On-Site Earthquake Early Warning Using Smartphones

Abstract

In this study, the measured accelerations of a single smartphone were used to provide an earthquake early warning system. In the presented system, after the smartphone is triggered, the triggering event is then classified as an earthquake event or not. Once an earthquake event is detected, the peak ground acceleration is then predicted every second until 10 s after the trigger. These predictions are made by the neural network classifier and predictor embedded in the smartphone, and an alert can be issued if a large peak ground acceleration is predicted. The proposed system is unique among approaches that use crowdsourcing ideas for earthquake early warning because the proposed system provides on-site earthquake early warning. In general, the accuracy rates of the earthquake classifications and peak ground acceleration predictions of the system were quite high according to the results of large amounts of earthquake and non-earthquake data. More specifically, according to said earthquake data, 96.9% of the issued alerts would be correct and 61.9% of the earthquakes that exceeded the threshold would have resulted in an alert being issued before the arrival of the peak ground acceleration. Among the false negative cases, approximate 97.8% would occur because of negative lead time. Using the shake table tests of worldwide and Meinong earthquake datasets, the proposed approach is confirmed to be quite promising.

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

“…There is minimal information in the literature on any systems that use smartphones as their ground motion sensors for on-site approaches except the one implemented by Hsu and Nieh (2020). Thus, we have mainly discussed implementations that use MEMS-based sensors.…”

“…(2012) BLESeisWon et al (2020) TaiwanHsu and Nieh (2020) China Hu et al (2021) Italy Picozzi et al (2015) and D'Alessandro et al (2020) Northern India Mittal et al (2019) Public alert generation Taiwan Chen et al (2015) China Peng et al (2021a) Quake Catcher Network* Cochran et al (2009) MyShake* Kong et al (2016a) and Kong et al (2020b) Community Seismic Network* Clayton et al (2015) and Faulkner et al (2011) Earthquake Network* Finazzi (2020) and Bossu et al (2021) Google* Allen and Stogaitis (2022) South Korea Lee et al (2019a) and Wu et al (2021) Taiwan Wu et al (2013a) China Peng et al(2013) …”

The scaling of PGA with IV2p and its potential for Earthquake Early Warning in Thessaly (Central Greece)

“…It is an alternative to using a Pd relationship and, therefore, leads to practical applications for early warning (Festa et al, 2008). Applications of IV2p include recordings by deployments of standard seismological instruments (e.g., Brondi et al, 2015;Spallarossa et al, 2019), as well as smartphones (Hsu and Nieh, 2020). This onsite approach has the advantage of eliminating network design factors (such as requiring multiple suitable locations for instrument installation), while being more immediate; essentially, earthquake location is no longer required.…”

“…In Thessaly (Central Greece), urban areas are located near major active faults increasing the threat of strong seismic events, with, possibly, devastating ramifications for financial and industrial activities, as well as the safety of local population. Advances in signal processing, telecommunications and seismology have gradually rendered the concept of a reliable Earthquake Early Warning System (EEWS) not only feasible, but quite reliable as well (Nakamura, 1988;Kanamori et al, 1997;Allen and Kanamori, 2003;Kanamori, 2005;Simons et al, 2006;Allen, 2007;Gasparini et al, 2011;Vallianatos, 2013, 2015;Parolai et al, 2015;Hsu and Nieh, 2020;Brooks et al, Volume 58 2021). Damages from an impending strong motion can be reduced by taking mitigation measures suitable for the given warning time (Espinosa-Aranda et al, 1995;Wu et al, 1998;Iannacone et al, 2010;Beltramone and Gomes, 2021).…”

Generating Phone-quality Records to Train Machine Learning Models for Smartphone-based Earthquake Early Warning

“…CPC used this information to detect earthquake, and calculated earthquake magnitude, epicenter and origin time. Hsu and Nieh (2020) also proposed a smartphone-based EEW system. This system is an on-site one that only used one smartphone for earthquake detection.…”