Analog ensemble data assimilation and a method for constructing analogs with variational autoencoders

06/01/2020

∙

It is proposed 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. A new method of constructing analogs using variational autoencoders (VAEs; a machine learning method) is proposed. The resulting analog methods using analogs from a catalog (AnEnOI), and using constructed analogs (cAnEnOI), are tested in the context of a multiscale Lorenz-`96 model, with standard EnOI and an ensemble square root filter for comparison. 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. The method using constructed analogs (cAnEnOI) is found to perform as well as a full ensemble square root filter, and to be robust over a wide range of tuning parameters.

READ FULL TEXT

Analog ensemble data assimilation and a method for constructing analogs with variational autoencoders

Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation

Adjoint-Free 4D-Var Methods Via Line Search Optimization For Non-Linear Data Assimilation

Multifidelity Ensemble Kalman Filtering using surrogate models defined by Physics-Informed Autoencoders

Seasonal and Trend Forecasting of Tourist Arrivals: An Adaptive Multiscale Ensemble Learning Approach

How to boost autoencoders?

Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation

Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother

Analog ensemble data assimilation and a method for constructing analogs with variational autoencoders

Related Research

Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation

Adjoint-Free 4D-Var Methods Via Line Search Optimization For Non-Linear Data Assimilation

Multifidelity Ensemble Kalman Filtering using surrogate models defined by Physics-Informed Autoencoders

Seasonal and Trend Forecasting of Tourist Arrivals: An Adaptive Multiscale Ensemble Learning Approach

How to boost autoencoders?

Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation

Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother