New Machine Learning Framework Improves Reduced-Order Model Accuracy Through Uncertainty-Aware Multi-Fidelity Learning
Researchers have proposed an uncertainty-aware, multi-fidelity closure modeling framework based on conditional normalizing flows to improve the predictive accuracy of reduced-order models (ROMs) for complex multiscale systems. The approach addresses the longstanding 'closure problem' by learning a probabilistic mapping from low-fidelity to high-fidelity model coefficients, with two correction strategies—direct learning and residual learning—tested on a 2D Navier-Stokes vortex merging problem. The work is significant because it not only improves ROM accuracy but also provides uncertainty quantification, which is essential for building confidence in ROM-based predictions in practical engineering and scientific applications.
A preprint posted to arXiv introduces a multi-fidelity (MF) learning framework that uses conditional normalizing flows—a class of deep generative models—to address the closure problem in reduced-order models (ROMs). ROMs are computationally efficient surrogates for complex multiscale systems, but they suffer from truncation errors and poor representation of interactions between resolved and unresolved scales. The proposed framework learns a probabilistic mapping from low-fidelity ROM coefficients to high-fidelity counterparts, enabling both improved predictive accuracy and uncertainty quantification. Two correction strategies are evaluated: direct learning, which predicts high-fidelity coefficients directly from low-fidelity inputs, and residual learning, which models the discrepancy between the two fidelity levels. Both strategies outperform uncorrected ROMs, with residual learning showing consistently superior performance. The framework is validated on a vortex merging problem governed by the two-dimensional Navier-Stokes equations. The built-in uncertainty quantification is highlighted as a critical feature for assessing prediction confidence and enabling reliable deployment of ROMs in real-world applications.
What's missing
As a preprint, this work has not yet undergone peer review. The study is validated on a single benchmark problem (2D vortex merging); generalizability to other multiscale systems or higher-dimensional problems remains untested.
What different sources said
- arXiv cs.LGCenter
Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.