Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity

TL;DR

This paper introduces a manifold learning-based method for knowledge discovery and inverse design in photonic nanostructures, enabling the evolution from complex to simpler designs while understanding device physics.

Contribution

The paper presents a novel manifold learning approach that simplifies the inverse design process of photonic nanostructures by exploring sub-manifolds in response space.

Findings

Enables evolution from complex to simple nanostructure designs

Provides insights into the physics of device operation

Outperforms traditional over-complex structure methods

Abstract

Here, we present a new approach based on manifold learning for knowledge discovery and inverse design with minimal complexity in photonic nanostructures. Our approach builds on studying sub-manifolds of responses of a class of nanostructures with different design complexities in the latent space to obtain valuable insight about the physics of device operation to guide a more intelligent design. In contrast to the current methods for inverse design of photonic nanostructures, which are limited to pre-selected and usually over-complex structures, we show that our method allows evolution from an initial design towards the simplest structure while solving the inverse problem.