Xuesen Chu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuesen Chu has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Fei Wu
Zhejiang University
3 shared publications - Hongkun Zhang
The First Affiliated Hospital of Zhejiang University School of Medicine
3 shared publications - Xiaojing Lv
China Ship Scientific Research Center, Wuxi 214082, China
3 shared publications - Zhengxing Huang
Zhejiang University, Hangzhou, China
3 shared publications Guangwen Yang
Tsinghua University
2 shared publications- Guangwen Yang
Tsinghua University
2 shared publications
Latest Publications
- Open Access
- 2 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (13) , 6622
RenaNet: Reynolds-Aware Neural Network for Rapid Flow Field Prediction via Lattice Boltzmann Simulations
Rapid surrogate models are attractive for iterative computational fluid dynamics (CFD) design loops, though defining their operating envelope remains crucial. This study proposes RenaNet, a Reynolds-aware convolutional gated recurrent unit (ConvGRU) surrogate, for predicting two-dimensional laminar and transitional flows past cylinder and square obstacles. Using two initial flow snapshots and a Reynolds-number map, the model predicts spatiotemporal flow states up to 2000 time steps into the future, with Lattice Boltzmann Method (LBM) simulations serving as ground truth. Trained on Reynolds numbers of (cylinder) and (square), RenaNet achieves a minimum validation mean squared error (MSE) of . A Reynolds-number ablation shows that removing the conditioning channel increases the validation MSE to , while a ConvLSTM baseline gives with 24% more parameters. RenaNet also uses a direct long-horizon prediction interface for distant target frames. Auxiliary physics diagnostics confirm that predictions trained via MSE maintain acceptable continuity residuals across fitting, interpolation, and extrapolation cases. The average inference time for a 1000-step prediction horizon is approximately 1.25 s, delivering a 500-fold speedup over the reference LBM solver. Interpolation errors range from to depending on Reynolds number and geometry, while extrapolation beyond the training regime increases errors to the order of . These results establish RenaNet as a robust, parameter-efficient surrogate for laminar and transitional flows, with a clearly characterized operational boundary that informs future extensions into turbulent regimes.- 2 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (13) , 6622
Open AccessRenaNet: Reynolds-Aware Neural Network for Rapid Flow Field Prediction via Lattice Boltzmann Simulations
Rapid surrogate models are attractive for iterative computational fluid dynamics (CFD) design loops, though defining their operating envelope remains crucial. This study proposes RenaNet, a Reynolds-aware convolutional gated recurrent unit (ConvGRU) surrogate, for predicting two-dimensional laminar and transitional flows past cylinder and square obstacles. Using two initial flow snapshots and a Reynolds-number map, the model predicts spatiotemporal flow states up to 2000 time steps into the future, with Lattice Boltzmann Method (LBM) simulations serving as ground truth. Trained on Reynolds numbers of (cylinder) and (square), RenaNet achieves a minimum validation mean squared error (MSE) of . A Reynolds-number ablation shows that removing the conditioning channel increases the validation MSE to , while a ConvLSTM baseline gives with 24% more parameters. RenaNet also uses a direct long-horizon prediction interface for distant target frames. Auxiliary physics diagnostics confirm that predictions trained via MSE maintain acceptable continuity residuals across fitting, interpolation, and extrapolation cases. The average inference time for a 1000-step prediction horizon is approximately 1.25 s, delivering a 500-fold speedup over the reference LBM solver. Interpolation errors range from to depending on Reynolds number and geometry, while extrapolation beyond the training regime increases errors to the order of . These results establish RenaNet as a robust, parameter-efficient surrogate for laminar and transitional flows, with a clearly characterized operational boundary that informs future extensions into turbulent regimes. - 26 March 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (4)
Generating Cardiac Magnetic Resonance Images from Electrocardiograms — A Multicenter Study
- 26 March 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (4)
Generating Cardiac Magnetic Resonance Images from Electrocardiograms — A Multicenter Study
- Open Access
- 9 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (2) , 721
Parallel Optimization for Coupled Lattice Boltzmann-Finite Volume Method on Heterogeneous Many-Core Supercomputer
Nowadays various coupling strategies have been developed to combine the strengths of different numerical methods in computational fluid dynamics (CFD), among which the coupled algorithm of the lattice Boltzmann-finite volume method (LBM-FVM) has gained widespread attention. However, research on parallel optimization of LBM-FVM coupled solvers remains limited, mostly focused on independent solvers. In this work, we proposed a flexible framework and optimization schemes to explore the coordinated balance of accuracy-efficiency-hardware adaptability. First, we designed a processor layout strategy to address load imbalance and communication redundancy in the coupled solver. We then developed several parallelization techniques, including LBM restructuring, data reuse, and SIMD optimization for targeted kernels on the most advanced architecture of the Sunway series in China, namely SW26010P heterogeneous many-core processors, which provide hardware architectural advantages well suited for large-scale parallel computational fluid dynamics. Finally, the accuracy of the LBM-FVM coupling simulations was validated through benchmark simulations of 2D/3D lid-driven cavity flow. The results show that our LBM-FVM coupling solver can accurately capture flow characteristics, with vortex structures consistent with experimental data. Additionally, we achieved a 152× speedup for the LBM solver and a 126× speedup for the coupled simulation compared to the standalone FVM simulation on the New Sunway supercomputer system. Our approach marks a milestone in the field of LBM implementations and provides a promising future for coupled algorithms in CFD.
