Uncertainty-aware flow field reconstruction using SVGP Kolmogorov–Arnold networks
Year: 2026
Type: article
Abstract: Reconstructing time-resolved flow fields from temporally sparse velocimetry measurements is critical for characterizing many complex thermal–fluid systems. The present work introduces a machine-learning framework for uncertainty-aware flow reconstruction using sparse variational Gaussian processes in the Kolmogorov-Arnold network topology (SVGP-KAN). This approach extends the classical foundations of Linear Stochastic Estimation (LSE) and Spectral Analysis Modal Methods (SAMM) while enabling principled epistemic uncertainty quantification. A systematic comparison of this framework is performed with the classical reconstruction methods as well as Kalman filtering. Using synthetic data from pulsed impingement jet flows, we assess performance across fractional PIV sampling rates ranging from 0.5% to 10%. Evaluation metrics include reconstruction error, generalization gap, structure preservation, and uncertainty calibration. The SVGP-KAN methods achieve reconstruction accuracy comparable to established methods, while also providing well-calibrated uncertainty estimates that reliably indicate when and where predictions degrade. The results demonstrate a robust, data-driven framework for flow field reconstruction with meaningful uncertainty quantification and offer practical guidance for experimental design in periodic flows.
Source: AI Thermal Fluids
Author: Y. Sungtaek Ju
Institution: University of California, Los Angeles
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,500
OpenAlex ID: W7133687922