Jianghan Bao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jianghan Bao has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Che Liu
Imperial College London, London, United Kingdom
5 shared publications - Tie Jun Cui
State Key Laboratory of Millimeter Waves Southeast University Nanjing China
4 shared publications Lei Zhang
State Key Laboratory of Millimeter Wave Southeast University Nanjing China
2 shared publicationsWen Ming Yu
State Key Laboratory of Millimeter Wave Southeast University Nanjing China
2 shared publicationsDaolin Fu
Qiantang Information Advanced Research Institute, Hangzhou, China
1 shared publication- Di Wang
National Laboratory of Solid State Microstructures
1 shared publication
Latest Publications
- Open Access
- 22 December 2025
- Published by Wiley in Advanced Electronic Materials
- Vol. 12 (3)
Physics‐Informed Deep Learning Method for Real‐Time Multi‐Harmonic Beamforming Based on Space‐Time‐Coding Metasurface
Space‐time‐coding metasurfaces (STCMs) enable simultaneous controls of electromagnetic wave across multiple harmonics, but designing high‐performance coding sequences in real time remains challenging. Here, we propose an unsupervised physics‐informed deep learning framework that can generate optimal spatiotemporal coding patterns for arbitrary single‐ and dual‐beam requirements at each harmonic frequency. The proposed method features three key innovations: physics‐informed mechanisms to enable unsupervised learning without requiring paired training data, a dedicated strategy for multi‐bit metasurface configurations, and the Conflict Averse Gradient descent (CAGrad) method to coordinate the parameter optimization across harmonics in multi‐task learning. Experiments on a 2‐bit STCM demonstrate robust beamforming capabilities over five harmonics, achieving an average radiation difference of 1.55 dB and real‐time design <0.1s. This is a 4‐order‐of‐magnitude improvement in computational efficiency compared with the particle swarm optimization methods. This work establishes a real‐time and physics‐aware design paradigm for intelligent metasurfaces in the next‐generation wireless systems.
- 22 December 2025
- Published by Wiley in Advanced Electronic Materials
- Vol. 12 (3)
Open AccessPhysics‐Informed Deep Learning Method for Real‐Time Multi‐Harmonic Beamforming Based on Space‐Time‐Coding Metasurface
Space‐time‐coding metasurfaces (STCMs) enable simultaneous controls of electromagnetic wave across multiple harmonics, but designing high‐performance coding sequences in real time remains challenging. Here, we propose an unsupervised physics‐informed deep learning framework that can generate optimal spatiotemporal coding patterns for arbitrary single‐ and dual‐beam requirements at each harmonic frequency. The proposed method features three key innovations: physics‐informed mechanisms to enable unsupervised learning without requiring paired training data, a dedicated strategy for multi‐bit metasurface configurations, and the Conflict Averse Gradient descent (CAGrad) method to coordinate the parameter optimization across harmonics in multi‐task learning. Experiments on a 2‐bit STCM demonstrate robust beamforming capabilities over five harmonics, achieving an average radiation difference of 1.55 dB and real‐time design <0.1s. This is a 4‐order‐of‐magnitude improvement in computational efficiency compared with the particle swarm optimization methods. This work establishes a real‐time and physics‐aware design paradigm for intelligent metasurfaces in the next‐generation wireless systems.
- Open Access
- 26 September 2025
- Published by Wiley in Advanced Functional Materials
- Vol. 36 (15)
A Smart Magnetically Actuated Flip‐Disc Programmable Metasurface with Ultralow Power Consumption for Real‐Time Channel Control
Programmable metasurfaces have garnered significant attention for their flexible dynamic manipulation of electromagnetic (EM) waves. However, electrically tunable variants require continuous power supply to control their operational states, resulting in substantial energy consumption and thermal management challenges; while mechanically tunable approaches rely on complex and costly structures and exhibit slow modulation speeds. To address these limitations, the study presents a magnetically actuated flip‐disc metasurface (FD‐MTS), an energy‐efficient and low‐cost platform for mechanical programmability. The bistable units of FD‐MTS achieve 0.1‐second inversion of reflection phase via magnetic actuation while maintaining non‐volatile encoding states without electrical current, enabling near‐zero power consumption. Experimental results confirm the exceptional EM‐manipulation capabilities of FD‐MTS by far‐field beamforming (single‐ and dual‐beam scenarios) and near‐field focusing. Based on FD‐MTS, a multi‐task reinforcement learning algorithm is developed for channel enhancement with real‐time channel state perception and fast adaptive optimization, which can reduce the iteration steps by 37.5% versus single‐task approaches. Measured results demonstrate 6 dB average enhancement in channel quality across diverse indoor locations. FD‐MTS provides a holistic solution for intelligent channel manipulation, representing an innovative convergence of kinetic art, dynamically reconfigurable hardware, and adaptive communication protocols.
