Nested smoothing algorithms for inference and tracking of heterogeneous multi-scale state-space systems

Multi-scale problems, where variables of interest evolve in different time-scales and live in different state-spaces, can be found in many fields of science. Here, we introduce a new recursive methodology for Bayesian inference that aims at estimating the static parameters and tracking the dynamic variables of these kind of systems. Although the proposed approach works in rather general setups, for clarity we analyze the case of a heterogeneous multi-scale model with 3 time-scales (static parameters, slow dynamic state variables and fast dynamic state variables). The proposed scheme, based on a nested filtering methodology of [27], combines three intertwined layers of filtering techniques that approximate recursively the joint posterior probability distribution of the parameters and both sets of dynamic state variables given a sequence of partial and noisy observations. We explore the use of both sequential Monte Carlo schemes and several Kalman filtering techniques in the different layers of the methodology to obtain approximations of the posterior probability distributions of interest. Some numerical results are presented for a stochastic two-scale Lorenz 96 model with unknown parameters.