Machine Learning–based Analysis of the 2015 M5.8 Alxa Left Banner Earthquake Sequence
Zhang Fan, Han Xiao-Ming, Pei Dong-Yang*, Cui Feng-Zhi, Bai Yi-Hang, Yang Xiao-Zhong
1. College of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
2. Inner Mongolia Autonomous Region Seismological Bureau, Hohhot 010051, China
3. College of Mathematics and Physics, North China Electric Power University, Beijing 102206, China
Abstract Machine learning (ML) efficiently and accurately processes dense seismic array data, improving earthquake catalog creation, which is crucial for understanding earthquake sequences and fault systems; analyzing its reliability is also essential. An M5.8 earthquake struck Alxa Left Banner, Inner Mongolia, China on April 15, 2015, a region with limited CENC monitoring capabilities, making analysis challenging. However, abundant data from ChinArray provided valuable observations for assessing the event. This study leveraged ChinArray data from the 2015 Alxa Left Banner earthquake sequence, employing machine learning (specifically PhaseNet, a deep learning method, and GaMMA, a Bayesian approach) for automated seismic phase picking, association, and location analysis. Our generated catalog, comprising 10,432 phases from 708 events, is roughly ten times larger than the CENC catalog,encompassing all CENC events with strong consistency. A slight magnitude overestimation is observed only at lower magnitudes. Furthermore, the catalog adheres to the Gutenberg-Richter and Omori laws spatially, temporally, and in magnitude distribution, demonstrating its high reliability. Double-difference tomography refined locations for 366 events, yielding a more compact spatial distribution with horizontal errors within 100m, vertical errors within 300m, and travel-time residuals within 0.05s. Depths predominantly range from 10-30km. Aftershocks align primarily NEE, with the mainshock east of the aftershock zone. The near-vertical main fault plane dips northwestward, exhibiting a Y-shaped branching structure, converging at depth and expanding towards the surface. FOCMEC analysis, using first motion and amplitude ratios, yielded focal mechanism solutions for 10 events, including the mainshock. These solutions consistently indicate a strike-slip mechanism with a minor extensional component. Integrating the earthquake sequence's spatial distribution and focal mechanisms suggests the seismogenic structure is a negative flower structure, consistent with the Dengkou-Benjing fault. Comparing the CENC and ML-generated catalogs using the maximum curvature (MAXC) method reveals a 0.6 decrease in completeness magnitude (MC). However, magnitude-frequency distribution discrepancies above the MAXC-estimated MC suggest MAXC may underestimate both MC and the b-value. This study analyzes the 2015 Alxa Left Banner M5.8 earthquake using a reliable, MLgenerated earthquake catalog, revealing detailed information about the sequence, faulting structure, aftershock distribution, and stress characteristics.
Fund: This research project is funded by the Inner Mongolia Natural Science Foundation (No. 2024MS04021), the Science and Technology Plan of Inner Mongolia Autonomous Region (No. 2023YFSH0004) and the Director Fund of the Inner Mongolia Autonomous Region Seismological Bureau (No. 2023GG01, No. 2023GG02, No. 2023MS05, No. 2023QN13).
About author: Zhang Fan received his Master's degree in Statistics from Inner Mongolia University of Finance and Economics in 2014. Currently, he serves as a Senior Engineer at the Inner Mongolia Seismic Station, Inner Mongolia Autonomous Region Seismological Bureau, and has been pursuing a Ph.D. at the School of Control and Computer Engineering, North China Electric Power University since September 2019. His research focuses on earthquake prediction and machine learning.
Cite this article:
. Machine Learning–based Analysis of the 2015 M5.8 Alxa Left Banner Earthquake Sequence[J]. APPLIED GEOPHYSICS, 2025, 22(3): 711-728.
2025, Vol. 22 
