Application of support vector machine for the fast and accurate reconstruction of nanostructures in optical scatterometry

Nonlinear regression methods, such as local optimization algorithms, are widely used in the extraction of nanostructure profile parameters in optical scatterometry. The success of local optimization algorithms heavily relies on the estimated initial solution. If the initial solution is not appropriately selected, it will either take a long time to converge to the global solution or will result in a local one. Thus, it is of great importance to developing a method to guarantee the capture of a globally optimal solution. In this paper, we propose a method that combines the support vector machine and Levenberg-Marquardt algorithm for the fast and accurate parameters extraction. The SVM technique is introduced to pick out a sub-range in the rough ranges of parameters, in which an arbitrary selected initial solution for the LM algorithm is then able to achieve the global solution with a higher possibility. Simulations and experiments conducted on a one-dimensional Si grating and a deep-etched multilayer grating have demonstrated the feasibility and efficiency of the proposed method.