This paper presents an efficient method of determining soil parameters for finite element analysis of deep excavation. Due to the limitation of soil tests, field measurements are often used to calibrate in‐situ soil properties. This process is time consuming and computationally cumbersome. In this paper, nonlinear optimization techniques are applied to determine the unknown parameters of an objective function, which is defined as the sum of the square of differences between observed and predicted values. The convergence and stability of the optimization algorithm are confirmed by three well‐known mathematical functions and a hypothetical excavation case under varied ground conditions. Finally, a case study is presented to show the reliability of the proposed soil parameter determination procedure.