- 26 September 2025
- Published by Wiley in Advanced Functional Materials
- Vol. 36 (15)
Open AccessA Smart Magnetically Actuated Flip‐Disc Programmable Metasurface with Ultralow Power Consumption for Real‐Time Channel Control
Programmable metasurfaces have garnered significant attention for their flexible dynamic manipulation of electromagnetic (EM) waves. However, electrically tunable variants require continuous power supply to control their operational states, resulting in substantial energy consumption and thermal management challenges; while mechanically tunable approaches rely on complex and costly structures and exhibit slow modulation speeds. To address these limitations, the study presents a magnetically actuated flip‐disc metasurface (FD‐MTS), an energy‐efficient and low‐cost platform for mechanical programmability. The bistable units of FD‐MTS achieve 0.1‐second inversion of reflection phase via magnetic actuation while maintaining non‐volatile encoding states without electrical current, enabling near‐zero power consumption. Experimental results confirm the exceptional EM‐manipulation capabilities of FD‐MTS by far‐field beamforming (single‐ and dual‐beam scenarios) and near‐field focusing. Based on FD‐MTS, a multi‐task reinforcement learning algorithm is developed for channel enhancement with real‐time channel state perception and fast adaptive optimization, which can reduce the iteration steps by 37.5% versus single‐task approaches. Measured results demonstrate 6 dB average enhancement in channel quality across diverse indoor locations. FD‐MTS provides a holistic solution for intelligent channel manipulation, representing an innovative convergence of kinetic art, dynamically reconfigurable hardware, and adaptive communication protocols.
- Open Access
Physics-driven unsupervised deep learning network for programmable metasurface-based beamforming
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (6) , 1675-1679
An Experimental Platform to Simulate Real-Time Correlated Sea Clutter Based on Space-Time-Coding Digital Metasurfaces
The traditional sea clutter simulation techniques encounter challenges in effectively balancing dynamic simulation, coupling effects, and construction cost management. To tackle these issues, we propose an experimental platform to simulate the sea clutter in real time using space-time-coding digital metasurfaces. Specifically, we use deep learning techniques to construct an encoding retrieval library with angle-insensitive characteristics. Combining the library with the desired clutter sequences generated by the zero memory nonlinearity approach, we can obtain the corresponding space-time-coding sequences for the simulation platform. To validate the proposed approach, we generate two correlated clutter signals following the Weibull and lognormal distributions under the illumination of monochromatic electromagnetic plane waves. Experimental results exhibit robust conformity with the theoretical values, demonstrating the dependability and stability of the proposed approach. These findings highlight the significant potential of our methods in various domains, including radar sensing and countermeasures.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (6) , 1675-1679
An Experimental Platform to Simulate Real-Time Correlated Sea Clutter Based on Space-Time-Coding Digital Metasurfaces
The traditional sea clutter simulation techniques encounter challenges in effectively balancing dynamic simulation, coupling effects, and construction cost management. To tackle these issues, we propose an experimental platform to simulate the sea clutter in real time using space-time-coding digital metasurfaces. Specifically, we use deep learning techniques to construct an encoding retrieval library with angle-insensitive characteristics. Combining the library with the desired clutter sequences generated by the zero memory nonlinearity approach, we can obtain the corresponding space-time-coding sequences for the simulation platform. To validate the proposed approach, we generate two correlated clutter signals following the Weibull and lognormal distributions under the illumination of monochromatic electromagnetic plane waves. Experimental results exhibit robust conformity with the theoretical values, demonstrating the dependability and stability of the proposed approach. These findings highlight the significant potential of our methods in various domains, including radar sensing and countermeasures.
