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.

[1]  Yuri Granik,et al.  Process window modeling using compact models , 2004, SPIE Photomask Technology.

[2]  Kevin D. Lucas,et al.  Rigorous and practical vector model for phase-shifting masks in optical lithography , 1992, Advanced Lithography.

[3]  F. F. Hiltz.  Analog Computer Simulation of a Neural Element , 1962 .

[4]  E. J. Nalos.  Neural theory and modeling, proceedings of the 1962 Ojai symposium , 1965 .

[5]  A. Neureuther,et al.  Domain decomposition methods for the rapid electromagnetic simulation of photomask scattering , 2002 .

[6]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[7]  Feng Shao,et al.  Fast rigorous simulation of mask diffraction using the waveguide method with parallelized decomposition technique , 2008, European Mask and Lithography Conference.

[8]  Feng Shao,et al.  Accuracy and performance of 3D mask models in optical projection lithography , 2011, Advanced Lithography.

[9]  Andreas Erdmann,et al.  Evaluation of various compact mask and imaging models for the efficient simulation of mask topography effects in immersion lithography , 2012, Advanced Lithography.

[10]  C. Burckhardt.  Diffraction of a Plane Wave at a Sinusoidally Stratified Dielectric Grating , 1966 .

[11]  T. Gaylord,et al.  Rigorous coupled-wave analysis of planar-grating diffraction , 1981 .

[12]  Kevin D. Lucas,et al.  Efficient and rigorous three-dimensional model for optical lithography simulation , 1996 .

[13]  S.,et al.  Numerical Solution of Initial Boundary Value Problems Involving Maxwell’s Equations in Isotropic Media , 1966 .

[14]  David Fryer,et al.  Accurate 3DEMF mask model for full-chip simulation , 2013, Advanced Lithography.

[15]  Peter De Bisschop,et al.  Validity of the Hopkins approximation in simulations of hyper-NA (NA>1) line-space structures for an attenuated PSM mask , 2006, SPIE Advanced Lithography.

[16]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[17]  C.-M. Yuan,et al.  Efficient light scattering modeling for alignment, metrology, and resist exposure in photolithography , 1992 .

[18]  Jens Timo Neumann,et al.  Polarization-induced astigmatism caused by topographic masks , 2007, SPIE Photomask Technology.

[19]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[20]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[21]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.