Deep learning is having a tremendous impact in many areas of computer science and engineering. Motivated by this success, deep neural networks are attracting increasing attention in many other disciplines, including the physical sciences. In this work, we show that artificial neural networks can be successfully used in the theoretical modeling and analysis of a variety of radiative-heat-transfer phenomena and devices. By using a set of custom-designed numerical methods able to efficiently generate the required training data sets, we demonstrate this approach in the context of three very different problems, namely (i) near-field radiative heat transfer between multilayer systems that form hyperbolic metamaterials, (ii) passive radiate cooling in photonic crystal slab structures, and (iii) thermal emission of subwavelength objects. Despite their fundamental differences in nature, in all three cases we show that simple neural-network architectures trained with data sets of moderate size can be used as fast and accurate surrogates for doing numerical simulations, as well as engines for solving inverse design and optimization in the context of radiative heat transfer. Overall, our work shows that deep learning and artificial neural networks provide a valuable and versatile toolkit for advancing the field of thermal radiation.
The thermal properties of individual subwavelength objects, which defy Planck's law, are attracting significant fundamental and applied interest in different research areas. Special attention has been devoted to anisotropic structures made of polar dielectrics featuring thicknesses smaller than both the thermal wavelength and the skin depth. Recently, a novel experimental technique has enabled the measurement of the thermal emissivity of anisotropic SiO 2 nanoribbons (with thicknesses on the order of 100 nm), demonstrating that their emission properties can be largely tuned by adjusting their dimensions. However, despite the great interest aroused by these results, their rigorous theoretical analysis has remained elusive due to the computational challenges arising from the vast difference in the length scales involved in the problem. In this work, we present a systematic theoretical analysis of the thermal emission properties of these dielectric nanoribbons based on simulations within the framework of fluctuational electrodynamics carried out with the boundary element method implemented in the SCUFF-EM code. In agreement with the experiments, we show that the emissivity of these subwavelength structures can be largely tuned and enhanced over the thin-film limit. We elucidate that the peculiar emissivity of these nanoribbons is due to the very anisotropic thermal emission that originates from the phonon polaritons of this material and the properties of the waveguide modes sustained by these dielectric structures. Our work illustrates the rich thermal properties of subwavelength objects, as well as the need for rigorous theoretical methods that are able to unveil the complex thermal emission phenomena emerging in this class of systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.