Machine Learning enables Ultra-Compact Integrated Photonics through Silicon-Nanopattern Digital Metamaterials

TL;DR

This paper presents a machine-learning-based design approach for creating ultra-compact, manufacturable integrated photonics devices using digital metamaterials, achieving some of the smallest footprints reported.

Contribution

It introduces a novel method combining machine learning and digital metamaterials for designing ultra-compact photonics devices with practical manufacturability.

Findings

Devices have footprints smaller than ${BB}^2$

Demonstrated designs include beamsplitters and waveguide bends

Approach is general and scalable

Abstract

In this work, we demonstrate three ultra-compact integrated-photonics devices, which are designed via a machine-learning algorithm coupled with finite-difference time-domain (FDTD) modeling. Through digitizing the design domain into "binary pixels" these digital metamaterials are readily manufacturable as well. By showing a variety of devices (beamsplitters and waveguide bends), we showcase the generality of our approach. With an area footprint smaller than ${\lambda_0}^2$, our designs are amongst the smallest reported to-date. Our method combines machine learning with digital metamaterials to enable ultra-compact, manufacturable devices, which could power a new "Photonics Moore's Law."