Developing six hybrid machine learning models based on gaussian process regression and meta-heuristic optimization algorithms for prediction of duration and cost of road tunnels construction

•Developing hybrid meta-heuristic algorithms to predict duration and cost of tunnels.•Utilizing 16 input parameters effective on the duration and cost of tunnels.•Applying 900 datasets obtained from 34 historical tunneling projects.•Sensitivity of the input parameters using mutual information test.•Recognition of the most robust model to duration and cost of tunnels. Tunnels are among essential subsurface projects used for various applications that often encounter instability, cost overruns and time consumption. Forecasting the duration and cost required to construct tunnels is always an essential factor in determining whether an assistant's decision-making system is useful or not. Therefore, research on the duration and cost of tunnels’ construction and the possibility of their distribution is essential, which can be a valid basis for concluding a contract and a tool to optimize the construction plan and reduce costs. In this work, six Gaussian process regression (GPR)-based meta-heuristic optimization algorithms, including GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, and GPR-SSO were developed to predict the duration and cost parameters. 900 datasets, including 16 input parameters obtained through 34 historical road tunnels, were utilized in the models. The performance prediction of the developed models from high to low was GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, GPR-SSO, and GPR, with ranking scores of 42, 36, 30, 22, 19, 13, and 6 (for the duration), and with ranking scores of 41, 35, 29, 23,19, 12, and 6 (for cost), respectively. However, the GPR-PSO hybrid model produced the most accurate results, and it was recommended to predict the duration and cost of road tunnels construction. The sensitivity analysis revealed that the most influential parameters on the duration and cost of tunnelling projects are the drilling machinery system and groundwater, respectively. The friction angle and cross-sectional tunnel were the least effective parameters for the duration and cost.