AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Learning Chaotic Dynamics in Dissipative Systems

Zongyi Li, Miguel Liu-Schiaffini, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar

NeurIPS 2022 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 4 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
add dissipativity regularization to the learned operator (ablation)Markov neural operator (MNO) · Kolmogorov flow Re=500stability under perturbed initial conditionsImproved
add dissipativity regularization (ablation)MNO · Kolmogorov flow Re=5000accuracyNo clear effect
vary dissipativity hyperparameters (loss weight, scaling factor, shell radius) (ablation)MNO · Lorenz-63step-wise and dissipative errorNo clear effect
learn identity residual instead of solution operator at small time step h (ablation)MNO · Kuramoto-Sivashinskyper-step and accumulated errorImproved
learn identity residual instead of solution operator at large time step h (ablation)MNO · Kuramoto-SivashinskyerrorNo clear effect
MNO instead of LSTM and GRUevolution operator model · Kuramoto-Sivashinsky h=1sFourier spectrum accuracyImproved
MNO instead of LSTM and GRUevolution operator model · Kuramoto-Sivashinsky h=1sother invariant statisticsNo clear effect
MNO instead of U-Net and LSTM-CNNvorticity predictor · Navier-Stokes Re=40vorticity errorImproved
train with H2 loss instead of L2 or H1 (ablation)MNO · Navier-Stokes Re=40vorticity error in L2, H1, H2 normsImproved
train with L2 or H1 loss instead of H2 (ablation)MNO · Navier-Stokes Re=40TKE and dissipation errorMixed
use derivative order slightly higher than the target quantity (e.g. velocity plus H1 loss for velocity) (ablation)MNO · Kolmogorov flow Re=500velocity errorImproved
use much higher derivative order loss (ablation)MNO · Kolmogorov flowinvariant statistics vs resolutionMixed

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