event

Ph.D. Proposal Oral Exam - Zhaocheng Liu

Primary tabs

Title:  Artificial intelligence-enabled inverse design of photonic nanostructures

Committee: 

Dr. Cai, Advisor  

Dr. Naeemi, Chair

Dr. Peterson

Abstract:

The objective of the proposal is to leverage the state-of-the-art artificial intelligence techniques to address the challenge of the inverse design of nanophotonic devices and materials. The advent of nanophotincs in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale, and thereby enabling diverse applications in optical imaging, beam steering, light modulation, dispersion engineering, holography, and many more. However, the design of such structures, to date, has relied on the expertise of an optical scientist to guide a progression of electromagnetic simulations that iteratively solve Maxwell’s equations until locally optimized solution can be attained. In the proposal, we developed a  hybird framework leveraging deep generative models and traditional artificial intelligence algorithms to identify the photonic structures in arbitrary topology. The evaluation of our algorithms shows that over 95% average accuracy can be achieved in less than 5 seconds for all the unit patterns of the nanostructure tested. We intend to apply our algorithm to the inverse design of  complicated multi-functional metasurfaces in the future researches. Our work introduces a generic approach for the design of photonic and optical structures in response to the near-field and far-field requirements, with broad applications in large-scale photonic design requiring trial-and-error practices.

Status

  • Workflow Status:Published
  • Created By:Daniela Staiculescu
  • Created:05/15/2019
  • Modified By:Daniela Staiculescu
  • Modified:05/15/2019

Categories

Target Audience