A Generic Framework for Optical Inverse Design

Sakibul Islam Sazzad

Providing work samples of electromagnetic, RF, antenna, and radar system analysis that I performed for graduate school assignments.

The lib is used to study the ideal behavior of metasurface. For classic optics, there are good ray tracing python libraries that support classic optics, like RayTracing (https://github.com/DCC-Lab/RayTracing#raytracing) and rayoptics (https://ray-optics.readthedocs.io/en/latest/).

Inverse design of Plasmonic Metasurfaces with Bidirectional Adversarial AutoEncoder

MetaZero - A reinforcement learning program to optimise metasurface radar cross section (RCS) by self-playing. Inspired by AlphaZero.

The code repository for the 2023 ICCP Paper: Polarization Multi-Image Synthesis with Birefringent Metasurfaces

MATLAB functions to plot 2D or 3D radiation & scattering patterns, intended for custom visualization of the response of antennas & metasurfaces.

code for Large area optimization of meta-lens via data-free machine learning

MATLAB implementation of the Huygens-Fresnel principle for the calculation of the scattering farfield pattern produced from the illumination of a finite-aperture rectangular metasurface.

SmartGlass (SG) is a python implementation of a diffractive optical neural network. Currently, it supports training an all-optical classifier (e.g. classify hand-written digits MNIST dataset). Besides, the framework can also be used to design optics based on a task like focusing and beam steering. However, custom object functions should be defin…

Meta_SCMT is a software to inverse design large-area dielectric metasurface. The key factor that differentiates the Meta_SCMT from current Local Periodic Approximation(LPA) based methods is that Meta_SCMT can achieve fullwave-level accuracy with much less computational resource.

DFlat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.

This repository hosts a simple demonstration of a deep learning approach for the inverse design of patch antennas. The goal is to explore energy-efficient designs and to significantly reduce simulation cost compared to conventional methods.

(Tensorflow Version) D-Flat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.