Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Abstract
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which the resolved variables are affected by model error originating from the hidden small-scale variables. The algorithm is then compared to an ensemble Kalman filter that adaptively mitigates model and sampling errors, and to the IEnKF-Q. The IEnKF-G is generally more accurate in the tested configurations, with substantial gains under partial observations and significant model error. This demonstrates the potential of generative data-driven models when paired with classical data assimilation methods, particularly when model error is substantial.
Related
- Ensemble Score Filter with Image Inpainting for Data Assimilation in Tracking Surface Quasi-geostrophic Dynamics with Partial Observations
- Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data Assimilation
- IEnSF: Iterative ensemble score filter for reducing error in posterior score estimation in nonlinear data assimilation
- LFS-SEnDA: a global ocean forecast system with an efficient Sliding-Ensemble-based Data Assimilation scheme
- Ensemble Forecast Updates without Model Re-integration Based on Ultra-rapid Data Assimilation: Idealized Experiments with a Heavy Rainfall Case
BibTeX
@misc{bocquet2026accounting,
title = {{Accounting for model error in ensemble variational data assimilation through learned generative dynamics}},
author = {Marc Bocquet and Tobias S. Finn and Sibo Cheng},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17333},
eprint = {2610.17333},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17333},
}
RIS
TY - UNPB
TI - Accounting for model error in ensemble variational data assimilation through learned generative dynamics
AU - Marc Bocquet
AU - Tobias S. Finn
AU - Sibo Cheng
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17333
UR - https://arxiv.org/abs/2610.17333
AB - Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which the resolved variables are affected by model error originating from the hidden small-scale variables. The algorithm is then compared to an ensemble Kalman filter that adaptively mitigates model and sampling errors, and to the IEnKF-Q. The IEnKF-G is generally more accurate in the tested configurations, with substantial gains under partial observations and significant model error. This demonstrates the potential of generative data-driven models when paired with classical data assimilation methods, particularly when model error is substantial.
ER -