Integrating recurrent neural networks with data assimilation for scalable data-driven state estimation

Penny, S. G.; Smith, T. A.; Chen, T.-C.; Platt, J. A.; Lin, H.-Y.; Goodliff, M.; Abarbanel, H. D. I.

doi:10.1029/2021MS002843

i

Integrating recurrent neural networks with data assimilation for scalable data-driven state estimation

2022
By Penny, S. G. ; Smith, T. A. ; Chen, T.-C. ; ...

Select the Download button to view the document

Please click the download button to view the document.

Details

Journal Title:

Journal of Advances in Modeling of Earth Systems
Personal Author:

Penny, S. G. ; Smith, T. A. ; Chen, T.-C. ; Platt, J. A. ; Lin, H.-Y. ; Goodliff, M. ; Abarbanel, H. D. I.
NOAA Program & Office:

CIRES (Cooperative Institute for Research in Environmental Sciences) ; CISESS (Cooperative Institute for Satellite Earth System Studies) ; OAR (Oceanic and Atmospheric Research) ; PSL (Physical Sciences Laboratory)
Description:

Data assimilation (DA) is integrated with machine learning in order to perform entirely datadriven online state estimation. To achieve this, recurrent neural networks (RNNs) are implemented as pretrained 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.
Keywords:

Machine Learning Neural Networks (Computer Science) Machine Learning Neural Networks (Computer Science)
Source:

Journal of Advances in Modeling Earth Systems 14(3): e2021MS002843
DOI:

https://doi.org/10.1029/2021MS002843
Document Type:

Journal Article
Funding:

Grant no. NA19NES4320002 ; Grant no. NA20OAR4600277 ; Grant no. NA17OAR4320101 ; Grant no. NA18NWS4680048
License:

https://creativecommons.org/licenses/by/4.0/
Rights Information:

CC BY
Compliance:

Submitted
Main Document Checksum:

urn:sha256:210dce642839e94b42a7ca9666e8af75e65a1dcd36d713cf0b966787fee4e33e
Download URL:

https://repository.library.noaa.gov/view/noaa/48163/noaa_48163_DS1.pdf
File Type:

[PDF - 72.53 MB ]

ON THIS PAGE

Details

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.