Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
This work addresses the problem of designing simpler and more efficient photonic nanostructures for researchers and engineers in photonics, offering an incremental improvement over existing inverse design methods.
This paper introduces a manifold learning approach for knowledge discovery and inverse design of photonic nanostructures. The method enables the evolution of an initial design towards the simplest possible structure while solving the inverse problem, addressing the limitation of current methods that rely on pre-selected and often overly complex structures.
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.