← Back to all news
arXiv Machine Learning By Hemanth Chandravamsi, Hangchuan Hu, Ponkrshnan Thiagarajan, Tamer A. Zaki

Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks

Read the original on arXiv Machine Learning →

The paper introduces a feature‑preserving latent‑EnKF for data assimilation of flows with shocks, addressing the failure of traditional EnKF when discontinuities are present. By updating ensembles in a low‑dimensional latent space learned via a coordinate‑conditioned auto‑decoder, the method maintains near‑Gaussian statistics and coherent flow features, enabling shock translation through coordinate morphing rather than superposition. Experiments on Sod shock‑tube, Mach 2 shock‑cylinder, and immersed‑body shape‑inference problems show accurate shock recovery without spurious oscillations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 11

Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks

arXiv:2602. 23461v2 Announce Type: replace-cross Abstract: Data assimilation (DA) for compressible flows with shocks is challenging because many classical DA methods generate spurious oscillations and nonphysical features near uncertain shocks.

By Xu-Hui Zhou, Lorenzo Beronilla, Michael K. Sleeman, Hangchuan Hu, Matthias Morzfeld, Andrew M. Stuart, Tamer A. Zaki
fine-tuning
More like this →
arXiv Statistics ML
Sep 17

A Continuous-Time Ensemble Kalman-Bucy Smoother for Causal Inference and Model Discovery

The paper presents an ensemble Kalman–Bucy smoother (EnKBS) for continuous‑time data assimilation of nonlinear dynamical systems, reconstructing conditional distributions from ensemble moments without needing tangent‑linear or adjoint models. It demonstrates that EnKBS achieves exact smoothing mean and covariance in the infinite‑ensemble limit for linear‑Gaussian systems and incorporates regularization techniques like covariance localization and inflation for high‑dimensional problems. The method is applied to Bayesian inference of causal relationships in a dyadic trigger‑feedback model and to an iterative learning algorithm that uncovers the structure and hidden parameters of a reduced‑order model of midlatitude atmospheric circulation, all with small ensembles under partial observations.

By Zhang Jiang (University of Wisconsin-Madison), Marios Andreou (University of Wisconsin-Madison), Sebastian Reich (University of Potsdam), Nan Chen (University of Wisconsin-Madison)
More like this →