- Open Access
- 10 January 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) , 3394-3408
Improved Few-Shot SAR Image Generation by Enhancing Diversity
Due to their remarkable capabilities of generation, deep-learning-based (DL) generative models have been widely applied in the field of synthetic aperture radar (SAR) image synthesis. This kind of data-driven DL methods usually requires abundant training samples to guarantee the performance. However, the number of SAR images for training is often insufficient because of expensive acquisitions. This typical few-shot image generation (FSIG) task still remains not fully investigated. In this article, we propose an optical-to-SAR (O2S) image translation model with a pairwise distance (PD) loss to enhance the diversity of generation. First, we replace the semantic maps used as the input of network in previous studies with more easily available optical images and apply the popular pix2pix model in image-to-image translation tasks as the foundation network. Second, inspired by the FSIG works in the traditional computer vision field, we propose a similarity preservation term in the loss function, which encourages the generated images to inherit the similarity relationship of the corresponding simulated SAR images. Third, the data augmentation experiments on the MSTAR dataset indicates the effectiveness of our model. With only five samples for each target category and six categories in total, the basic O2S network boosts the classification accuracy by 4.81% and 2.27% for data of depression angle of 15° and 17°, respectively. The PD loss is capable of bringing additional 2.23% and 1.78% improvement. The investigation on similarity curves also suggests that the generated images enhanced by the PD loss have closer similarity behaviors to the real SAR images.
- 10 January 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) , 3394-3408
Open AccessImproved Few-Shot SAR Image Generation by Enhancing Diversity
Due to their remarkable capabilities of generation, deep-learning-based (DL) generative models have been widely applied in the field of synthetic aperture radar (SAR) image synthesis. This kind of data-driven DL methods usually requires abundant training samples to guarantee the performance. However, the number of SAR images for training is often insufficient because of expensive acquisitions. This typical few-shot image generation (FSIG) task still remains not fully investigated. In this article, we propose an optical-to-SAR (O2S) image translation model with a pairwise distance (PD) loss to enhance the diversity of generation. First, we replace the semantic maps used as the input of network in previous studies with more easily available optical images and apply the popular pix2pix model in image-to-image translation tasks as the foundation network. Second, inspired by the FSIG works in the traditional computer vision field, we propose a similarity preservation term in the loss function, which encourages the generated images to inherit the similarity relationship of the corresponding simulated SAR images. Third, the data augmentation experiments on the MSTAR dataset indicates the effectiveness of our model. With only five samples for each target category and six categories in total, the basic O2S network boosts the classification accuracy by 4.81% and 2.27% for data of depression angle of 15° and 17°, respectively. The PD loss is capable of bringing additional 2.23% and 1.78% improvement. The investigation on similarity curves also suggests that the generated images enhanced by the PD loss have closer similarity behaviors to the real SAR images.
- 24 December 2020
- Published by American Physical Society (APS) in Physical Review B
- Vol. 102 (24) , 245142
Electronic and magnetic properties of the Jahn-Teller active fluoride from first-principles calculationsIn perovskite-type compounds, the interplay of the cooperative Jahn-Teller effect, electronic correlations, and orbital degrees of freedom leads to intriguing properties. is a newly synthesized Jahn-Teller active fluoroperovskite where the octahedrons are considerably distorted. Based on the first-principles calculation, we analyze its electronic structure and magnetic properties. Our numerical results show that the ions adopt the high-spin configuration and the material exhibits -type orbital ordering. We also estimate the magnetic exchange couplings and find that the in-plane and interplanar nearest-neighbor interactions are ferromagnetic and antiferromagnetic, respectively. The ground state of this material is -type antiferromagnetic, in agreement with the experiments. Our results give a complete explanation of its electronic structure and magnetic and orbital order, and help to further comprehend the behaviors of Jahn-Teller active perovskite-type fluoride.- 24 December 2020
- Published by American Physical Society (APS) in Physical Review B
- Vol. 102 (24) , 245142
Electronic and magnetic properties of the Jahn-Teller active fluoride from first-principles calculationsIn perovskite-type compounds, the interplay of the cooperative Jahn-Teller effect, electronic correlations, and orbital degrees of freedom leads to intriguing properties. is a newly synthesized Jahn-Teller active fluoroperovskite where the octahedrons are considerably distorted. Based on the first-principles calculation, we analyze its electronic structure and magnetic properties. Our numerical results show that the ions adopt the high-spin configuration and the material exhibits -type orbital ordering. We also estimate the magnetic exchange couplings and find that the in-plane and interplanar nearest-neighbor interactions are ferromagnetic and antiferromagnetic, respectively. The ground state of this material is -type antiferromagnetic, in agreement with the experiments. Our results give a complete explanation of its electronic structure and magnetic and orbital order, and help to further comprehend the behaviors of Jahn-Teller active perovskite-type fluoride.