Inverse design of directional hybrid nanoantennas using neural networks

Controlling the directionality of quantum emitter (QE) radiation is crucial for advancing nanophotonic devices, yet designing compact, single nanoantennas for this purpose remains challenging with traditional methods due to computational demands and optimization complexity. This paper introduces a neural-network-based inverse design approach to efficiently optimize single core–shell nanosphere antennas and their derivatives — notched core–shell structures and dimers — for highly directional QE emission. We systematically compare the radial basis function (RBF), support vector regression (SVR), and backpropagation neural network (BPNN) algorithms. Our results demonstrate BPNN’s superior performance in accurately mapping nanoantennas’ geometric and material parameters to their far-field radiation characteristics. Subsequent BPNN-driven optimization confirms that all three investigated structures (single core–shell, notched core–shell, and dimer) can achieve robust directional emission. This is accomplished by precisely exciting higher-order electric and magnetic multipoles engineered to possess equal amplitudes and opposite phases, thereby facilitating directional radiation from QEs and enabling more efficient nanophotonic device design.