Nanophotonic Inverse Design with SPINS: Software Architecture and Practical Considerations

TL;DR

SPINS is a flexible, reproducible computational framework for nanophotonic inverse design that leverages gradient-based optimization and computational graphs, addressing practical challenges like initial conditions and local minima.

Contribution

This paper introduces SPINS, a novel software architecture for nanophotonic inverse design that emphasizes flexibility, reproducibility, and practical heuristics for optimization.

Findings

SPINS enables efficient gradient-based nanophotonic design.

The framework addresses practical issues like initial conditions and local minima.

SPINS demonstrates reproducible and flexible design workflows.

Abstract

A computational nanophotonic design library for gradient-based optimization called SPINS is presented. Borrowing the concept of computational graphs, SPINS is a design framework that emphasizes flexibility and reproducible results. The mathematical and architectural details to achieve these goals are presented, and practical considerations and heuristics for using inverse design are discussed, including the choice of initial condition and the landscape of local minima.