Small Ensemble-based Data Assimilation: A Machine Learning-Enhanced Data Assimilation Method with Limited Ensemble Size
This work addresses the computational efficiency problem for researchers and practitioners in fields like meteorology and oceanography using data assimilation, though it is incremental as it builds on existing ensemble methods with machine learning enhancements.
The study tackled the trade-off between accuracy and computational cost in ensemble-based data assimilation by proposing a method that combines the ensemble Kalman filter with a fully connected neural network to correct suboptimal states from small ensembles. The results showed that this approach achieved higher accuracy than traditional methods with the same ensemble size and negligible extra computational cost, as demonstrated in Lorenz systems and ocean wave simulations.
Ensemble-based data assimilation (DA) methods have become increasingly popular due to their inherent ability to address nonlinear dynamic problems. However, these methods often face a trade-off between analysis accuracy and computational efficiency, as larger ensemble sizes required for higher accuracy also lead to greater computational cost. In this study, we propose a novel machine learning-based data assimilation approach that combines the traditional ensemble Kalman filter (EnKF) with a fully connected neural network (FCNN). Specifically, our method uses a relatively small ensemble size to generate preliminary yet suboptimal analysis states via EnKF. A FCNN is then employed to learn and predict correction terms for these states, thereby mitigating the performance degradation induced by the limited ensemble size. We evaluate the performance of our proposed EnKF-FCNN method through numerical experiments involving Lorenz systems and nonlinear ocean wave field simulations. The results consistently demonstrate that the new method achieves higher accuracy than traditional EnKF with the same ensemble size, while incurring negligible additional computational cost. Moreover, the EnKF-FCNN method is adaptable to diverse applications through coupling with different models and the use of alternative ensemble-based DA methods.