analiza aiqbench
This paper tackles a known weakness of the ensemble Kalman filter: it smears shock fronts when the shock's location is uncertain. The authors propose running the filter's updates in a learned latent space, where a coordinate-conditioned auto-decoder lets shocks move coherently instead of being blended at displaced positions. For ML readers, the practical question is whether learned latent representations can make classical estimation methods work on discontinuous physics. The evidence so far is limited to 1D and 2D benchmark problems (Sod shock tube, Mach 2 cylinder, immersed body), so generalization to realistic three-dimensional flows remains to be shown.
Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks
arXiv:2606.12559v2 Announce Type: replace-cross Abstract: The ensemble Kalman filter (EnKF) is widely adopted for sequential data assimilation, but fails for solutions with discontinuities, such as shocks in compressible flows. For ensembles with uncertainty in discontinuity location, the EnKF analysis can lose physical consistency, which can be viewed through three lenses: (i) bimodal pointwise statistics in the forecast ensemble, (ii) mixed-sign analysis weights in the affine superposition of forecast members, and (iii) spatially distributed Kalman-gain profiles that modify the state around a discontinuity rather than translating it coherently. In order to preserve flow features in the analysis state and, as such, maintain physical consistency, a feature-preserving latent-EnKF is introduced. The proposed method performs the ensemble update in a low-dimensional latent space learned by a coordinate-conditioned auto-decoder. The latent representation retains near-Gaussian ensemble statistics and provides coordinates in which flow features vary coherently across the forecast ensemble. The EnKF updates performed on the latent codes are decoded into coherent changes in the represented flow features, translating shocks through coordinate morphing rather than superposing them at displaced locations. The corresponding Kalman-gain profiles generated by the latent-EnKF exhibit an approximately step-like variation across the discontinuities, allowing the fronts to translate while preserving sharp features and monotonicity. Sod shock-tube, Mach~2 shock-cylinder, and immersed-body shape-inference tests with sparse, noisy observations demonstrate accurate recovery of shocks and contact discontinuities without spurious oscillations.
Abstract:The ensemble Kalman filter (EnKF) is widely adopted for sequential data assimilation, but fails for solutions with discontinuities, such as shocks in compressible flows. For ensembles with uncertainty in discontinuity location, the EnKF analysis can lose physical consistency, which can be viewed through three lenses: (i) bimodal pointwise statistics in the forecast ensemble, (ii) mixed-sign analysis weights in the affine superposition of forecast members, and (iii) spatially distributed Kalman-gain profiles that modify the state around a discontinuity rather than translating it coherently. In order to preserve flow features in the analysis state and, as such, maintain physical consistency, a feature-preserving latent-EnKF is introduced. The proposed method performs the ensemble update in a low-dimensional latent space learned by a coordinate-conditioned auto-decoder. The latent representation retains near-Gaussian ensemble statistics and provides coordinates in which flow features vary coherently across the forecast ensemble. The EnKF updates performed on the latent codes are decoded into coherent changes in the represented flow features, translating shocks through coordinate morphing rather than superposing them at displaced locations. The corresponding Kalman-gain profiles generated by the latent-EnKF exhibit an approximately step-like variation across the discontinuities, allowing the fronts to translate while preserving sharp features and monotonicity. Sod shock-tube, Mach~2 shock-cylinder, and immersed-body shape-inference tests with sparse, noisy observations demonstrate accurate recovery of shocks and contact discontinuities without spurious oscillations.
Computational Physics (physics.comp-ph); Machine Learning (cs.LG); Numerical Analysis (math.NA); Fluid Dynamics (physics.flu-dyn)
arXiv:2606.12559 [physics.comp-ph]
(or arXiv:2606.12559v2 [physics.comp-ph] for this version)
https://doi.org/10.48550/arXiv.2606.12559 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 321 cuvinte
Subiecte conexe
Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
arXiv · 10 iun. 2026
Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks
arXiv · 12 iun. 2026
LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations
arXiv · 6 oct. 2026
Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks
arXiv · 21 sept. 2026