Borehole strain monitoring plays a critical role in earthquake precursor research. With the accumulation of observation data, traditional data processing methods struggle to handle the challenges of big data. This study proposes a segmented variational mode decomposition method and a GRU-LUBE deep learning network based on machine learning theory. The algorithm enhances data correlation during decomposition and effectively predicts borehole strain data changes. We extract pre-earthquake anomalies from four-component borehole strain data of the Guza station for two major earthquakes in Sichuan (Wenchuan and Lushan earthquakes), obtaining more comprehensive anomalies than previous studies. Statistical analysis reveals similar abnormal phenomena in the Guza station’s borehole strain data before both earthquakes, suggesting shared crustal stress accumulation and release patterns. These findings highlight the need for further research to improve earthquake prediction and preparedness through understanding underlying mechanisms.
28 January 2022 in Journal of Electrical Engineering & Technology
On 20 April 2013, Lushan experienced an earthquake with a magnitude of 7.0. In seismic assessments, borehole strainmeters, recognized for their remarkable sensitivity and inherent reliability in tracking crustal deformation, are extensively employed. However, traditional data-processing methods encounter challenges when handling massive dataset-s. This study proposes using a Graph WaveNet graph neural network to analyze borehole strain data from multiple stations near the earthquake epicenter and establishes a node graph structure using data from four stations near the Lushan epicenter, covering the years 2010–2013. After excluding the potential effects of pressure, temperature, and rainfall, we statistically analyzed the pre-earthquake anomalies. Focusing on the Guza, Xiaomiao, and Luzhou stations, which are the closest to the epicenter, the fitting results revealed two acceleration events of anomalous accumulation that occurred before the earthquake. Occurring approximately 4 months before the earthquake event, the first acceleration event indicated the pre-release of energy from a weak fault section. Conversely, the acceleration event observed a few days before the earthquake indicated a strong fault section that reached an unstable state with accumulating strain. We tentatively infer that these two anomalous cumulative accelerations may be related to the preparation phase for a large earthquake. This study highlights the considerable potential of graph neural networks in conducting multistation studies of pre-earthquake anomalies.
On 20 April 2013, Lushan experienced a magnitude 7.0 earthquake. In seismic assessments, borehole strain meters, recognized for their remarkable sensitivity and inherent reliability in tracking crustal deformation, are extensively employed. However, traditional data processing methods encounter challenges when handling massive datasets. This study proposes using a graph wavenet graph neural network to analyze borehole strain data from multiple stations near the earthquake epicenter and establishes a node graph structure using data from four stations near the Lushan epicenter, covering years 2010–2013. After excluding the potential effects of pressure, temperature, and rainfall, we statistically analyzed the pre-earthquake anomalies. Focusing on the Guza, Xiaomiao, and Luzhou stations, which are the closest to the epicenter, the fitting results revealed two accelerations of anomalous accumulation before the earthquake. Approximately four months before the earthquake event, one acceleration suggests the pre-release of energy from a weak fault section. Conversely, the acceleration a few days before the earthquake indicated a strong fault section reaching an unstable state with accumulating strain. We tentatively infer that these two anomalous cumulative accelerations may be related to the preparation phase for a large earthquake. This study highlights the considerable potential of graph neural networks in con-ducting multi-station studies of pre-earthquake anomalies.
As a major natural hazard, earthquakes are accompanied by lithospheric stress accumulation and anomalies in multiple physical fields during their preparation process. Identifying pre-earthquake anomalies is therefore of great scientific significance for understanding earthquake preparation and improving earthquake prediction. Taking the 2013 Lushan earthquake in Sichuan, China (Ms 7.0), as a case study, this work presents a comprehensive analysis of geomagnetic and borehole strain observations to investigate the spatiotemporal evolution of pre-earthquake multi-physical-field anomalies. First, Variational Mode Decomposition (VMD) was applied to geomagnetic and borehole strain data to achieve multi-scale signal decomposition, thereby separating long-term background variations from short-period disturbance components. Subsequently, the Pyraformer model was employed to model and predict the high-frequency feature sequences, and the prediction residuals were extracted to quantify pre-earthquake anomalies. The results show that borehole strain anomalies first emerged along local fault segments during the pre-seismic stage and gradually accumulated, whereas geomagnetic anomalies subsequently intensified and accelerated at adjacent stations. Overall, the anomalies exhibited a spatiotemporal evolution pattern characterized by local-to-regional expansion and stage-wise accelerated accumulation. Further analysis indicates that borehole strain anomalies generally preceded geomagnetic anomalies, with a time lag ranging from several days to several weeks between the rapid accumulation stage of borehole strain anomalies and the strengthening stage of geomagnetic anomalies. In addition, the cumulative anomaly curves commonly displayed a pronounced S-shaped growth pattern, reflecting the gradual increase in stress-strain during earthquake preparation and its subsequent transfer to the electromagnetic field response. These findings reveal a coupling relationship between the stress-strain field and the electromagnetic field during the earthquake preparation process. The integrated VMD-Pyraformer framework proposed in this study demonstrates strong stability and reliability in identifying geomagnetic and borehole strain anomalies and provides new observational evidence and an effective analytical approach for multi-station, multi-parameter joint monitoring and pre-earthquake anomaly identification.