Interpretable structural model error discovery from sparse assimilation increments using spectral bias‐reduced neural networks: A quasi‐geostrophic turbulence test …

R Mojgani, A Chattopadhyay… - Journal of Advances in …, 2024 - Wiley Online Library
Earth system models suffer from various structural and parametric errors in their
representation of nonlinear, multi‐scale processes, leading to uncertainties in their long …

[PDF][PDF] xesn: Echo state networks powered by Xarray and Dask

TA Smith, SG Penny, JA Platt, TC Chen - Journal of Open Source …, 2024 - joss.theoj.org
Xesn is a Python package that allows scientists to easily design Echo State Networks
(ESNs) for forecasting problems. ESNs are a Recurrent Neural Network architecture …

Dynamic-Mode Decomposition of Geostrophically Balanced Motions from SWOT Altimetry

T Uchida, Y Badarvada, KE Lapo, X Xu, JJ Early… - arXiv preprint arXiv …, 2024 - arxiv.org
The decomposition of oceanic flow into its balanced and unbalanced motions carries
theoretical and practical significance for the oceanographic community. These two motions …

Nonlinear ensemble filtering with diffusion models: Application to the surface quasi-geostrophic dynamics

F Bao, HG Chipilski, S Liang, G Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
The intersection between classical data assimilation methods and novel machine learning
techniques has attracted significant interest in recent years. Here we explore another …