Abstract
In this work we present recent and new results for the theory and algorithms of efficient estimation of the coarse-grain dynamics of a multiscale chaotic dynamical system, where observations may be limited both spatial and in time, and the observations are correlated with the slow states. The rigorous mathematical statement and convergence result with a rate of convergence to the reduced order filter problem is given for the case of correlated sensor noise. Based on this result, algorithms for efficient numerical solution of the filtering problem for the coarse-grain dynamics are provided. We then address a second issue, which presents itself in the case of chaotic systems and degrades particle filtering performance; the growth of small errors at an exponential rate. We solve this problem by introducing an optimal control problem for the solution of the proposal distribution and develop a numerical algorithm for it’s solution. The algorithms developed in this work are demonstrated on the widely used multiscale chaotic Lorenz 1996 model, that mimics mid-latitude convection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anderson, J.L.: An Ensemble Adjustment Kalman Filter for Data Assimilation. Monthly Weather Review 129, 2884–2903 (2001)
Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking. IEEE Transactions on Signal Processing 50(2), 174–188 (2002). https://doi.org/10.1109/78.978374
Bain, A., Crisan, D.: Fundamentals of Stochastic Filtering. Springer (2009)
Beeson, R.: Reduced order nonlinear filters for multi-scale systems with correlated sensor noise. In: 21st International Conference on Information Fusion (FUSION) 2018 (FUSION 2018). Cambridge, United Kingdom (Great Britain) (2018)
Beeson, R., Namachchivaya, N.S., Perkowski, N.: Dimensional reduction in nonlinear filter- ing: Multi-scale systems and correlated sensor noise. In Preparation
Crisan, D.: Particle approximations for a class of stochastic partial differential equations. Ap- plied Mathematics and Optimization 54, 293–314 (2006)
Del Moral, P., Miclo, L.: Branching and Interacting Particle Systems Approximations of Feynman-Kac Formulae with Applications to Non-linear Filtering. In: Se´minaire de Prob- abilite´s XXXIV, Lecture Notes in Mathematics, vol. 1729, pp. 1–145. Springer-Verlag Berlin (2000)
Doucet, A.: On sequential simulation-based methods for Bayesian filtering. Tech. rep., Cam- bridge University (1998)
E, W., Liu, D., Vanden-Eijnden, E.: Analysis of multiscale methods for stochastic differential equations. Communication on Pure and Applied Mathematics 58, 1544–1585 (2005)
Fatkullin, I., Vanden-Eijnden, E.: A computational strategy for multiscale systems. Journal of Computational Physics 200(2), 605–638 (2004)
Fleming, W.H.: Exit probabilities and optimal stochastic12. control. Applied Mathematics and Optimization 4, 329–346 (1978)
Fleming, W.H.: PLogarithmic transformations and stochastic control, pp. 131–141. Springer Berlin Heidelberg, Berlin, Heidelberg (1982). https://doi.org/10.1007/bfb0004532. URL http://dx.doi.org/10.1007/BFb0004532
Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEEE Proceedings F 140(2), 107–113 (1993)
Gustafsson, F., Saha, S.: Particle filtering with dependent noise. In: 2010 13th International Conference on Information Fusion, pp. 1–4 (2010). https://doi.org/10.1109/icif.2010.5712052
Harlim, J., Kang, E.L.: Filtering partially observed multiscale systems with heterogeneous multiscale methods-based reduced climate models. Mon. Wea. Rev. 140(3), 860–873 (2012)
Imkeller, P., Namachchivaya, N.S., Perkowski, N., Yeong, H.C.: Dimensional reduction in nonlinear filtering: A homogenization approach. Ann. Appl. Probab. 23(6), 2290–2326 (2013). https://doi.org/10.1214/12-aap901. URL http://dx.doi.org/10.1214/12-AAP901
Kang, E.L., Harlim, J.: Filtering partially observed multiscale systems with heterogeneous multiscale methods-based reduced climate models. Monthly Weather Review 140, 860–873 (2012)
Karatzas, I., Shreve, S.E.: Brownian Motion and Stochastic Calculus. Springer-Verlag New York Inc. (1988)
