Enhanced graph neural network for rapid multi-field seismic prediction in shield tunnels with contact loss defects

Key Points

• Improved seismic prediction was achieved using an enhanced graph neural network model, demonstrating effectiveness in identifying defects.
• The approach leveraged machine learning techniques to accurately predict seismic activities related to contact loss in tunnels.
• Assessment involved analyzing the relationship between defects and seismic data collected in specific shield tunnels.
• This highlights the need for advanced prediction methods to ensure structural safety, particularly in urban infrastructure.