Perfectly vertical grating couplers have various applications in optical I/O such as connector design, coupling to multicore optical fibers and multilayer silicon photonics. However, it is challenging to achieve perfectly vertical coupling without simultaneously increasing reflection. In this paper, we use the adjoint method as well as an adjoint-inspired methodology to design devices that can be fabricated using only a single-etch step in a c-Si 193 nm DUV immersion lithography process, while maintaining good coupling and low reflection. Wafer-level testing of devices fabricated by a pilot line foundry confirms that both design paradigms result in state-of-the-art experimental insertion loss (<2 dB) and bandwidths (∼20 nm) while having only moderate in-band reflection (<−10 dB). Our best design has a (median) 1.82 dB insertion loss and 21.3 nm 1 dB-bandwidth.
We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This technique uses a probabilistic generative neural network interfaced with an electromagnetic solver to assist in the design of photonic devices, such as grating couplers. We show that PHORCED obtains better performing grating coupler designs than local gradient-based inverse design via the adjoint method, while potentially providing faster convergence over competing state-of-the-art generative methods. As a further example of the benefits of this method, we implement transfer learning with PHORCED, demonstrating that a neural network trained to optimize 8° grating couplers can then be re-trained on grating couplers with alternate scattering angles while requiring >10× fewer simulations than control cases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.