Polynomial Chaos based on the parallelized ensemble Kalman filter to estimate precipitation states

  • Luis Sanchez universidad de carabobo
  • Saba Infante
  • Jose Marcano
  • Victor Griffin

Abstract

This article develops a methodology combining methods of numerical analysis and stochastic differential equations with computational algorithms to treat problems which have complex nonlinear dynamics in high dimensions. A method to estimate parameters and states of a dynamic system is proposed inspired by the parallelized ensemble Kalman filter (PEnKF) and the polynomial chaos theory of Wiener-Askey. The main advantage of the proposal is in providing a precise efficient algorithm with low computational cost. For the analysed data, the methods provide good predictions, spatially and temporally, for the unknown precipitation states for the first 24 hours. Two goodness of fit measures provide confidence in the quality of the model predictions. The performance of the parallel algorithm, measured by the acceleration and efficiency factors, shows an increase of 7% in speed with respect to the sequential version and is most efficient for P = 2 threads.

References

E. Allen, Modeling with Ito Stochastic Differential Equations, Published by Springer, Texas Tech University, USA, 2007.

B. Anderson and J. Moore, Optimal Filtering, Prentice-Hall, 1979.

C. Andrieu and J. Thoms, A tutorial on adaptive MCMC, Statistics and Computing, Volume 18, Number 4, 343-373, 2008. DOI:10.1007/s11222-008-9110-y

S. Arulampalam, S. Maskell, N. Gordon and T. Clapp, A Tutorial on Particle Filters for On-line Non-linear/Non-Gaussian Bayesian Tracking, IEEE Trans. Sig. Proc., Vol. 50(2), PP. 174-188, 2002

K. Bakar, Bayesian Analysis of Daily Maximum Ozone Levels, Thesis for the degree of Doctor of Philosophy, 2011. http://eprints.soton.ac.uk

T. Bengtsson, P. Bickel and B. Li, Curse-of-dimensionality revisited: Collapseof the particle filter in very large scale systems, Probabilityand Statistics: Essays in Honor of David A. Freedman, vol. 2, pp.316-334, 2008.

J. Crank and P. Nicolson, A practical method for numerical evaluation of solutions of partial differential equations of the heat conduction type, Proc. Camb. Phil. Soc., Vol. 43, pp. 50-67, 1947. doi:10.1007/BF02127704.

A. Doucet, J. DE Freitas and N. Gordon, Sequential Monte Carlo in Practice, Springer Verlag, New York, 2001.

A. Doucet, S. Godsill and C. Andrieu, On sequential Monte Carlo samplingmethods for Bayesian filtering, Statist. Comput., vol. 10, no. 3, pp. 197-208, 2000.

G. Evensen, Data assimilation: the ensemble Kalman Filter, Second Edition, Springer, 2009.

G. Evensen, Sequential data assimilation with a nonlinear quasi-geostrophic model using Monte Carlo methods to forecast error statistics, J. Geophys. Res. Vol. 99, pp. 10143-10162, 1994.

G. Evensen, The ensemble Kalman filter: theoretical formulation and practical implementation, Ocean dynamics, Vol. 53, pp. 343-367, 2003.

G. Evensen and P. van Leeuwen, Assimilation of Geosat altimeter data for the Agulhas current using the ensemble Kalman filter with a quasi-geostrophic model, Mon. Wea. Rev., Vol. 124, pp. 85-96, 1996.

P. Fearnhead, Markov chain Monte Carlo, sufficientstatistics, and particle filters, J. Computat.Graph. Statist., vol. 11, no. 4, pp.848-862, 2002.

W. Fong, S. Godsill, A. Doucet and M. West, Monte Carlo Smoothing With Application to Audio Signal Enhancement, IEEE Transactions on Signal Processing, Vol. 50, pp. 438-449, 2002.

A. Gelb, Applied Optimal Estimation, MIT Press, 1974.

S. Godsill, A. Doucet and M. West, Monte Carlo Smoothing for Nonlinear Time Series, Journal of the American Statistical Association, Vol. 99, pp. 156-167, 2004.

N. Gordon, D. Salmond and A. Smith, Novel approach to nonlinear/non-Gaussian Bayesian state estimation, IEE Proceedings F on Radar and Signal Processing, 140 (2): 107-113, 1993. doi:10.1049/ip-f-2.1993.0015.

D. Higdon, A process-convolution approach to modeling temperatures in the north Atlantic Ocean, Journal of Environmental and Ecological Statistics, 5, 173-190, 1998.

A. Hurn, K. Lindsay and V. Martin, On the efficacy of simulated maximum likelihood for estimating the parameters of stochastic differential equations, Journal of Time Series Analysis, Vol. 24, pp. 45-63, 2003.

S. Infante, J. Rojas, A. Hernández and V. Cartaya, Modelos de espacio estado basados en la distribución normal inversa gaussiana: Una aplicación al análisis de series de tiempo de la econom´ıa venezolana, Revista de Estad´ıstica, del Instituto Interamericano de

Estad´ıstica, Vol 62, 178, 5-36, 2010.

A. Jazwinski, Stochastic Processes and Filtering Theory, Academic Press, Inc. New York, USA, 1970.

S. Julier and J. Uhlmann, A new extension of the Kalman filter to nonlinear systems, In Proc. AeroSense: 11th Int. Symp. Aerospace/Defense Sensing, Simulation and Controls, pp. 182-193, 1997.

