Self-supervised learning waveform inversion for seismic forward-prospecting in tunnels: A case study in Pearl River Delta Water Resources Allocation Project in China

Tunnel and underground engineering construction often encounter unfavorable geology, leading to disasters such as water and mud inrushes, landslides, etc. In order to prevent geological hazards, it is important to look ahead and predict the location and distribution of adverse geology ahead of the tunnel face. This process is known as seismic forward-prospecting in tunnels, and it typically requires an accurate calculation of velocity. Seismic waveform inversion methods based on deep learning have demonstrated potential in estimating velocity from synthetic seismic data. However, the superiority of these methods over traditional ones on field data is still an area of active research. Here, we use the Pearl River Delta Water Resources Allocation Project in China as an example to develop a self-supervised learning waveform inversion method for building a reliable velocity distribution in front of the tunnel. By introducing the background velocity as large-scale information and implementing multi-scale loss functions, the previous self-supervised learning inversion method on synthetic data is improved. Additionally, the corresponding network-based workflow for field data is proposed. To demonstrate the effectiveness of the proposed method, we conducted a comparison with practical tunneling exposure, where the low-velocity zone corresponds with the fault-fractured zones and the water-flowing zones. This indicates that the results obtained from our proposed method can be used as geological guidance for safe tunneling practices. In the end, the applicability and disadvantages of the proposed deep-learning inversion method for seismic forward-prospecting in tunnels are discussed.