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

arXiv: https://arxiv.org/abs/2006.01101 · HTML: https://mlsanity.com/paper/2006.01101/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers](https://mlsanity.com/paper/2103.09360/) (2021)
- [Bridging observation, theory and numerical simulation of the ocean using Machine Learning](https://mlsanity.com/paper/2104.12506/) (2021)
- [A VAE Approach to Sample Multivariate Extremes](https://mlsanity.com/paper/2306.10987/) (2023)
- [Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation](https://mlsanity.com/paper/2103.00318/) (2021)
- [Evaluation of Machine Learning Techniques for Forecast Uncertainty Quantification](https://mlsanity.com/paper/2111.14844/) (2021)
- [Ensemble Kalman filter in latent space using a variational autoencoder pair](https://mlsanity.com/paper/2502.12987/) (2025)
- [Latent Twins](https://mlsanity.com/paper/2509.20615/) (2025)
- [Online machine-learning forecast uncertainty estimation for sequential data assimilation](https://mlsanity.com/paper/2305.08874/) (2023)
- [Learning low-dimensional representations of ensemble forecast fields using autoencoder-based methods](https://mlsanity.com/paper/2502.04409/) (2025)
- [Generating observation guided ensembles for data assimilation with denoising diffusion probabilistic model](https://mlsanity.com/paper/2308.06708/) (2023)
- [U-Net Kalman Filter (UNetKF): An Example of Machine Learning-assisted Ensemble Data Assimilation](https://mlsanity.com/paper/2403.12366/) (2024)
- [Accounting for model error in ensemble variational data assimilation through learned generative dynamics](https://mlsanity.com/paper/2610.17333/) (2026)

## Abstract (arXiv)

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.