Active Learning Boosts Data-Driven Reduced Models for Digital Twins

research #rom 🔬 Research|Analyzed: Jan 5, 2026 09:55•

Published: Jan 5, 2026 05:00

•

1 min read

Analysis

This paper presents a valuable active learning framework for improving the efficiency and accuracy of reduced-order models (ROMs) used in digital twins. By intelligently selecting training parameters, the method enhances ROM stability and accuracy compared to random sampling, potentially reducing computational costs in complex simulations. The Bayesian operator inference approach provides a probabilistic framework for uncertainty quantification, which is crucial for reliable predictions.

Key Takeaways

•Introduces an active learning framework for data-driven ROMs.
•Uses Bayesian operator inference for probabilistic ROM solutions.
•Demonstrates improved ROM stability and accuracy compared to random sampling.

Reference / Citation

View Original

"Since the quality of data-driven ROMs is sensitive to the quality of the limited training data, we seek to identify training parameters for which using the associated training data results in the best possible parametric ROM."

ArXiv Stats MLJan 5, 2026 05:00

* Cited for critical analysis under Article 32.

Older

The ascent of the AI therapist

Newer

Deep learning estimation of the spectral density of functional time series on large domains