Machine Learning enables Ultra-Compact Integrated Photonics through Silicon-Nanopattern Digital Metamaterials
This work addresses the problem of creating ultra-compact and manufacturable integrated-photonics devices for the photonics industry, potentially enabling a 'Photonics Moore's Law'.
This paper demonstrates three ultra-compact integrated-photonics devices, including beamsplitters and waveguide bends, designed using a machine-learning algorithm coupled with FDTD modeling. The resulting designs have an area footprint smaller than λ0^2, making them among the smallest reported to date.
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 ${λ_0}^2$, 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."