Machine learning based compact photonic structure design for strong light confinement

TL;DR

This paper introduces a machine learning approach to design ultra-compact photonic structures with strong light confinement, achieving the smallest numerically optimized device footprint and demonstrating improved coupling efficiency for optical applications.

Contribution

The study presents a novel machine learning-based method for designing extremely small photonic devices with enhanced light confinement and coupling efficiency, surpassing traditional design sizes.

Findings

Achieved a device footprint of 2 μm x 1 μm, the smallest numerically optimized size.

Optimized slab thickness of 280 nm yields a focus FWHM of 0.158 λ and coupling efficiency of -1.87 dB.

Designed devices are easy to fabricate and operate at telecommunication wavelengths.

Abstract

We present a novel approach based on machine learning for designing photonic structures. In particular, we focus on strong light confinement that allows the design of an efficient free-space-to-waveguide coupler which is made of Si- slab overlying on the top of silica substrate. The learning algorithm is implemented using bitwise square Si- cells and the whole optimized device has a footprint of $\boldsymbol{2 \, \mu m \times 1\, \mu m}$, which is the smallest size ever achieved numerically. To find the effect of Si- slab thickness on the sub-wavelength focusing and strong coupling characteristics of optimized photonic structure, we carried out three-dimensional time-domain numerical calculations. Corresponding optimum values of full width at half maximum and coupling efficiency were calculated as $\boldsymbol{0.158 \lambda}$ and $\boldsymbol{-1.87\,dB}$ with slab thickness of $\boldsymbol{280nm}$. Compared to the conventional counterparts, the optimized lens and coupler designs are easy-to-fabricate via optical lithography techniques, quite compact, and can operate at telecommunication wavelengths. The outcomes of the presented study show that machine learning can be beneficial for efficient photonic designs in various potential applications such as polarization-division, beam manipulation and optical interconnects.