Measurement and prediction of tunnelling-induced ground settlement in karst region by using expanding deep learning method

This paper presents the measurement and prediction of the tunnelling-induced surface response in karst ground, Guangzhou, China. A predictive method of ground settlement is proposed named as the expanding deep learning method. This method kinetically uses the expanding tunnelling data to predict ground settlement in real time. Four types of deep learning methods are compared, including artificial neural network (ANN), long short-term memory neural networks (LSTM), gated recurrent unit neural networks (GRU), and 1d convolutional neural networks (Conv1d). Based on static Pearson correlation coefficient, a kinetic correlation analysis method is proposed to evaluate the variable significance of input data on the ground settlement. The effect of cemented karst caves and variable geological conditions are then analysed. The results indicate that the expanding Conv1d model precisely predict the tunnelling-induced ground settlement. The kinetic correlation analysis can reflect the variable influence of geological condition and tunnelling operation parameters on the ground settlement.

Automated summary

This paper presents the measurement and prediction of tunnelling-induced surface response in karst ground in Guangzhou, China. A predictive method called the expanding deep learning method is proposed, which uses expanding tunnelling data to predict ground settlement in real time. Results show that the expanding Conv1d model can accurately predict the tunnelling-induced ground settlement, and kinetic correlation analysis reflects the variable influence of geological conditions and tunnelling operation parameters on ground settlement.