The issue of tunneling has long been of interest to mankind and one of the options to reduce the distance of roads, access to difficult areas, create shelters and access to the ground. There are different types of tunnels and its drilling methods vary according to the use of the tunnels. Today, most tunnels are drilled with mechanized methods that are faster, safer, easier, and more economical and practical. One of the important points in using Mechanical Excavation method in tunneling is to correctly predict the performance or in other words to predict the progress of the Tunnel Boring Machine. Predicting and estimating the progress of tunnels and drilling machines is very important in tunnel construction projects. Accurate estimation of tunnel progress leads to accurate estimation of tunnel construction time and subsequent estimation of tunnel construction costs. One of the well-known and practical indicators in the progress of the Tunnel Boring Machine is the Field Penetration Index (FPI). Various studies have been conducted to predict and estimate the Field Penetration Index and various relationships have been presented by renowned researchers around the world. In the present study, an attempt has been made to develop relationships for predicting and estimating the Field Penetration Index. Using 4 methods of C RT, M5P, CUBIST and GEP, which are a subset of Supervised Learning Methods, models were developed to predict the Field Penetration Index and the efficiency and validity of the developed models compared to similar global models. It was evaluated and finally concluded that Supervised Learning Methods can accurately predict the Field Penetration Index for the Tunnel Boring Machine.