In-Situ Ellipsometry Solutions Using Sequential Monte Carlo

  • Alan D. Marrs
Part of the Statistics for Engineering and Information Science book series (ISS)


This chapter presents an example of an actual industrial application in which Sequential Monte Carlo (SMC) methods have led to significant progress toward the goal of on-line control of growing semiconductor composition. This chapter will differ from the majority of contributions to this book in that it presents an example application in which SMC has been used to solve a real problem in industrial process monitoring. By necessity we shall not dwell upon such issues as whether to use SIS, SIR, ASIR, Resample-move, Residual-resample, kernel-smoothing or any of the myriad of mechanisms for “herding” our set of posterior samples from one time step to the next. Similarly, the chapter does not seek to introduce the latest “jolly-wheeze” for implementing a Bayesian recursive filter using Sequential Monte Carlo. The chapter describes how the power of vanilla SMC methods can be used to overcome the analytical problems inherent in highly nonlinear physical measurement models and that, even with a relatively small number of particles, adequate results can be obtained.


Particle Filter Spectroscopic Ellipsometry Sequential Monte Carlo Switching Matrix Ellipsometry Measurement 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Alan D. Marrs

There are no affiliations available

Personalised recommendations