Programmable metasurfaces for future photonic artificial intelligence

2025-05-12

Nature Reviews Physics

AI Summary

Photonic neural networks (PNNs) suffer from poor scalability, static architectures, and limited co-design compatibility with digital electronics. Method: This work introduces, for the first time, a photonic AI hardware paradigm based on programmable metasurfaces, employing dynamically tunable metasurfaces as core photonic computing units to enable hardware-level reconfigurability, in-situ training, and adaptation to non-stationary tasks; it further integrates photonic-electronic co-design, 3D heterogeneous packaging, and CMOS-compatible nanophotonic fabrication. Contribution/Results: The approach overcomes fundamental physical limitations of conventional PNNs in energy efficiency, latency, and throughput, significantly enhancing functional flexibility and system-level scalability. It provides a practical, manufacturable pathway toward high-efficiency, low-latency, and commercially viable photonic AI accelerators, advancing photonic AI from proof-of-concept demonstrations to real-world deployment.

Technology Category

• Machine Learning: Hardware-aware ML
• Philosophy and Ethics of AI: Philosophical Foundations of AI
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Photonic neural networks (PNNs), which share the inherent benefits of photonic systems, such as high parallelism and low power consumption, could challenge traditional digital neural networks in terms of energy efficiency, latency, and throughput. However, producing scalable photonic artificial intelligence (AI) solutions remains challenging. To make photonic AI models viable, the scalability problem needs to be solved. Large optical AI models implemented on PNNs are only commercially feasible if the advantages of optical computation outweigh the cost of their input-output overhead. In this Perspective, we discuss how field-programmable metasurface technology may become a key hardware ingredient in achieving scalable photonic AI accelerators and how it can compete with current digital electronic technologies. Programmability or reconfigurability is a pivotal component for PNN hardware, enabling in situ training and accommodating non-stationary use cases that require fine-tuning or transfer learning. Co-integration with electronics, 3D stacking, and large-scale manufacturing of metasurfaces would significantly improve PNN scalability and functionalities. Programmable metasurfaces could address some of the current challenges that PNNs face and enable next-generation photonic AI technology.

Problem

• Scalability issues in photonic AI solutions
• High input-output overhead costs in optical AI
• Need for programmable metasurfaces in photonic AI

Innovation

• Programmable metasurfaces enable scalable photonic AI
• Co-integration with electronics improves PNN scalability
• 3D stacking enhances metasurface manufacturing scale