Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation
Abstract
Data assimilation (DA) is integrated with machine learning in order to perform entirely data-driven online state estimation. To achieve this, recurrent neural networks (RNNs) are implemented as surrogate models to replace key components of the DA cycle in numerical weather prediction (NWP), including the conventional numerical forecast model, the forecast error covariance matrix, and the tangent linear and adjoint models. It is shown how these RNNs can be initialized using DA methods to directly update the hidden/reservoir state with observations of the target system. The results indicate that these techniques can be applied to estimate the state of a system for the repeated initialization of short-term forecasts, even in the absence of a traditional numerical forecast model. Further, it is demonstrated how these integrated RNN-DA methods can scale to higher dimensions by applying domain localization and parallelization, providing a path for practical applications in NWP.
Cite
@article{arxiv.2109.12269,
title = {Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation},
author = {Stephen G. Penny and Timothy A. Smith and Tse-Chun Chen and Jason A. Platt and Hsin-Yi Lin and Michael Goodliff and Henry D. I. Abarbanel},
journal= {arXiv preprint arXiv:2109.12269},
year = {2022}
}
Comments
22 pages, 16 figures