Abstarct: Excavation of underground spaces is associated with ground displacement, deformation, and surface settlement. Investigating and predicting these deformations, particularly for urban tunnels, is of critical importance, and the accuracy of such predictions heavily depends on the type and level of the models used, as well as the geotechnical parameters. The surrounding ground of the tunnel is subject to inherent uncertainty in geotechnical parameters. The aim of this research is to examine the impact of the inherent uncertainty of geotechnical parameters on settlement caused by tunnel excavation. This study focuses on the Sadr-Niayesh tunnel project, and to assess this uncertainty, the range of parameter variations was obtained from the results of performed tests. Then, using the Plaxis 3D software, the settlement resulting from the tunnel excavation was calculated baxsed on the average data from the tests. A sensitivity analysis was conducted on the parameters of elastic modulus, cohesion, and friction angle by considering one parameter as variable while keeping the other two parameters constant. A total of 150 models were constructed for this wide range of data. Subsequently, a predictive neural network model was developed to obtain the settlement values baxsed on the results. Using the Monte Carlo technique, 1000 random data points were generated, and settlement was predicted using the neural network. Additionally, the distribution function of each parameter was plotted using the Easy Fit software. The mean predicted settlement by the neural network was 24.3 mm, with a standard deviation of 2.6, and the distribution function curve exhibited slight positive skewness. The results show that the settlement values obtained from the Plaxis 3D model with average parameters predict with 90% accuracy compared to the measured data. Furthermore, the neural network-baxsed model also demonstrated high accuracy, with a 98% match to the numerical modeling. Additionally, the uncertainty analysis of geotechnical parameters indicates that the uncertainty in the elastic modulus has the greatest impact, while the friction angle and cohesion parameters have less influence on surface settlement.