Merging automatic differentiation and the adjoint method for photonic inverse design

Abstract: Optimizing shapes and topology of physical devices is crucial for both scientific and technological advancements, given its wide-ranging implications across numerous industries and research areas. Innovations in shape and topology optimization have been seen across a wide range of fields, notably structural mechanics, fluid mechanics, and photonics. Gradient-based inverse design techniques have been particularly successful for photonic and optical problems, resulting in integrated, miniaturized hardware that has set new standards in device performance. To calculate the gradients, there are typically two approaches: implementing specialized solvers using automatic differentiation or deriving analytical solutions for gradient calculation and adjoint sources by hand. In this work, we propose a middle ground and present a hybrid approach that leverages and enables the benefits of automatic differentiation and machine learning frameworks for handling gradient derivation while using existing, proven solvers for numerical solutions. Utilizing the adjoint method, we turn existing numerical solvers differentiable and seamlessly integrate them into an automatic differentiation framework. Further, this enables users to integrate the optimization environment with machine learning applications which could lead to better photonic design workflows. We illustrate the approach through two distinct examples: optimizing the Purcell factor of a magnetic dipole in the vicinity of an optical nanocavity and enhancing the light extraction efficiency of a {\textmu}LED.