S. Julier and J. Uhlmann, Unscented Filtering and Nonlinear Estimation, Proceedings of the IEEE 92, 3, 401-422, 2004.

G. Kitagawa, Monte Carlo Filter and Smoother for Nonlinear Non Gaussian State Models, Journal of Computation and Graphical Statistics. Vol. 5, pp. 1-25, 1996.

P. Kloeden and E. Platen, Numerical Solution of Stochastic Differential Equations, Springer-Verlag, 1992.

D. Lee, Nonlinear Bayesian Filtering with Applications to Estimation and Navigation, Thesis for the degree of Doctor of Philosophy, 2005. http://repository.tamu.edu/bitstream/handle/1969.1/2269/etd-tamu-2005A-AERO-Lee.pdf?sequence=1

M. Lin, J. Zhang, Q. Cheng and R. Chen, Independent Particle Filters, Journal of the American Statistical Association, Theory and Methods. 100: 472, 1412-1421, 2005.

J. Liu and R. Chen, Sequential Monte Carlo Methods for Dynamical Systems, Journal of the American Statistical Association, Vol. 83, pp. 1032-1044, 1998.

J. Liu and M. West, Combine Parameter and State Estimation in Simulation Based Filtering, In Sequential Monte Carlo Methods in Practice, Eds. A. Doucet, J. F. G. De Freitas, and N. J. Gordon, New York: Springer Verlag, pp. 197-217, 2000.

J. Li and D. Xiu, A Generalized Polynomial Chaos Based Ensemble Kalman Filter with High Accuracy, Journal of Computational Physics, Vol. 228, No. 15, 2009, pp. 5454-5469, 2009. doi:10.1016/j.jcp.2009.04.029

R. Madankan, Polynomial Chaos Based Method for State and Parameter Estimation, M.S. Thesis, Univ. at Buffalo, State University of New York, Buffalo, NY, 2011.

B. Ø Kesendal, Stochastic Differential Equations, An Introduction with Applicatins, Springer, fifth edition, 2000.

E. Platen, An introduction to numerical methods for stochastic differential equations, Acta Numerica, pp. 197-246, 1999.

A. Pedersen, A new approach to maximum likelihood estimation for stochastic differential equations based on discrete observations, Scandinavian Journal of Statistics, 22, 55-71, 1995.

M. Pitt and N. Shephard, Filtering via simulation: Auxiliary particle filters, J. Amer. Statist. Assoc. , vol. 94, no. 446, pp. 590-599, 1996.

L. Sánchez, S. Infante, V. Griffin and D. Rey, Spatiotemporal dynamic model and parallelized ensemble Kalman Filter for precipitation data, Reporte técnico, Departamento de Matemáticas, Facultad de Ciencia y Tecnologia, Universidad de Carabobo, 2014.

L. Sánchez and S. Infante, Reconstruction of chaotic dynamic systems using non-linear filters, Chilean Journal of Statistics. Vol. 4, No. 1, 35-54, 2013.

D. Simon, Optimal State Estimation Kalman, H Infinity, and Nonlinear Approaches, John Wiley and Sons, publication, 2006.

C. Snyder, T. Bengtsson, P. Bickel and J. Anderson, Obstacles to high-dimensional particle filtering, Monthly Weather Review 136(12): 4629-4640, 2008.

G. Storvik, Particle filters for state-spacemodels with the presence of unknown static parameters, IEEE Trans. Signal Process., vol. 50, no. 2, pp. 281-289, 2002.

O. Stramer and M. Bognar, Bayesian inference for irreducible diffusion processes using the pseudo-marginal approach, Bayesian Analisys, Volume 6, Number 2, pp. 231-258, 2011.

O. Stramer, M. Bognar and P. Schneider, Bayesian Inference of Discretely Sampled Markov Processes with Closed-Form Likelihood Expansions, The Journal of Financial Econometrics, 8: 450-480, 2010.

M. West and J. Harrison, Bayesian Forecasting and Dynamic Models, Springer, (2nd Ed.) 1997.

C. Wikle and S. Holan, Polynomial nonlinear spatio-temporal integro-difference equation models, Journal of Time Series Analysis. 32, 339-350, 2011. DOI:10.1111//j.1467-9892.2011.00729.x

B. Wilkinson and M. Allen, Parallel Programming: Techniques and Application Using Networked Workstations and Parallel, Computers 2nd edition Prentice-Hall Inc, 2005.

L. Wuan, Wiener Chaos Expansion and Numerical Solutions of Stochastic Partial Differential Equations, Thesis for the Degree of Doctor of Philosophy California Institute of Technology Pasadena, California, 2006.

D. Xiu and G. Karniadakis, The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations, SIAM Journal on Scientific Computing, Vol. 24, No. 2, pp. 619-644, 2002.

Published
2015-02-21
How to Cite
Sanchez, L., Infante, S., Marcano, J., & Griffin, V. (2015). Polynomial Chaos based on the parallelized ensemble Kalman filter to estimate precipitation states. Statistics, Optimization & Information Computing, 3(1), 79-95. https://doi.org/10.19139/soic.v3i1.113
Section
Research Articles

Most read articles by the same author(s)