.png){kind=icon}
.png){kind=icon}
Return
ACTIVE OPERATOR INFERENCE FOR LEARNING LOW-DIMENSIONAL DYNAMICAL-SYSTEM MODELS FROM NOISY DATA
.png){kind=icon}
OA
AI
DOI：10.1137/21M1439729.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Noise poses a challenge for learning dynamical-system models because already small variations can distort the dynamics described by trajectory data. This work builds on operator inference from scientific machine learning to infer low-dimensional models from high-dimensional state trajectories polluted with noise. The presented analysis shows that, under certain conditions, the inferred operators are unbiased estimators of the well-studied projection-based reduced operators from traditional model reduction. Furthermore, the connection between operator inference , projection-based model reduction enables bounding the mean-squared errors of predictions made with the learned models with respect to traditional reduced models. The analysis also motivates an active operator inference approach that judiciously samples high-dimensional trajectories with the aim of achieving a low mean-squared error by reducing the effect of noise. Numerical experiments with high-dimensional linear and nonlinear state dynamics demonstrate that predictions obtained with active operator inference have orders of magnitude lower mean-squared errors than operator inference with traditional, equidistantly sampled trajectory data.
Keywords:
scientific machine learning
nonintrusive model reduction
operator inference
design of experiments
reduced models
noise
Journal
IF:
2.6
Papers:
5.1K
Citations:
1.8W