Machine learning techniques to construct patched analog ensembles for data assimilation.
Published in Journal of Computational Physics, 2021
Highlights: Domains need to be partitioned when constructing analogs for geophysical models. Patches make the training of machine learning models more robust. The use of patches makes in data assimilation can be implemented in parallel. General autoencoders with an affine transformation in the latent space can be used. Patched constructed analogs can approximate ensemble members within DA methods.
Recommended citation: Yang, L. Minah, Ian Grooms, and Keith A. Julien. "The fidelity of exponential and IMEX integrators for wave turbulence: introduction of a new near-minimax integrating factor scheme." Journal of Computational Physics 434 (2021): 109992. https://doi.org/10.1016/j.jcp.2021.110532