Machine learning based compact photonic structure design for strong light confinement

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 Sislab overlying on the top of silica substrate. The learning algorithm is implemented using bitwise square Sicells and the whole optimized device has a footprint of 2μm × 1μm, which is the smallest size ever achieved numerically. To find the effect of Sislab thickness on the subwavelength 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 0.158λ and −1.87dB with slab thickness of 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. Studies on subwavelength light focusing phenomenon are increasing over time due to immense needs of light energy enhancement via confining it to a narrow region [1, 2, 3]. Light focusing into a tight spot smaller than the wavelength of light may find place in various optical applications including nanolithography, optical microscopy, optical measurements and optical data storage. Especially, highresolution imaging and strong beam coupling can be achieved by using the light focusing effect beyond the diffraction limit [4, 5]. Various subwavelength focus-