Application of artificial intelligence technology in the study of anthropogenic earthquakes: a review

Abstract

Artificial intelligence (AI) has emerged as a crucial tool in the monitoring and research of anthropogenic earthquakes (AEs). Despite its utility, AEs monitoring faces significant challenges due to the intricate signal characteristics of seismic events, low signal-to-noise ratio (SNR) in data, and insufficient spatial coverage of monitoring networks, which complicate the effective deployment of AI technologies. This review systematically explores recent advancements in AI applications for identifying and classifying AEs, detecting weak signals, phase picking, event localization, and seismic risk analysis, while highlighting current issues and future developmental directions. Key challenges include accurately distinguishing specific anthropogenic seismic events due to their intricate signal patterns, limited model generalizability caused by constrained training datasets, and the lack of comprehensive models capable of handling event recognition, detection, and classification across diverse scenarios. Despite these obstacles, innovative approaches such as data-sharing platforms, transfer learning (TL), and hybrid AI models offer promising solutions to enhance AEs monitoring and improve predictive capabilities for induced seismic hazards. This review provides a scientific foundation to guide the ongoing development and application of AI technologies in AEs monitoring, forecasting, and disaster mitigation.