Exploiting temporal coherence for self-supervised denoising of turbulent flows
- 1 July 2026
- journal article
- Published by AIP Publishing in Physics of Fluids
- Vol. 38 (7)
Abstract
Denoising plays a crucial role in experimental fluid mechanics, where measurement noise can significantly contaminate flow structures and distort statistical quantities. A self-supervised denoising framework, incorporating a squeeze-and-excitation (SE) attention module and a convolutional long short-term memory (ConvLSTM) unit, referred to as SE–ConvLSTM, is developed by exploiting the temporal coherence of flows. The model reconstructs the target flow field from a sequence of preceding noisy snapshots, with performance primarily governed by the temporal correlation of the input data, determined by the input time span and the temporal interval between snapshots. The denoising capability of SE–ConvLSTM is systematically evaluated for two-dimensional flow fields under a wide range of noise intensities, noise types, and flow configurations, with comparisons against both classical and deep-learning methods. The results demonstrate that SE–ConvLSTM achieves superior performance for temporally uncorrelated noise, enabling more accurate noise removal while preserving fine-scale flow structures, spatial continuity, and turbulent statistics, particularly under severe noise contamination. The denoising performance is closely related to the ratio of the integral time scales of the noisy and reference flows, with improved accuracy obtained when temporal coherence is better preserved in the noisy field. Extension to three-dimensional flow fields further confirms the robustness of the framework in reconstructing volumetric structures. Overall, the SE–ConvLSTM provides an effective and generalizable approach for denoising noisy flow measurements.Keywords
Funding Information
- National Natural Science Foundation of China (12302367)
- Zhejiang Provincial Natural Science Foundation of China (LQ24A020013)
This publication has 59 references indexed in Scilit:
- Super-resolution analysis via machine learning: a survey for fluid flowsTheoretical and Computational Fluid Dynamics, 2023
- Image denoising in the deep learning eraArtificial Intelligence Review, 2022
- Review of Acquisition and Signal Processing Methods for Electromagnetic Noise Reduction and Retrieval of Surface Nuclear Magnetic Resonance ParametersSurveys in Geophysics, 2022
- Tomographic long-distance µPIV to investigate the small scales of turbulence in a jet at high Reynolds numberExperiments in Fluids, 2021
- PIV anisotropic denoising using uncertainty quantificationExperiments in Fluids, 2017
- Proper orthogonal decomposition truncation method for data denoising and order reductionExperiments in Fluids, 2017
- On PIV random error minimization with optimal POD-based low-order reconstructionExperiments in Fluids, 2015
- Denoising of time-resolved PIV for accurate measurement of turbulence spectra and reduced error in derivativesExperiments in Fluids, 2012
- Denoising methods for time-resolved PIV measurementsExperiments in Fluids, 2011
- Effect of resolution on the speed and accuracy of particle image velocimetry interrogationExperiments in Fluids, 1992