Artificial intelligence driven tunneling-induced surface settlement prediction

Abstract

There has been an increasing demand for shield tunnel construction due to the extensive utilization and limited land in metropolitan cities. However, the behaviors of soils and rocks exhibit a high level of uncertainty in material modeling. Artificial Intelligence (AI) techniques exhibit huge potential in addressing geotechnical issues that involve non-linear soil-structure interaction. This paper aims to review AI-driven prediction of tunneling-induced surface settlement, focusing on aspects of dataset establishment, input feature selection, and hyperparameter optimization. An overview of AI key applications in surface settlement prediction over the past decades is compiled. Furthermore, the capabilities and limitations of diverse AI techniques are discussed, guiding the selection of methodologies for different scenarios. Subsequently, recent developments such as AI variants, the latest optimization algorithms, and cutting-edge methods are illustrated. Lastly, possible countermeasures of AI for challenges in pragmatic applications are proposed, offering orientations for further research in AI-driven tunneling-induced surface settlement prediction.