A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan

A timely, high-resolution earthquake catalog is crucial for estimating seismic evolution and assessing hazards. This study aims to introduce a deep-learning-based real-time microearthquake monitoring system (RT-MEMS) for Taiwan, designed to provide rapid and reliable earthquake catalogs. The system...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei-Fang Sun, Sheng-Yan Pan, Yao-Hung Liu, Hao Kuo-Chen, Chin-Shang Ku, Che-Min Lin, Ching-Chou Fu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3353
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330800783261696
author Wei-Fang Sun
Sheng-Yan Pan
Yao-Hung Liu
Hao Kuo-Chen
Chin-Shang Ku
Che-Min Lin
Ching-Chou Fu
author_facet Wei-Fang Sun
Sheng-Yan Pan
Yao-Hung Liu
Hao Kuo-Chen
Chin-Shang Ku
Che-Min Lin
Ching-Chou Fu
author_sort Wei-Fang Sun
collection DOAJ
description A timely, high-resolution earthquake catalog is crucial for estimating seismic evolution and assessing hazards. This study aims to introduce a deep-learning-based real-time microearthquake monitoring system (RT-MEMS) for Taiwan, designed to provide rapid and reliable earthquake catalogs. The system integrates continuous data from high-quality seismic networks via SeedLink with deep learning models and automated processing workflows. This approach enables the generation of an earthquake catalog with higher resolution and efficiency than the standard catalog announced by the Central Weather Administration, Taiwan. The RT-MEMS is designed to capture both background seismicity and earthquake sequences. The system employs the SeisBlue deep learning model, trained with a local dataset, to process continuous waveform data and pick P- and S-wave arrivals. Earthquake events are then associated and located using a modified version of PhasePAPY. Three stable RT-MEMS have been established in Taiwan: one for monitoring background seismicity along a creeping fault segment and two for monitoring mainshock–aftershock sequences. The system can provide timely information on changes in seismic activity following major earthquakes and generate long-term catalogs. The refined catalogs from RT-MEMS contribute to a more detailed understanding of seismotectonic structures and serve as valuable datasets for subsequent research.
format Article
id doaj-art-21b0e89712d24a2e89afd9000f8ed336
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-21b0e89712d24a2e89afd9000f8ed3362025-08-20T03:46:49ZengMDPI AGSensors1424-82202025-05-012511335310.3390/s25113353A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for TaiwanWei-Fang Sun0Sheng-Yan Pan1Yao-Hung Liu2Hao Kuo-Chen3Chin-Shang Ku4Che-Min Lin5Ching-Chou Fu6Department of Geosciences, National Taiwan University, Taipei City 10617, TaiwanDepartment of Geosciences, National Taiwan University, Taipei City 10617, TaiwanDepartment of Geosciences, National Taiwan University, Taipei City 10617, TaiwanDepartment of Geosciences, National Taiwan University, Taipei City 10617, TaiwanInstitute of Earth Sciences, Academia Sinica, Taipei City 115201, TaiwanNational Center for Research on Earthquake Engineering, National Institutes of Applied Research, Taipei City 106219, TaiwanInstitute of Earth Sciences, Academia Sinica, Taipei City 115201, TaiwanA timely, high-resolution earthquake catalog is crucial for estimating seismic evolution and assessing hazards. This study aims to introduce a deep-learning-based real-time microearthquake monitoring system (RT-MEMS) for Taiwan, designed to provide rapid and reliable earthquake catalogs. The system integrates continuous data from high-quality seismic networks via SeedLink with deep learning models and automated processing workflows. This approach enables the generation of an earthquake catalog with higher resolution and efficiency than the standard catalog announced by the Central Weather Administration, Taiwan. The RT-MEMS is designed to capture both background seismicity and earthquake sequences. The system employs the SeisBlue deep learning model, trained with a local dataset, to process continuous waveform data and pick P- and S-wave arrivals. Earthquake events are then associated and located using a modified version of PhasePAPY. Three stable RT-MEMS have been established in Taiwan: one for monitoring background seismicity along a creeping fault segment and two for monitoring mainshock–aftershock sequences. The system can provide timely information on changes in seismic activity following major earthquakes and generate long-term catalogs. The refined catalogs from RT-MEMS contribute to a more detailed understanding of seismotectonic structures and serve as valuable datasets for subsequent research.https://www.mdpi.com/1424-8220/25/11/3353real-time microearthquake monitoring systemdeep learningSeedLinkautomated workflowearthquake catalog
spellingShingle Wei-Fang Sun
Sheng-Yan Pan
Yao-Hung Liu
Hao Kuo-Chen
Chin-Shang Ku
Che-Min Lin
Ching-Chou Fu
A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
Sensors
real-time microearthquake monitoring system
deep learning
SeedLink
automated workflow
earthquake catalog
title A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
title_full A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
title_fullStr A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
title_full_unstemmed A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
title_short A Deep-Learning-Based Real-Time Microearthquake Monitoring System (RT-MEMS) for Taiwan
title_sort deep learning based real time microearthquake monitoring system rt mems for taiwan
topic real-time microearthquake monitoring system
deep learning
SeedLink
automated workflow
earthquake catalog
url https://www.mdpi.com/1424-8220/25/11/3353
work_keys_str_mv AT weifangsun adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT shengyanpan adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT yaohungliu adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT haokuochen adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT chinshangku adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT cheminlin adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT chingchoufu adeeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT weifangsun deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT shengyanpan deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT yaohungliu deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT haokuochen deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT chinshangku deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT cheminlin deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan
AT chingchoufu deeplearningbasedrealtimemicroearthquakemonitoringsystemrtmemsfortaiwan