Assimilating Observations to Improve Arctic Sea Ice Seasonal Prediction: A Variational Autoencoder Latent Space Particle Filter Approach
Open Access
- 27 May 2025
- journal article
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 130 (6)
Abstract
Assimilating observational data is essential for improving Arctic sea ice model prediction, yet the high‐dimensional nature of such models poses challenges for applying nonlinear particle filtering methods. To address this, we propose a Latent Space Particle Filter (LSPF) approach that leverages a variational autoencoder (VAE) deep neural network to extract low‐dimensional representations of sea ice physical fields. This method compresses the high‐dimensional data into a latent subspace, enabling efficient statistical sampling and generating a large number of low‐dimensional samples for nonlinear particle filtering. We train the VAE using multiple sea ice reanalysis data sets and conduct historical assimilation experiments using the latest ice‐ocean coupled model developed by Princeton University's Geophysical Fluid Dynamics Laboratory. Results indicate that assimilating satellite observations of sea ice concentration and thickness with LSPF during the winter freezing period significantly reduces model errors, particularly for sea ice thickness. All simulations are extended to September without additional assimilation and evaluated with independent satellite observations and mooring data. Findings further demonstrate that wintertime nonlinear particle filter assimilation can improve prediction skill, especially when performed every 3 days, reducing model errors by approximately 30%–50%. Therefore, the LSPF method proposed in this study provides a promising and effective solution for nonlinear data assimilation in realistic high‐dimensional geoscience applications.Keywords
Funding Information
- National Natural Science Foundation of China (42130605, 42206253, 42205025, 72293604, 41922044)
- Guangdong Ocean University (060302032305, 060302032105, 060302032102)
This publication has 48 references indexed in Scilit:
- Skillful regional prediction of Arctic sea ice on seasonal timescalesGeophysical Research Letters, 2017
- Skillful seasonal forecasts of Arctic sea ice retreat and advance dates in a dynamical forecast systemGeophysical Research Letters, 2016
- Sea ice decline and 21st century trans‐Arctic shipping routesGeophysical Research Letters, 2016
- Impact of sea ice initialization on sea ice and atmosphere prediction skill on seasonal timescalesGeophysical Research Letters, 2016
- Model forecast skill and sensitivity to initial conditions in the seasonal Sea Ice OutlookGeophysical Research Letters, 2015
- Will Arctic sea ice thickness initialization improve seasonal forecast skill?Geophysical Research Letters, 2014
- Assimilating SMOS sea ice thickness into a coupled ice‐ocean model using a local SEIK filterJournal of Geophysical Research: Oceans, 2014
- Predicting September sea ice: Ensemble skill of the SEARCH Sea Ice Outlook 2008-2013Geophysical Research Letters, 2014
- Seasonal to interannual Arctic sea ice predictability in current global climate modelsGeophysical Research Letters, 2014
- Particle filter‐based data assimilation for a three‐dimensional biological ocean model and satellite observationsJournal of Geophysical Research: Oceans, 2013