Articles | Volume 21, issue 3
https://doi.org/10.5194/npg-21-633-2014
© Author(s) 2014. This work is distributed under
the Creative Commons Attribution 3.0 License.Special issue:
Monte Carlo fixed-lag smoothing in state-space models
Abstract. This paper presents an algorithm for Monte Carlo fixed-lag smoothing in state-space models defined by a diffusion process observed through noisy discrete-time measurements. Based on a particle approximation of the filtering and smoothing distributions, the method relies on a simulation technique of conditioned diffusions. The proposed sequential smoother can be applied to general nonlinear and multidimensional models, like the ones used in environmental applications. The smoothing of a turbulent flow in a high-dimensional context is given as a practical example.