# Composing a surrogate observation operator for sequential data assimilation

arXiv: https://arxiv.org/abs/2201.12514 · HTML: https://mlsanity.com/paper/2201.12514/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 4 of 4)

- [Using machine learning to correct model error in data assimilation and forecast applications](https://mlsanity.com/paper/2010.12605/) (2020)
- [A comparison of combined data assimilation and machine learning methods for offline and online model error correction](https://mlsanity.com/paper/2107.11114/) (2021)
- [Correcting biased observation model error in data assimilation](https://mlsanity.com/paper/1611.05405/) (2016)
- [Kalman-Takens filtering in the presence of dynamical noise](https://mlsanity.com/paper/1611.05414/) (2016)

## Abstract (arXiv)

In data assimilation, state estimation is not straightforward when the observation operator is unknown. This study proposes a method for composing a surrogate operator when the true operator is unknown. A neural network is used to improve the surrogate model iteratively to decrease the difference between the observations and the results of the surrogate model. A twin experiment suggests that the proposed method outperforms approaches that tentatively use a specific operator throughout the data assimilation process.