In this work, we propose a novel framework for large-scale aperiodic nanophotonic inverse design utilizing an experimental machine-learning technique. With this technique, we create an extensive dataset of 10 million experimental structures for enhanced flat-optics design. This largest publicly available inverse design dataset, achieved through electron beam lithography, bypasses the extensive computational demand of first-principle simulations. Experimental acquisition ensures the dataset embodies real-world variances, leading to ML models with a ten-fold improved prediction accuracy in optical responses, drastically reducing validation RMSE from 0.012 to 0.0018. With this dataset, we developed a framework for large-scale aperiodic photonics design capable of designing tens of structures per second. We demonstrate the efficiency of the proposed technique by creating a large (3x3mm) aperiodic photonic structure composed of >10000 individual structures with pre-defined transmission/reflection responses.
In this work we make use of an inverse design methodology for the design of high efficiency deformation robust flat optics. Our approach leverages neural network predictors trained to quickly estimate the results of finite difference time domain (FDTD) simulations. By rapidly exploring the solution space, we find geometries that exhibit an optical response tolerant to dimensional errors. We validate our approach by fabricating and characterizing flat optics polarizers on top of polyamide tape. The devices exhibit a polarization efficiency of 85% over a 200 nm bandwidth and retain high performance when subjected to large deformations, in contrast to a control non-robust design.
Over the past twenty years flat-optics and metasurfaces emerged as a promising light manipulation technology. One of the challenges is obtaining scalable and highly efficient designs that can withstand the fabrication errors associated with nanoscale manufacturing. This problem becomes more severe in flexible structures. In this work, we present an inverse design platform that enables the fast design of flexible metasurfaces that maintain high performance under deformations. We validate this method by a series of experiments in which we realize broadband flexible light polarizers efficiency of 80% over 200 nm bandwidths.
This work presents an AI-driven framework to extract the biological tissue's refractive index and thickness maps from a single RGB image. This approach is based on a physical light-trapping surface and an unsupervised inverse search projector which projects given RGB pixel to the sample's refractive index and thickness at the corresponding coordinate.
We introduce a universal design platform for the development of highly-efficient wavefront engineering structures. To validate this methodology, we fabricated many different optical devices with an experimental efficiency exceeding 99%.
Flat optics allow the production of integrated, lightweight, portable and wearable optical devices. In this work we propose a flat optics design platform that employs concepts from evolutionary algorithms to deep learning with convolutional neural networks, and demonstrate a general design framework that can furnish an arbitrarily designed system response in as little as 50nm of silicon. The proposed framework is fundamental for our most recent experimental paper, in which we present a plethora of high efficiency devices, including, but not limited to: polarizing beam splitters, dichroic mirrors and metasurfaces for a novel 2-pixel display technology.
In this work, we introduce a technique capable of recovering both the refractive index and thickness maps of a cell using a single measurement in the form of a color photograph of the sample. Our method exploits the appearance of thin-film interference colors on a cell when placed on top of a suitable surface. An inverse search algorithm is used to map these colors to the refractive index and thickness values of each pixel in the image. Experimentally, we show the technique can achieve a 10-2 RIU sensitivity, sufficient to differentiate between cellular organelles.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.