Kushner, H.J.: Weak Convergence Methods and Singularly Perturbed Stochastic Control and Filtering Problems. Birkha¨user, Boston (1990)
van Leeuwen, P.J.: Nonlinear data assimilation in geosciences: an extremely efficient particle filter. Quart. J. Royal Meteor. Soc. 136, 1991–1999 (2010)
Lingala, N., Perkowski, N., Yeong, H.C., Namachchivaya, N.S., Rapti, Z.: Probabilistic Engi- neering Mechanics. Probabilistic Engineering Mechanics 37(C), 160–169 (2014)
Lingala, N., Sri Namachchivaya, N., Perkowski, N., Yeong, H.C.: Particle filtering in high- dimensional chaotic systems. Chaos: An Interdisciplinary Journal of Nonlinear Science 22(4), 047,509 (2012)
Lorenz, E.N.: Predictability: A problem partly solved. In: Proceedings of the ECMWF Semi- nar on Predictability, vol. 1, pp. 1–18. ECMWF (1996)
Majda, A., Timofeyev, I., Vanden-Eijnden, E.: A Mathematical Framework for Stochastic Cli- mate Models. Comm. Pure Appl. Math. 54, 891–974 (2001)
Majda, A.J., Timofeyev, I., Vanden-Eijnden, E.: Systematic Strategies for Stochastic Mode Reduction in Climate. J. of Atmospheric Sciences 60, 1705–1722 (2003)
Ă˜ksendal, B.: An introduction to Malliavin calculus with applications to economics (1997). Lecture notes
Ott, E., Hunt, B.R., Szunyogh, I., Zimin, A.V., Kostelich, E.J., Corazza, M., Kalnay, E., Patil, D.J., Yorke, J.A.: A local ensemble Kalman filter for atmospheric data assimilation. Tellus 56A, 415–428 (2004)
Papanicolaou, G.C., Stroock, D., Varadhan, S.R.S.: Martingale approach to some limit the- orems. In: Papers from the Duke Turbulence Conference. Duke University, Durham, North Carolina (1976)
Pardoux, E.: Stochastic partial differential equations and filtering of diffusion pro- cesses. Stochastics 3(1-4), 127–167 (1980). https://doi.org/10.1080/17442507908833142. URL http://www.tandfonline.com/doi/abs/10.1080/17442507908833142
Pardoux, E., Peng, S.: Backward doubly stochastic differential equations and systems of quasi- linear SPDEs. Probability Theory and Related Fields (98), 209–227 (1994)
Pardoux, E., Veretennikov, A.Y.: On Poisson Equation and Diffusion Approximation 2. The Annals of Probability 31(3), 1166–1192 (2003)
Park, J.H., Namachchivaya, N.S., Yeong, H.C.: Particle filters in a multiscale environment: Homogenized hybrid particle filter. Journal of Applied Mechanics 78 (2011)
Rozovskii, B.L.: Stochastic Evolution System: Linear Theory and Aplications to Non-linear Filtering. Kluwer Academic Publishers, Dordrecht (1990)
Saha, S., Gustafsson, F.: Marginalized particle filter for dependent gaussian noise processes. In: 2012 IEEE Aerospace Conference, pp. 1–6 (2012). https://doi.org/10.1109/aero.2012.6187212
Vanden-Eijnden, E.: Numerical techniques for multi-scale dynamical systems with stochastic effects. Communications in Mathematical Sciences 1(2), 385–391 (2003)
Veretennikov, A.Y.: On polynomial mixing bounds for stochastic differential equations. Stochastic Processes and their Applications 70, 115–127 (1997)
Yang, T., Laugesen, R.S., Mehta, P.G., Meyn, S.P.: Multivariable feedback particle filter. Au- tomatica 71, 10–23 (2016)
Yeong, H.C., Beeson, R., Namachchivaya, N.S., Perkowski, N.: Particle filters with nudging in multiscale chaotic system: with application to the lorenz-96 atmospheric model. In Sub- mission (2018)
Yeong, H.C., Park, J.H., Namachchivaya, N.S.: Particle filters in a multiscale en- vironment: with application to the lorenz-96 atmospheric model. Stochastics and Dynamics 11(02n03), 569–591 (2011). https://doi.org/10.1142/s0219493711003450. URL http://www.worldscientific.com/doi/abs/10.1142/S0219493711003450
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Beeson, R., Sri Namachchivaya, N. (2019). Nudged Particle Filters in Multiscale Chaotic Systems with Correlated Sensor Noise. In: Yin, G., Zhang, Q. (eds) Modeling, Stochastic Control, Optimization, and Applications. The IMA Volumes in Mathematics and its Applications, vol 164. Springer, Cham. https://doi.org/10.1007/978-3-030-25498-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-25498-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-25497-1
Online ISBN: 978-3-030-25498-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)