Under a squeezing condition on the dynamics, a discrete-time square-root ensemble Kalman filter (and its surrogate-model variant) achieves long-time mean state estimation error of order ε, the observation noise level, plus surrogate error δ.
Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates and the sparsity of the observations, filtering estimates can remain accurate in the long-time horizon. As a case study, we integrate FourCastNet, a weather surrogate model, within a variational data assimilation framework using partial, noisy ERA5 data. Our results show that filtering estimates remain accurate over a year-long assimilation window and provide effective initial conditions for forecasting tasks, including extreme event prediction.
citation-role summary
background 1
citation-polarity summary
fields
math.DS 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Long-time accuracy of ensemble Kalman filters for chaotic and machine-learned dynamical systems
Under a squeezing condition on the dynamics, a discrete-time square-root ensemble Kalman filter (and its surrogate-model variant) achieves long-time mean state estimation error of order ε, the observation noise level, plus surrogate error δ.