Application of artificial neural networks to compact mask models in optical lithography simulation

Abstract

Compact mask models provide an alternative to speed up rigorous mask diffraction computation based on electromagnetic field modeling. The high time expense of the rigorous mask models in the simulation process challenges the exploration of innovative modeling techniques to compromise accuracy and speed in the computation of the diffracted field and vectorial imaging in optical lithographic systems. The artificial neural network (ANN) approach is presented as an alternative to retrieve the spectrum of the mask layout in an accurate yet efficient way. The validity of the ANN for different illuminations, feature sizes, pitches, and shapes is investigated. The evaluation of the performance of this approach is performed by a process windows analysis, comparison of the spectra, best focus, and critical dimension through pitch. The application of various layouts demonstrates that the ANN can also be trained with different patterns to reproduce various effects such as shift of the line position, different linewidths, and line ends. Comparisons of the ANN approach with other compact models such as boundary layer model, pulses modification, spectrum correction, and pupil filtering techniques are presented.