scholarly journals Model reduction and inverse problems and data assimilation with geophysical applications. A special issue in honor of I. Michael Navon's 75th birthday

2016 ◽  
Vol 82 (10) ◽  
pp. 625-630 ◽  
Author(s):  
Răzvan Ştefănescu ◽  
Bernd R. Noack ◽  
Adrian Sandu
Keyword(s):  
Data Assimilation ◽  
Inverse Problems ◽  
Model Reduction ◽  
75Th Birthday ◽  
Special Issue

Jointly learning variational data assimilation models and solvers for geophysical dynamics

2021 ◽  
Author(s):  
Ronan Fablet ◽  
Bertrand Chapron ◽  
Lucas Drumetz ◽  
Etienne Memin ◽  
Olivier Pannekoucke ◽  
...  
Keyword(s):  
Neural Networks ◽  
Data Assimilation ◽  
Inverse Problems ◽  
Automatic Differentiation ◽  
Variational Data Assimilation ◽  
Point Of View ◽  
Variational Model ◽  
Short Term ◽  
End To End ◽  
Short Term Forecasting

<p>This paper addresses representation learning for the resolution of inverse problems  with geophysical dynamics. Among others, examples of inverse problems of interest include space-time interpolation, short-term forecasting, conditional simulation w.r.t. available observations, downscaling problems… From a methodological point of view, we rely on a variational data assimilation framework. Data assimilation (DA) aims to reconstruct the time evolution of some state given a series of  observations, possibly noisy and irregularly-sampled. Here, we investigate DA from a machine learning point of view backed by an underlying variational representation.  Using automatic differentiation tools embedded in deep learning frameworks, we introduce end-to-end neural network architectures for variational data assimilation. It comprises two key components: a variational model and a gradient-based solver both implemented as neural networks. A key feature of the proposed end-to-end learning architecture is that we may train the neural networks models using both supervised and unsupervised strategies. We first illustrate applications to the reconstruction of Lorenz-63 and Lorenz-96 systems from partial and noisy observations. Whereas the gain issued from the supervised learning setting emphasizes the relevance of groundtruthed observation dataset for real-world case-studies, these results also suggest new means to design data assimilation models from data. Especially, they suggest that learning task-oriented representations of the underlying dynamics may be beneficial. We further discuss applications to short-term forecasting and sampling design along with preliminary results for the reconstruction of sea surface currents from satellite altimetry data. </p><p>This abstract is supported by a preprint available online: https://arxiv.org/abs/2007.12941</p>

Inverse Problems and Model Reduction Techniques

2010 ◽  
pp. 255-262 ◽  
Author(s):  
Juan Luis Fernández-Martínez ◽  
Michael Tompkins ◽  
Zulima Fernández-Muñiz ◽  
Tapan Mukerji
Keyword(s):  
Inverse Problems ◽  
Model Reduction ◽  
Reduction Techniques
Sign in / Sign up

Export Citation Format

Share Document