Guoqiang Lei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guoqiang Lei has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Xuerui Mao
Beijing Institute of Technology
3 shared publications D. Exposito
2 shared publications- Jie Yao
Beijing Institute of Technology
2 shared publications - Dandan Xiao
Beijing Institute of Technology
1 shared publication - Haijun Zhang1 shared publication
- Jie Ren
State Key Laboratory of Environment Characteristics and Effects for Near-space, Beijing Institute of Technology 1 , Beijing 100081
1 shared publication
Latest Publications
- 14 October 2026
- Published by Elsevier in Computer Physics Communications
- Vol. 330
Discontinuity-aware physics-informed neural network for phase-field method in three-phase flow with phase change
- 14 October 2026
- Published by Elsevier in Computer Physics Communications
- Vol. 330
Discontinuity-aware physics-informed neural network for phase-field method in three-phase flow with phase change
- 6 July 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 565
Discontinuity-aware KAN-based physics-informed neural networks
- 6 July 2026
- Published by Elsevier in Journal of Computational Physics
- Vol. 565
Discontinuity-aware KAN-based physics-informed neural networks
- 1 July 2026
- Published by AIP Publishing in Physics of Fluids
- Vol. 38 (7)
Discontinuity-aware autoencoder for dimensionality reduction of shock-dominated supersonic flows
Supersonic flows are characterized by strong non-stationarity and discontinuity arising from the coexistence of turbulent fluctuations and shock waves. Classical dimensionality reduction approaches exhibit inherent limitations in this regime. Linear methods such as proper orthogonal decomposition (POD) are constrained by the Kolmogorov barrier, while nonlinear autoencoder (AEs)-based manifolds (e.g., multilayer perceptron, MLP, and Kolmogorov–Arnold networks, KAN) rely on inherently smooth representations and, therefore, struggle to accurately resolve discontinuities. To address these challenges, a discontinuity-aware autoencoder (DAE) is proposed to better extract low-dimensional representations of shock-dominated flows. The method extends the KAN-based AE by incorporating learnable non-smooth basis functions into the spline-based activation functions, enabling the unified representation of both smooth and discontinuous flow features. The proposed approach is evaluated on the shock-dominated Burgers' equation, a supersonic square cylinder wake, and flow past cylinder arrays involving strong shock–shock and shock–vortex interactions. The results demonstrate that the DAE consistently outperforms POD, MLP-based, and KAN-based AEs in reconstruction accuracy while requiring fewer modes and parameters. This improvement is attributed to the ability of DAE to explicitly capture discontinuous features and preserve sharp gradients without Gibbs-type oscillations. These findings suggest that incorporating discontinuity-aware representations is essential for efficient dimensionality reduction and reduced-order modeling of shock-dominated systems and provide a physically consistent framework for data-driven modeling of compressible flows.
- 1 July 2026
- Published by AIP Publishing in Physics of Fluids
- Vol. 38 (7)
Discontinuity-aware autoencoder for dimensionality reduction of shock-dominated supersonic flows
Supersonic flows are characterized by strong non-stationarity and discontinuity arising from the coexistence of turbulent fluctuations and shock waves. Classical dimensionality reduction approaches exhibit inherent limitations in this regime. Linear methods such as proper orthogonal decomposition (POD) are constrained by the Kolmogorov barrier, while nonlinear autoencoder (AEs)-based manifolds (e.g., multilayer perceptron, MLP, and Kolmogorov–Arnold networks, KAN) rely on inherently smooth representations and, therefore, struggle to accurately resolve discontinuities. To address these challenges, a discontinuity-aware autoencoder (DAE) is proposed to better extract low-dimensional representations of shock-dominated flows. The method extends the KAN-based AE by incorporating learnable non-smooth basis functions into the spline-based activation functions, enabling the unified representation of both smooth and discontinuous flow features. The proposed approach is evaluated on the shock-dominated Burgers' equation, a supersonic square cylinder wake, and flow past cylinder arrays involving strong shock–shock and shock–vortex interactions. The results demonstrate that the DAE consistently outperforms POD, MLP-based, and KAN-based AEs in reconstruction accuracy while requiring fewer modes and parameters. This improvement is attributed to the ability of DAE to explicitly capture discontinuous features and preserve sharp gradients without Gibbs-type oscillations. These findings suggest that incorporating discontinuity-aware representations is essential for efficient dimensionality reduction and reduced-order modeling of shock-dominated systems and provide a physically consistent framework for data-driven modeling of compressible flows.
