TY  - JOUR
A1  - Gottwald, Georg A.
A1  - Reich, Sebastian
T1  - Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
T2  - Chaos : an interdisciplinary journal of nonlinear science
N2  - We present a supervised learning method to learn the propagator map of a dynamical system from partial and noisy observations. In our computationally cheap and easy-to-implement framework, a neural network consisting of random feature maps is trained sequentially by incoming observations within a data assimilation procedure. By employing Takens's embedding theorem, the network is trained on delay coordinates. We show that the combination of random feature maps and data assimilation, called RAFDA, outperforms standard random feature maps for which the dynamics is learned using batch data.
Y1  - 2021
UR  - https://publishup.uni-potsdam.de/frontdoor/index/index/docId/59518
SN  - 1054-1500
SN  - 1089-7682
VL  - 31
IS  - 10
PB  - AIP
CY  - Melville
ER  -