Broadband solar absorber and high-temperature thermal emitter based on deep-learning optimization and design

Abstract

Nowadays, the efficient use of the vast energy available in the solar spectrum is expected to solve the current energy crisis to a certain extent. Solar absorbers with metamaterial structures have become a research hotspot in this field owing to their good performance and have achieved many excellent results. However, most of the materials used in current research are precious metals, whose high cost and low melting points greatly limit their application prospects. In addition, due to the complex structure and large number of design parameters, traditional exploration methods require a lot of time and computational resources. This paper uses a deep learning algorithm to explore and optimize a multilayer broadband metamaterial solar absorber, consisting of Cr as the substrate with alternately stacked Al2O3 and Ti. The deep learning algorithm used performs well on various datasets, with a forward prediction relative error of only 0.14% and a reverse optimization error of only 0.5%. The designed absorber has an absorptivity greater than 90% across a bandwidth of 2078 nm. The average absorptivity is greater than 90% in the 280–2780 nm range and reaches 94.06% in the 442–2520 nm range. The solar spectrum absorption efficiency under AM 1.5 solar illumination reaches 97%, and it is very insensitive to both incident angle and polarization state. The high-temperature thermal radiation absorption energy at 1600 K closely matches the blackbody radiation energy, demonstrating its excellent thermal radiation absorption capacity at high temperatures. Its thermal radiation capacity is also excellent, with a thermal radiation efficiency greater than 80% over a temperature range of 200 K to 1600 K and a high thermal radiation efficiency of 91.31% at 1600 K. This study applies deep learning methods to micro- and nano-optical technology and designs a solar absorber with excellent photovoltaic properties and photothermal conversion performance. The excellent thermal radiation absorption capacity at high temperatures, combined with a thermal radiation efficiency that remains high and even improves as the temperature increases from room temperature to high levels, makes this optimally structured absorber significant in the fields of thermal energy conversion and thermal management. It not only provides new ideas and methods for solar energy utilization technology, but also contributes to the research and manufacturing of metamaterials and metamaterial-based devices.

Graphical abstract: Broadband solar absorber and high-temperature thermal emitter based on deep-learning optimization and design

Transparent peer review

To support increased transparency, we offer authors the option to publish the peer review history alongside their article.

View this article’s peer review history

Article information

Article type
Paper
Submitted
03 Nov 2025
Accepted
20 Jan 2026
First published
21 Jan 2026

J. Mater. Chem. A, 2026, Advance Article

Broadband solar absorber and high-temperature thermal emitter based on deep-learning optimization and design

Q. He, Z. Liu, Z. Yi and F. Zhou, J. Mater. Chem. A, 2026, Advance Article , DOI: 10.1039/D5TA08912C

To request permission to reproduce material from this article, please go to the Copyright Clearance Center request page.

If you are an author contributing to an RSC publication, you do not need to request permission provided correct acknowledgement is given.

If you are the author of this article, you do not need to request permission to reproduce figures and diagrams provided correct acknowledgement is given. If you want to reproduce the whole article in a third-party publication (excluding your thesis/dissertation for which permission is not required) please go to the Copyright Clearance Center request page.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements