This presentation, “Deep Learning for the Inverse Design of Metasurface-Based Energy Materials,” was created by Yang Deng (Ph.D. student in electrical and computer engineering, Duke University) as part of the Duke University Energy Data Analytics Ph.D. Student Fellows Program. Learn more about the program: bit.ly/edafellows

Abstract: “All-dielectric metasurfaces emerged as prominent platforms to manipulate energy at surfaces and have proven their capabilities as highly efficient energy materials. With thermal and waste energy eliminated by tailored emission, all-dielectric metasurfaces provide a revolutionary solution for efficient energy harvesting. However, all-dielectric metasurfaces require extensive numerical simulations to understand their physical properties. Deep learning approaches have been studied on the accelerated inverse design of metasurfaces, yet more complex geometries remain mostly unexplored. I am interested in identifying deep learning solutions that can accurately identify complex all-dielectric metasurface geometry that yields targeted frequency-dependent scatterings. The project’s success should accelerate the inverse design of all-dielectric metasurfaces, offering unprecedented high-performance thermal materials in energy harvesting applications. The deep learning methods can particularly identify optimal ADM thermal emitters ready to deploy in the realization of high-efficiency thermophotovoltaic cells.”

Support for this work was provided by the Alfred P. Sloan Foundation Grant G-2020-13922 through the Duke University Energy Data Analytics Ph.D. Student Fellows Program.

Note: Conclusions reached or positions taken by researchers or other grantees represent the views of the grantees themselves and not those of the Alfred P. Sloan Foundation or its trustees, officers, or staff.

Learn about the Energy Data Analytics Lab at Duke: energy.duke.edu/research/energy-data
Get email updates on energy news and events at Duke: bit.ly/energyduke