Modelling tunnel squeezing using gene expression programming: a case study

Abstract

Squeezing is a well-known geotechnical phenomenon in the excavation of underground spaces, especially tunnels. Squeezing occurs under different geotechnical conditions in weak rock masses. A study was carried out to develop a mathematical and practical model to predict squeezing so that risk mitigation measures can be taken if necessary. A mathematical model based on a gene expression programming algorithm was developed using a database of 115 squeezing case histories. Four model performance evaluation criteria – specificity, sensitivity, accuracy and Matthew's correlation coefficient – and the receiver operating characteristic curve were then assessed based on a testing dataset. The accuracy of the model was also compared with that of previously developed models. Found to be able to determine squeezing with acceptable accuracy, the model was then used to investigate squeezing-prone areas in the Beheshtabad water-conveyance tunnel in Iran.