The application of deep learning to seismic electric signal (SES) anomaly detection remains underexplored in geophysics. This study introduces the integration of a 1D convolutional neural network (1DCNN) with a self-attention mechanism to automate SES analysis in a station in a certain place in China. Utilizing physics-informed data augmentation, our framework adapts to real-world interference scenarios, including subway operations and tidal fluctuations. The model achieves an F1-score of 0.9797 on a 7-year dataset, demonstrating superior robustness and precision compared to traditional manual interpretation. This work establishes a practical deep learning solution for real-time geoelectric anomaly monitoring, offering a transformative tool for earthquake early warning systems.

Time series anomaly detection is one of the core tasks in time series data analysis, aiming to identify abnormal events or behaviors from normal temporal data, and plays a critically important role across numerous domains. In seismic data analysis, the identification of anomaly intervals preceding earthquake occurrences holds significant research value for subsequent earthquake prediction. This study evaluates the effectiveness of a large time series model named Timer in detecting anomalies within seismic time series data collected by tiltmeters. As a multi-task time series model, Timer has achieved state-of-the-art performance on forecasting, imputation, and anomaly detection tasks across multiple benchmark datasets, and is therefore selected as the core model in this study. This study employs the Timer model combined with the Constrained Gaussian-Noise Optimization and Smoothing (COGNOS) method for anomaly detection in seismic time series data, and compares the results with those of the original Timer model. Additionally, several mainstream time series anomaly detection models are selected as baselines for comparison. To comprehensively validate the model’s performance, comparative experiments were conducted on both the publicly available SIRGAS GNSS dataset and a real-world seismic dataset collected by tiltmeters. The experimental results demonstrate that the Timer model exhibits outstanding performance in anomaly detection on seismic time series data, and achieves further improvement when integrated with the COGNOS method.

Geomagnetically induced geoelectric fields can exhibit substantial spatial variability because regional subsurface electrical structures affect surface electromagnetic responses. This study characterized the induced geoelectric field across mainland China during the extreme geomagnetic storm of 10 May 2024, using observations from the China Geoelectric Network. We evaluated changes in field intensity, ratios between collinear short- and long-dipole measurements, and regional variations in polarization direction, with particular emphasis on the onset of the storm. The geoelectric response showed pronounced spatial heterogeneity, with substantial differences among stations during storm onset. At most stations, measurements from collinear short and long dipoles maintained consistent ratios, indicating stable local scaling between the two electrode configurations. In contrast, polarization directions inferred from the long-dipole measurements showed no uniform relationship with local land–sea orientations. High-density electrical exploration data further supported this interpretation. These findings indicate that local subsurface electrical structures play an important role in controlling geoelectric field measurements and their responses to geomagnetic disturbances. This study provides a quantitative assessment of storm-time geoelectric field variations across mainland China and establishes a basis for investigating regional electromagnetic phenomena associated with induced geoelectric fields.