arXiv:2606.09857v1 Announce Type: new Abstract: Reduced-order models (ROMs) provide an efficient surrogate for complex multiscale systems, but their predictive accuracy is often compromised by truncation errors and the inadequate representation of interactions between resolved and unresolved scales. The missing effect of truncated (unresolved) scales on ROM (resolved) scales is often denoted as the closure problem. In this work, we formulate ROM closure modeling as a multi-fidelity (MF) learning problem and propose an uncertainty-aware MF framework based on conditional normalizing flow to enha
The increasing complexity of multi-scale systems in AI and scientific computing necessitates more robust and uncertainty-aware solutions for model reduction and prediction, making this a timely development in computational science.
This work directly addresses a core challenge in scientific machine learning and AI, enabling more accurate and reliable reduced-order models crucial for accelerating research and development in fields from fluid dynamics to materials science.
The explicit incorporation of uncertainty-aware multi-fidelity learning via conditional normalizing flows offers a more sophisticated approach to closure modeling, improving the predictive power and trustworthiness of AI-driven simulations.
- · Computational scientists
- · AI/ML researchers in scientific computing
- · Engineering simulation software providers
- · Traditional ROM methods lacking uncertainty quantification
- · Systems relying on highly inaccurate surrogate models
Improved accuracy and efficiency of complex system simulations across various scientific and engineering disciplines.
Faster design cycles and optimized performance for products and systems developed using these enhanced simulation capabilities.
Accelerated discovery of new materials, energy solutions, and biomedical treatments due to more reliable computational models.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG