A devastating MW 7.4 earthquake struck the northern Longitudinal Valley in eastern Taiwan on 3 April 2024. The intense and prolonged aftershock sequence over the following month exposed both the region's tectonic complexity and the challenge of timely earthquake cataloging. Gaps in the initial catalog from the local agency revealed short-term incompleteness, potentially delaying critical hazard assessments and emphasizing the need for more efficient data-processing workflows. To address this issue, we developed an ML-based workflow, AutoQuake, which detects 5x more events and 10x more focal mechanisms than the local agency catalogs. The resulting high-resolution catalog reveals newly developed conjugate faulting between the CRF and LVF systems and showcases the potential of ML-driven workflows for rapid seismic hazard assessment.
Figure: Structural interaction in the northern Longitudinal Valley region. (Left) The black dots indicate the events recorded in the AutoQuake catalog. The green circles and dark red lines represent the 2018–2021 relocated events and fault model, respectively, both from Huang and Wang (2022); The red dashed line highlights the structures newly revealed by the 3 April earthquake sequence, identified through the AutoQuake catalog. (Right) Profile S-S' in NNE-SSW is selected to show the derived focal mechanisms (red: thrust faulting, green: strike-slip faulting, blue: normal faulting) and the comparison with velocity models (Huang et al., 2014).
Data download
Citation
Yang, H.-Y.^, H.-H. Huang*, E.-S. Wu^, H.-A. Chen^, C.-N. Liu, Y.-F. Hsu, W.-T. Liang, and C.-S. Ku (2025), An ML-Enhanced Earthquake Catalog for the 2024 Mw 7.4 Hualien Earthquake Sequence: Insights into Structural Transition from Collision to Subduction in Eastern Taiwan, J. Geophys. Res., 130, e2025JB032792, https://doi.org/10.1029/2025JB032792.