- 1 December 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (12)
Feature-based modal decomposition of non-stationary flows
Linear model reduction methods are limited in providing accurate low-dimensional approximations of non-stationary flows featuring translation, rotation, scaling, etc., due to the Kolmogorov barrier. To mitigate this barrier, a Feature-based Proper Orthogonal Decomposition (FPOD) method, which is a local registration approach inspired by image processing techniques, is proposed. This method captures the spatiotemporal evolution of fluid structures through local adaptive meshing, which aligns their positions and flow field variables in the storage space and subsequently eliminates convection–diffusion effects. In numerical tests of the advection–diffusion equation, Burgers' equation, a co-rotating vortex pair, and flow around a cylinder with and without acceleration, FPOD demonstrated superior performances in modal compression, reconstruction, and prediction over linear and nonlinear registration and quadratic manifold approaches, particularly in non-stationary scenarios. Code is available at https://github.com/leigq/FPOD.
- 1 December 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (12)
Feature-based modal decomposition of non-stationary flows
Linear model reduction methods are limited in providing accurate low-dimensional approximations of non-stationary flows featuring translation, rotation, scaling, etc., due to the Kolmogorov barrier. To mitigate this barrier, a Feature-based Proper Orthogonal Decomposition (FPOD) method, which is a local registration approach inspired by image processing techniques, is proposed. This method captures the spatiotemporal evolution of fluid structures through local adaptive meshing, which aligns their positions and flow field variables in the storage space and subsequently eliminates convection–diffusion effects. In numerical tests of the advection–diffusion equation, Burgers' equation, a co-rotating vortex pair, and flow around a cylinder with and without acceleration, FPOD demonstrated superior performances in modal compression, reconstruction, and prediction over linear and nonlinear registration and quadratic manifold approaches, particularly in non-stationary scenarios. Code is available at https://github.com/leigq/FPOD.
- Open Access
- 30 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 20050-20063
Popeye: A Unified Visual-Language Model for Multisource Ship Detection From Remote Sensing Imagery
Ship detection needs to identify ship locations from remote sensing (RS) scenes. Due to different imaging payloads, various appearances of ships, and complicated background interference from the bird's eye view, it is difficult to set up a unified paradigm for achieving multi-source ship detection. To address this challenge, in this article, leveraging the large language models (LLMs)'s powerful generalization ability, a unified visual-language model called Popeye is proposed for multi-source ship detection from RS imagery. Specifically, to bridge the interpretation gap across the multi-source images for ship detection, a novel unified labeling paradigm is designed to integrate different visual modalities and the various ship detection ways, i.e., horizontal bounding box (HBB) and oriented bounding box (OBB). Subsequently, the hybrid experts encoder is designed to refine multi-scale visual features, thereby enhancing visual perception. Then, a visual-language alignment method is developed for Popeye to enhance interactive comprehension ability between visual and language content. Furthermore, an instruction adaption mechanism is proposed for transferring the pre-trained visual-language knowledge from the nature scene into the RS domain for multi-source ship detection. In addition, the segment anything model (SAM) is also seamlessly integrated into the proposed Popeye to achieve pixel-level ship segmentation without additional training costs. Finally, extensive experiments are conducted on the newly constructed ship instruction dataset named MMShip, and the results indicate that the proposed Popeye outperforms current specialist, open-vocabulary, and other visual-language models in zero-shot multi-source various ship detection tasks.
- 30 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 20050-20063
Open AccessPopeye: A Unified Visual-Language Model for Multisource Ship Detection From Remote Sensing Imagery
Ship detection needs to identify ship locations from remote sensing (RS) scenes. Due to different imaging payloads, various appearances of ships, and complicated background interference from the bird's eye view, it is difficult to set up a unified paradigm for achieving multi-source ship detection. To address this challenge, in this article, leveraging the large language models (LLMs)'s powerful generalization ability, a unified visual-language model called Popeye is proposed for multi-source ship detection from RS imagery. Specifically, to bridge the interpretation gap across the multi-source images for ship detection, a novel unified labeling paradigm is designed to integrate different visual modalities and the various ship detection ways, i.e., horizontal bounding box (HBB) and oriented bounding box (OBB). Subsequently, the hybrid experts encoder is designed to refine multi-scale visual features, thereby enhancing visual perception. Then, a visual-language alignment method is developed for Popeye to enhance interactive comprehension ability between visual and language content. Furthermore, an instruction adaption mechanism is proposed for transferring the pre-trained visual-language knowledge from the nature scene into the RS domain for multi-source ship detection. In addition, the segment anything model (SAM) is also seamlessly integrated into the proposed Popeye to achieve pixel-level ship segmentation without additional training costs. Finally, extensive experiments are conducted on the newly constructed ship instruction dataset named MMShip, and the results indicate that the proposed Popeye outperforms current specialist, open-vocabulary, and other visual-language models in zero-shot multi-source various ship detection tasks.