Plasmonic nanostructure design and characterization via Deep Learning

TLDR

Nanophotonics has revolutionized optics by enabling manipulation of light–matter interactions with subwavelength structures, yet design, fabrication, and characterization remain largely iterative and the inverse problem of obtaining geometry from a desired response is still challenging. We experimentally show that a deep neural network trained on thousands of synthetic experiments can recover sub‑wavelength dimensions from far‑field measurements and directly solve the inverse design problem, enabling rapid creation of metasurface optical elements and optimized nanostructures for sensing, imaging, and spectroscopy.

Abstract

Nanophotonics, the field that merges photonics and nanotechnology, has in recent years revolutionized the field of optics by enabling the manipulation of light-matter interactions with subwavelength structures. However, despite the many advances in this field, the design, fabrication and characterization has remained widely an iterative process in which the designer guesses a structure and solves the Maxwell's equations for it. In contrast, the inverse problem, i.e., obtaining a geometry for a desired electromagnetic response, remains a challenging and time-consuming task within the boundaries of very specific assumptions. Here, we experimentally demonstrate that a novel Deep Neural Network trained with thousands of synthetic experiments is not only able to retrieve subwavelength dimensions from solely far-field measurements but is also capable of directly addressing the inverse problem. Our approach allows the rapid design and characterization of metasurface-based optical elements as well as optimal nanostructures for targeted chemicals and biomolecules, which are critical for sensing, imaging and integrated spectroscopy applications.