Physics‐Informed Deep Learning Method for Real‐Time Multi‐Harmonic Beamforming Based on Space‐Time‐Coding Metasurface
Open Access
- 22 December 2025
- journal article
- Published by Wiley in Advanced Electronic Materials
- Vol. 12 (3)
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62288101)
- National Natural Science Foundation of China (62301146)
- Natural Science Foundation of Jiangsu Province (BK20230816)
- China Postdoctoral Science Foundation (2023M730554)
- China Postdoctoral Science Foundation (BX20220065)
This publication has 33 references indexed in Scilit:
- Physics-driven unsupervised deep learning network for programmable metasurface-based beamformingiScience, 2024
- Fully Breaking Entanglement of Multiple Harmonics for Space‐ and Frequency‐Division Multiplexing Wireless Applications via Space‐Time‐Coding MetasurfaceAdvanced Science, 2024
- Machine‐Learning‐Enabled Multi‐Frequency Synthesis of Space‐Time‐Coding Digital MetasurfacesAdvanced Functional Materials, 2024
- Electromagnetic Metamaterials and Metasurfaces: From Theory To Applications2024
- Conditional Generative Adversarial Networks for Inverse Design of Multifunctional MetasurfacesAdvanced Photonics Research, 2022
- Joint Multi‐Frequency Beam Shaping and Steering via Space–Time‐Coding Digital MetasurfacesAdvanced Functional Materials, 2020
- Deep Learning: A Rapid and Efficient Route to Automatic Metasurface DesignAdvanced Science, 2019
- Deep learningNature, 2015
- Coding metamaterials, digital metamaterials and programmable metamaterialsLight: Science & Applications, 2014
- From metamaterials to metadevicesNature Materials, 2012