3 papers
physics.flu-dyn2026
A Hybrid POD-Autoencoder Framework for Reduced Order Modeling of Turbulent Flow via Strategic Field Decomposition
Xianglong Li, Zeng Liu, Zhan Wang +3
This study proposes a hybrid reduced-order modeling (ROM) framework for the simulation of turbulent flow. The central idea is to decompose flow dynamics according to their temporal…
physics.ao-ph2026
Enabling High-Accuracy Data Assimilation with Limited Ensembles via Machine Learning-Based Covariance Correction
Zhou Yao, Zhilin Li, Li Zhao +4
Data assimilation (DA) integrates numerical model forecasts with observations to achieve the optimal state estimation. Ensemble-based methods, such as the ensemble Kalman filter (E…
cs.LG2025
Small Ensemble-based Data Assimilation: A Machine Learning-Enhanced Data Assimilation Method with Limited Ensemble Size
Zhilin Li, Zhou Yao, Xianglong Li +5
Ensemble-based data assimilation (DA) methods have become increasingly popular due to their inherent ability to address nonlinear dynamic problems. However, these methods often fac…