Numerical Optimization of a Nanophotonic Cavity by Machine Learning for Near-Unity Photon Indistinguishability at Room Temperature

Room-temperature (RT), on-chip deterministic generation of indistinguishable photons coupled to photonic integrated circuits is key for quantum photonic applications. Nevertheless, high indistinguishability ( I ) at RT is difficult to obtain due to the intrinsic dephasing of most deterministic single-photon sources (SPS). Here, we present a numerical demonstration of the design and optimization of a hybrid slot-Bragg nanophotonic cavity that achieves a theoretical near-unity I and a high coupling efficiency (β) at RT for a variety of single-photon emitters. Our numerical simulations predict modal volumes in the order of 10 -3 (λ/2n) 3 , allowing for strong coupling of quantum photonic emitters that can be heterogeneously integrated. We show that high I and β should be possible by fine-tuning the quality factor ( Q ) depending on the intrinsic properties of the single-photon emitter. Furthermore, we perform a machine learning optimization based on the combination of a deep neural network and a genetic algorithm (GA) to further decrease the modal volume by almost 3 times while relaxing the tight dimensions of the slot width required for strong coupling. The optimized device has a slot width of 20 nm. The design requires fabrication resolution in the limit of the current state-of-the-art technology. Also, the condition for high I and β requires a positioning accuracy of the quantum emitter at the nanometer level. Although the proposal is not a scalable technology, it can be suitable for experimental demonstration of single-photon operation.