AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations

Pengpeng Xiao, Phillip Si, Peng Chen

ICLR 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evolve latent dynamics with LDNet surrogate instead of full dynamicsLD-EnSF · Kolmogorov FlowT_d (s): 10,829 -> 0.049Improved
evolve latent dynamics with LDNet surrogate instead of full dynamicsLD-EnSF · Tsunami ModelingT_d (s): 211.30 -> 0.050Improved
evolve latent dynamics with LDNet surrogate instead of full dynamicsLD-EnSF · Atmospheric ModelingT_d (s): 35,603 -> 0.070Improved
assimilate in a 52-dim LDNet latent space instead of 512-dim VAE latent spaceLD-EnSF · Atmospheric ModelingT_f (s): 2.42 -> 1.42Improved
skip decoding to full state at every assimilation stepLD-EnSF · Atmospheric ModelingT_r (s): 35.08 -> 0.017Improved
use improved LDNet (shifted initial latent state, two-stage training, ResNet and Fourier reconstruction net) rather than original LDNet (ablation)LDNet · Tsunami Modelingrelative RMSE of full-state approximationImproved
add Fourier encoding and improved architecture to LDNet (ablation)LDNet · Kolmogorov Flowrelative RMSE of full-state approximationImproved
replace VAE-dyn (VAE with LSTM) latent dynamics by LDNetLD-EnSF · Kolmogorov, Tsunami, Atmosphericrelative RMSE of full-state approximationImproved
use VAE-dyn surrogate as forward model in Latent-EnSFLatent-EnSF · Kolmogorov, Tsunami, Atmosphericassimilation relative RMSEHurt
assimilate in latent space instead of full spaceEnSF · Kolmogorov, Tsunami, Atmosphericassimilation relative RMSEImproved
raise observation noise from none to 5%, 10%, 20% (ablation)LD-EnSF · Kolmogorov, Tsunami, Atmosphericrelative RMSE of states and parametersHurt
use nonstationary Gaussian instead of Gaussian observation noise (ablation)LD-EnSF · Tsunami ModelingAssimilation error: 0.053 -> 0.086Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy