← Papers
Latent models

AdaLED

Adaptive learning of effective dynamics for online modeling of complex systems

Paper title Adaptive learning of effective dynamics for online modeling of complex systems

Kičić et al. (ETH Zurich, Harvard) · Aero & CFD · General PDEs · Public: code

Paper arXiv 2304.01732PDF

Couples a running solver with a surrogate trained online during the same run: a convolutional autoencoder and an ensemble of probabilistic LSTMs. The simulation switches to the surrogate when its error against the solver and the ensemble uncertainty are below set thresholds, and returns to the solver when the uncertainty rises.

Published
CMAME

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. Latent modelsD-JEPA — One geometry latent, reused across flow conditions and physics
  2. Latent modelsCourant — A state-adaptive Perceiver surrogate with local support
  3. Latent modelsAeroJEPA — Semantic Latent Representations for 3D Aerodynamic Fields