- 9 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (2) , 721
Open AccessParallel Optimization for Coupled Lattice Boltzmann-Finite Volume Method on Heterogeneous Many-Core Supercomputer
Nowadays various coupling strategies have been developed to combine the strengths of different numerical methods in computational fluid dynamics (CFD), among which the coupled algorithm of the lattice Boltzmann-finite volume method (LBM-FVM) has gained widespread attention. However, research on parallel optimization of LBM-FVM coupled solvers remains limited, mostly focused on independent solvers. In this work, we proposed a flexible framework and optimization schemes to explore the coordinated balance of accuracy-efficiency-hardware adaptability. First, we designed a processor layout strategy to address load imbalance and communication redundancy in the coupled solver. We then developed several parallelization techniques, including LBM restructuring, data reuse, and SIMD optimization for targeted kernels on the most advanced architecture of the Sunway series in China, namely SW26010P heterogeneous many-core processors, which provide hardware architectural advantages well suited for large-scale parallel computational fluid dynamics. Finally, the accuracy of the LBM-FVM coupling simulations was validated through benchmark simulations of 2D/3D lid-driven cavity flow. The results show that our LBM-FVM coupling solver can accurately capture flow characteristics, with vortex structures consistent with experimental data. Additionally, we achieved a 152× speedup for the LBM solver and a 126× speedup for the coupled simulation compared to the standalone FVM simulation on the New Sunway supercomputer system. Our approach marks a milestone in the field of LBM implementations and provides a promising future for coupled algorithms in CFD.
- 1 April 2025
- Published by Springer Nature in Journal of Hydrodynamics
- Vol. 37 (2) , 230-238
Liutex-shear interaction in Lamb-Oseen vortex and three-dimensional cylinder flow at Re = 3 900 simulated with SWLBM
- 1 April 2025
- Published by Springer Nature in Journal of Hydrodynamics
- Vol. 37 (2) , 230-238
Liutex-shear interaction in Lamb-Oseen vortex and three-dimensional cylinder flow at Re = 3 900 simulated with SWLBM
- 25 November 2024
- Published by Elsevier in Ocean Engineering
- Vol. 315
Physics-enhanced data-driven turbulence model for flow around submerged bodies
- 25 November 2024
- Published by Elsevier in Ocean Engineering
- Vol. 315
Physics-enhanced data-driven turbulence model for flow around submerged bodies
- 3 October 2024
- Published by Springer Nature
- p. 551-561
Physical-Priors-Guided Aortic Dissection Detection Using Non-Contrast-Enhanced CT Images
- 3 October 2024
- Published by Springer Nature
- p. 551-561
Physical-Priors-Guided Aortic Dissection Detection Using Non-Contrast-Enhanced CT Images
- 3 October 2024
- Published by Springer Nature
- p. 109-119
Cross-Modality Cardiac Insight Transfer: A Contrastive Learning Approach to Enrich ECG with CMR Features
- 3 October 2024
- Published by Springer Nature
- p. 109-119
Cross-Modality Cardiac Insight Transfer: A Contrastive Learning Approach to Enrich ECG with CMR Features
- 6 September 2024
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 133 (10) , 104001
Interfacial Thermal Fluctuations Stabilize Bulk Nanobubbles
Consensus on bulk nanobubble stability remains elusive, despite accepted indirect evidence for longevity. We develop a nanobubble evolution model by incorporating thermal capillary wave theory that reveals that dense nanobubbles generated by acoustic cavitation tend to shrink and intensify interfacial thermal fluctuations; this significantly reduces surface tension to neutralize enhanced Laplace pressure, and secures their stabilization at a finite size. A stability criterion emerges: thermal fluctuation intensity scales superlinearly with curvature: , . The model prolongs the time frame for nanobubble contraction to 2 orders of magnitude beyond classical theory estimates, and captures the equilibrium radius (90–215 nm) within the experimental range.- 6 September 2024
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 133 (10) , 104001
Interfacial Thermal Fluctuations Stabilize Bulk Nanobubbles
Consensus on bulk nanobubble stability remains elusive, despite accepted indirect evidence for longevity. We develop a nanobubble evolution model by incorporating thermal capillary wave theory that reveals that dense nanobubbles generated by acoustic cavitation tend to shrink and intensify interfacial thermal fluctuations; this significantly reduces surface tension to neutralize enhanced Laplace pressure, and secures their stabilization at a finite size. A stability criterion emerges: thermal fluctuation intensity scales superlinearly with curvature: , . The model prolongs the time frame for nanobubble contraction to 2 orders of magnitude beyond classical theory estimates, and captures the equilibrium radius (90–215 nm) within the experimental range.