In this section
@article{Kalliadasis:2015:10.1016/j.jcp.2015.05.002,
author = {Kalliadasis, S and Krumscheid, S and Pavliotis, GA},
doi = {10.1016/j.jcp.2015.05.002},
journal = {Journal of Computational Physics},
pages = {314--328},
title = {A new framework for extracting coarse-grained models from time series with multiscale structure},
url = {http://dx.doi.org/10.1016/j.jcp.2015.05.002},
volume = {296},
year = {2015}
}
TY - JOUR
AB - In many applications it is desirable to infer coarse-grained models from observational data. The observed process often corresponds only to a few selected degrees of freedom of a high-dimensional dynamical system with multiple time scales. In this work we consider the inference problem of identifying an appropriate coarse-grained model from a single time series of a multiscale system. It is known that estimators such as the maximum likelihood estimator or the quadratic variation of the path estimator can be strongly biased in this setting. Here we present a novel parametric inference methodology for problems with linear parameter dependency that does not suffer from this drawback. Furthermore, we demonstrate through a wide spectrum of examples that our methodology can be used to derive appropriate coarse-grained models from time series of partial observations of a multiscale system in an effective and systematic fashion.
AU - Kalliadasis,S
AU - Krumscheid,S
AU - Pavliotis,GA
DO - 10.1016/j.jcp.2015.05.002
EP - 328
PY - 2015///
SN - 1090-2716
SP - 314
TI - A new framework for extracting coarse-grained models from time series with multiscale structure
T2 - Journal of Computational Physics
UR - http://dx.doi.org/10.1016/j.jcp.2015.05.002
UR - http://hdl.handle.net/10044/1/24003
VL - 296
ER -