Work

Integrated Transformer approach for immersed-tunnel settlement prediction considering spatial heterogeneity and temporal degradation of sand filling compactness

Year: 2026

Type: article

Abstract: Settlement stability of immersed tunnels is strongly affected by the spatial heterogeneity and long-term degradation of sand filling compactness. Existing settlement prediction methods mainly rely on historical monitoring data while overlooking the time-dependent evolution of foundation compactness, resulting in insufficient prediction accuracy under heterogeneous geological and operational conditions. To overcome these limitations, this study develops an integrated Transformer-based approach that combines elastic wave detection, field monitoring data, and compactness degradation modeling for long-term settlement prediction of immersed tunnels. Elastic wave testing is first employed to characterize the two-dimensional distribution of sand filling compactness, and an empirical evolution model is established to capture the temporal degradation characteristics under different filling conditions. Subsequently, an improved IASB-Transformer model is developed to integrate settlement time-series information with time-varying compactness features, enabling effective learning of the coupled spatial–temporal deformation patterns of tunnel foundations. The results demonstrate that the proposed IASB-Transformer achieved an average coefficient of determination (R 2 ) of 0.951 across the evaluated monitoring points, outperforming the vanilla Transformer, LSTM, CNN, and RF models. At the representative monitoring point A35, incorporating the time-varying compactness sequence increased R 2 from 0.87 to 0.94, corresponding to an absolute increase of 0.07 and an approximately 8 % relative improvement in R 2 . The proposed model also exhibited lower prediction errors and more stable performance under heterogeneous filling conditions. The developed framework provides a physically interpretable approach for long-term settlement prediction and differential-settlement assessment of immersed tunnels considering the evolving condition of foundation filling materials.

Source: Tunnelling and Underground Space Technology

DOI: 10.1016/j.tust.2026.108156

Authors: Ziyao Xu, Zhengzhong Qiu, Ailan Che, Hanxu Zhou, Ganglie Yuan

Institutions: Shenzhen University, Shanghai Jiao Tong University

Language: English

Topic: Geotechnical Engineering and Analysis

Subfield: Safety, Risk, Reliability and Quality

Field: Engineering

Domain: Physical Sciences

SDGs: Industry, innovation and infrastructure, Sustainable cities and communities

Open Access status: hybrid

Estimated APC paid: $3,820