aiqbench analysis
This research introduces a neural ensemble Kalman filter (EnKF) to resolve spurious oscillations in data assimilation for compressible flows with shocks. By mapping forecast ensembles to deep neural network parameters and enforcing smooth variations via physics-informed transfer learning, the method successfully avoids nonphysical features that plague classical approaches. The study demonstrates significant improvements in handling bimodal distributions near uncertain shock locations using numerical experiments on fluid dynamics benchmarks.
Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks
arXiv:2602.23461v3 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. We focus here on the ensemble Kalman filter (EnKF). We show that the poor performance of the EnKF may be attributed to the bimodal forecast distribution that can arise in the vicinity of an uncertain shock location; this violates the assumptions underpinning the EnKF, which assume a forecast which is close to Gaussian. To address this issue we introduce the new neural EnKF. The basic idea is to systematically embed neural function approximations within ensemble DA by mapping the forecast ensemble of shocked flows to the parameter space (weights and biases) of a deep neural network (NN) and to subsequently perform DA in that space. The nonlinear mapping encodes sharp and smooth flow features in an ensemble of NN parameters. Neural EnKF updates are therefore well-behaved only if the NN parameters vary smoothly within the neural representation of the forecast ensemble. We show that such a smooth variation of network parameters can be enforced via physics-informed transfer learning, and demonstrate that in so-doing the neural EnKF avoids the spurious oscillations and nonphysical features that plague the EnKF. The applicability of the neural EnKF is demonstrated through a series of systematic numerical experiments with the inviscid Burgers' equation, the Sod shock tube, and a two-dimensional blast wave.
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. We focus here on the ensemble Kalman filter (EnKF). We show that the poor performance of the EnKF may be attributed to the bimodal forecast distribution that can arise in the vicinity of an uncertain shock location; this violates the assumptions underpinning the EnKF, which assume a forecast which is close to Gaussian. To address this issue we introduce the new neural EnKF. The basic idea is to systematically embed neural function approximations within ensemble DA by mapping the forecast ensemble of shocked flows to the parameter space (weights and biases) of a deep neural network (NN) and to subsequently perform DA in that space. The nonlinear mapping encodes sharp and smooth flow features in an ensemble of NN parameters. Neural EnKF updates are therefore well-behaved only if the NN parameters vary smoothly within the neural representation of the forecast ensemble. We show that such a smooth variation of network parameters can be enforced via physics-informed transfer learning, and demonstrate that in so-doing the neural EnKF avoids the spurious oscillations and nonphysical features that plague the EnKF. The applicability of the neural EnKF is demonstrated through a series of systematic numerical experiments with the inviscid Burgers' equation, the Sod shock tube, and a two-dimensional blast wave.
Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG)
arXiv:2602.23461 [physics.flu-dyn]
(or arXiv:2602.23461v3 [physics.flu-dyn] for this version)
https://doi.org/10.48550/arXiv.2602.23461 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.
Full text under the publisher's open licence · 325 words
Related coverage
Neural ensemble Kalman filter: Data assimilation for compressible flows with shocks
arXiv · Jun 12, 2026
Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks
arXiv · Oct 16, 2026
Efficient Real-Time Adaptation of ROMs for Unsteady Flows Using Data Assimilation
arXiv · Sep 1, 2026
Accounting for model error in ensemble variational data assimilation through learned generative dynamics
arXiv · Oct 14, 2026