Using machine learning techniques to generate analog ensembles for data assimilation
<p>We propose to use analogs of the forecast mean to generate an ensemble of perturbations for use in ensemble optimal interpolation (EnOI) or ensemble variational (EnVar) methods.&#160; In addition to finding analogs from a library, we propose a new method of constructing analogs using autoencoders (a machine learning method).&#160; To extend the scalability of constructed analogs for use in data assimilation on geophysical models, we propose using patching schemes to divide the global spatial domain into digestable chunks.&#160; Using patches makes training the generative models possible and has the added benefit of being able to exploit parallel computing powers.&#160; The resulting analog methods using analogs from a catalog (AnEnOI), constructed analogs (cAnEnOI), and patched constructed analogs (p-cAnEnOI) are tested in the context of a multiscale Lorenz-`96 model, with standard EnOI and an ensemble square root filter for comparison.&#160; The use of analogs from a modestly-sized catalog is shown to improve the performance of EnOI, with limited marginal improvements resulting from increases in the catalog size.&#160; The method using constructed analogs is found to perform as well as a full ensemble square root filter, and to be robust over a wide range of tuning parameters.&#160; Lastly, we find that p-cAnENOI with larger patches produces the best data assimilation performance despite having larger reconstruction errors.&#160; All patch variants except for the variant that uses the smallest patch size outperform cAnEnOI as well as some traditional data assimilation methods such as the ensemble square root filter.</p>