML has been applied to discriminate in real-time whether a signal stems from an actual earthquake based on the initial part of ground motions (Li et al 2018;Meier et al 2019;Liu et al 2022).…”

Section: Prediction Of Ground-motion Intensity From Time Seriesmentioning

confidence: 99%

Recent advances in earthquake seismology using machine learning

Kubo,

Naoi,

Kano

2024

Earth Planets Space

View full text Add to dashboard Cite

Given the recent developments in machine-learning technology, its application has rapidly progressed in various fields of earthquake seismology, achieving great success. Here, we review the recent advances, focusing on catalog development, seismicity analysis, ground-motion prediction, and crustal deformation analysis. First, we explore studies on the development of earthquake catalogs, including their elemental processes such as event detection/classification, arrival time picking, similar waveform searching, focal mechanism analysis, and paleoseismic record analysis. We then introduce studies related to earthquake risk evaluation and seismicity analysis. Additionally, we review studies on ground-motion prediction, which are categorized into four groups depending on whether the output is ground-motion intensity or ground-motion time series and the input is features (individual measurable properties) or time series. We discuss the effect of imbalanced ground-motion data on machine-learning models and the approaches taken to address the problem. Finally, we summarize the analysis of geodetic data related to crustal deformation, focusing on clustering analysis and detection of geodetic signals caused by seismic/aseismic phenomena. Graphical Abstract

show abstract

Section: Prediction Of Ground-motion Intensity From Time Seriesmentioning

confidence: 99%

Recent advances in earthquake seismology using machine learning

Kubo,

Naoi,

Kano

2024

Earth Planets Space

View full text Add to dashboard Cite

show abstract

“…To be more precise, it takes information from a sensor at a location to detect earthquakes and generate alerts at the same location using a single sensor, with all algorithm processing taking place at that station (Allen and Melgar, 2019;Bindi et al, 2015;Picozzi et al, 2015). In general, on-site EEWS serves a significant role in bridging the gap of the blind zone, which frequently experiences the worst ground shaking and where an EEWS cannot issue an alarm close to the epicentre (Chen et al, 2015;Wang et al, 2022). The basic form of an on-site EEWS can be a ground motion threshold-based method that sounds an alarm or warning as soon as unusual or harmful ground motion is discovered.…”

Section: Classification Of the Earthquake Early Warning Systems Based...mentioning

confidence: 99%

Earthquake early warning systems based on low-cost ground motion sensors: A systematic literature review

et al. 2022

View full text Add to dashboard Cite

Earthquake early warning system (EEWS) plays an important role in detecting ground shaking during an earthquake and alerting the public and authorities to take appropriate safety measures, reducing possible damages to lives and property. However, the cost of high-end ground motion sensors makes most earthquake-prone countries unable to afford an EEWS. Low-cost Microelectromechanical systems (MEMS)-based ground motion sensors are becoming a promising solution for constructing an affordable yet reliable and robust EEWS. This paper contributes to advancing Earthquake early warning (EEW) research by conducting a literature review investigating different methods and approaches to building a low-cost EEWS using MEMS-based sensors in different territories. The review of 59 articles found that low-cost MEMS-based EEWSs can become a feasible solution for generating reliable and accurate EEW, especially for developing countries and can serve as a support system for high-end EEWS in terms of increasing the density of the sensors. Also, this paper proposes a classification for EEWSs based on the warning type and the EEW algorithm adopted. Further, with the support of the proposed EEWS classification, it summarises the different approaches researchers attempted in developing an EEWS. Following that, this paper discusses the challenges and complexities in implementing and maintaining a low-cost MEMS-based EEWS and proposes future research areas to improve the performance of EEWSs mainly in 1) exploring node-level processing, 2) introducing multi-sensor support capability, and 3) adopting ground motion-based EEW algorithms for generating EEW.

show abstract

“…However, it may meet the limitations in terms of source rupture area. Recently, the machine learning (ML) approach is evolved and is widely used for the EEW (Allen and Melgar 2019;Wang et al 2022). The ML approach has the potential to overcome the limitation of the current EEW approaches.…”

Section: Summary and Future Recommendationsmentioning

confidence: 99%

Progress on the earthquake early warning and shakemaps system using low-cost sensors in Taiwan

Yang

2022

Geosci. Lett.

Self Cite

View full text Add to dashboard Cite

Building an earthquake early warning (EEW) network requires the installation of seismic instruments around the seismogenic zone. Using low-cost sensors to build a seismic network for EEW and to generate shakemaps is a cost-effective way in the field of seismology. The National Taiwan University (NTU) network employing 762 P-Alert low-cost sensors based on micro-electro-mechanical systems (MEMS) technology is operational for almost the last 10 years in Taiwan. This instrumentation is capable of recording the strong ground motions of up to ± 2 g and is dense enough to record the near-field ground motion. The NTU system has shown its importance during various earthquakes that caused damage in Taiwan. Although the system is capable of acting as a regional as well as an onsite warning system, it is particularly useful for onsite warning. Using real-time seismic signals, each P-Alert device provided a 2–8 s warning time for the near-source earthquake regions situated in the blind zone of the Central Weather Bureau (CWB) regional EEW system, during the 2016 $${{{M}}}_{{{w}}}$$ M w 6.4 Meinong and 2018 $${{{M}}}_{{{w}}}$$ M w 6.4 Hualien earthquakes. The shakemaps plotted by the P-Alert dense network help to assess the damage pattern and act as key features in the risk mitigation process. These shakemaps are delivered to the intended users, including the disaster mitigation authorities, for possible relief purposes. Currently, the P-Alert network can provide peak ground acceleration (PGA), peak ground velocity (PGV), spectral acceleration ($${S}_{a}$$ S a ) at different periods, and CWB intensity shakemaps. Using shakemaps, it is found that PGV is a better indicator of damage detection than PGA. Encouraged by the performance of the P-Alert network, more instruments are installed in Asia-Pacific countries.

show abstract

Using LSTM Neural Networks for Onsite Earthquake Early Warning

Cited by 27 publications

References 22 publications

Recent advances in earthquake seismology using machine learning

Recent advances in earthquake seismology using machine learning

Earthquake early warning systems based on low-cost ground motion sensors: A systematic literature review

Progress on the earthquake early warning and shakemaps system using low-cost sensors in Taiwan

Contact Info

Product

Resources

About