• Journal of the Society of Disaster Information
• /
• v.16 no.4
• /
• pp.670-681
• /
• 2020

Purpose: This study aims to derive a PGV prediction equation and to enhance the application of the Onsite EEW technology which has developed through previous studies. Method: The prediction equation for the Onsite EEW derived from earthquake data M≥3.0 and MMI≥II over the past four years. Local seismic risk is estimated using M and PGV deduced from P wave properties. Result: The improved PGV prediction equation estimated the MMI with an average accuracy of 94.8% and the 𝜏_c : Pd method also showed valid performance for alerting local seismic risks. Conclusion: Onsite EEW technology is successfully applied to Korea, and becomes to reduce the blind zone to about 14km.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.133-143
• /
• 2020

Purpose: This study aims to derive a predictive empirical equation for PGV prediction from P-wave using earthquake records in Korea and to verify the reliability of Onsite EEW. Method: The noise of P wave is removed from the observations of 627 seismic events in Korea to derive an empirical equation with PGV on the base rock, and reliability of Onsite alarms is verified from comparing PGV's predictions and observations through simulation using the empirical equation. Result: P-waves were extracted using the Filter Picker from earthquake observation records that eliminated noises, a linear regression with PGV was used to derive a predictive empirical equation for Onsite EEW. Through the on-site warning simulation we could get a success rate of 80% within the MMI±1 error range above MMI IV or higher. Conclusion: Through this study, the design feasibility and performance of Onsite EEWS using domestic earthquake records were verified. In order to increase validity, additional medium-sized seismic observations from abroad are required, the mis-detection of P waves is controlled, and the effect of seismic amplification on the surface is required.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.25 no.2
• /
• pp.71-81
• /
• 2021

This paper presents a real-time, false-pick filter based on deep learning to reduce false alarms of an onsite Earthquake Early Warning (EEW) system. Most onsite EEW systems use P-wave to predict S-wave. Therefore, it is essential to properly distinguish P-waves from noises or other seismic phases to avoid false alarms. To reduce false-picks causing false alarms, this study made the EEWNet Part 1 'False-Pick Filter' model based on Convolutional Neural Network (CNN). Specifically, it modified the Pick_FP (Lomax et al.) to generate input data such as the amplitude, velocity, and displacement of three components from 2 seconds ahead and 2 seconds after the P-wave arrival following one-second time steps. This model extracts log-mel power spectrum features from this input data, then classifies P-waves and others using these features. The dataset consisted of 3,189,583 samples: 81,394 samples from event data (727 events in the Korean Peninsula, 103 teleseismic events, and 1,734 events in Taiwan) and 3,108,189 samples from continuous data (recorded by seismic stations in South Korea for 27 months from 2018 to 2020). This model was trained with 1,826,357 samples through balancing, then tested on continuous data samples of the year 2019, filtering more than 99% of strong false-picks that could trigger false alarms. This model was developed as a module for USGS Earthworm and is written in C language to operate with minimal computing resources.

• Journal of the Society of Disaster Information
• /
• v.14 no.4
• /
• pp.440-449
• /
• 2018

Purpose: This study aims to design and verify an onsite EEWS that extracts the P-wave from a single seismic station and deduce the PGV. Method: The P-wave properties of Pd, Pv, and Pa were calculated by using 12 seismic waveform data extracted from historic seismic records in Korea, and the PGVs were computed using empirical equation on the P properties - PGV relationship and compared with the observed values. Results: Comparison of the observed and estimated PGVs within the alarm level shows the error rate of 86.7% as minimum. By reducing the PTW to 2 seconds, the alarm time can be shortened by 1 second and the seismic blind zone near the epicenter can be shortened by 6 Km. Conclusion: Through this study, we confirmed the availability of the on-site EEWS in Korea. For practical use, it is necessary to develop regression formula and algorithm reflect local effect in Korea by increasing the number of seismic waveform data through continuous observation, and to eliminate the noise from the site.