Estimating the parameters of dynamical systems from Big Data using Sequential Monte Carlo samplers

In this paper the authors present a method which facilitates computationally efficientparameter estimation of dynamical systems from a continuously growing set of measure-ment data. It is shown that the proposed method, which utilises Sequential Monte Carlosamplers, is guaranteed to be fully parallelisable (in contrast to Markov chain MonteCarlo methods) and can be applied to a wide variety of scenarios within structural dynam-ics. Its ability to allowconvergenceof one’s parameter estimates, as more data is analysed,sets it apart from other sequential methods (such as the particle filter)