Issue 27, 2025

Inverse design of multilayer film compatible with infrared stealth and radiative heat dissipation through deep reinforcement learning

Abstract

With the rapid development of infrared detection technology, the demand for high-performance infrared stealth materials is becoming increasingly urgent. Conventional materials achieve infrared stealth by reducing emissivity across the entire infrared spectrum but significantly weaken radiative heat dissipation performance. In this paper, to meet the requirements of both infrared stealth and radiative heat dissipation, we combine deep reinforcement learning with the transfer matrix method to optimize the material and thickness of each layer, enabling the inverse design of a multilayer film structure (cGST 278 nm/Ag 16 nm/cGST 508 nm/Ag 160 nm) that effectively integrates both functions. It exhibits average emissivity as low as 16.1% and 17.7% in the 3–5 μm and 8–14 μm atmospheric window bands, respectively, and an average emissivity of 78.2% in the non-atmospheric window band (5–8 μm). This structure's spectrally selective emission characteristics were further validated and analyzed through its radiation intensity, infrared-detected temperature, electromagnetic field distribution, and power loss density. Moreover, further verification demonstrates that its performance remains angle-insensitive over a wide range of incident angles (0°–70°). The infrared stealth-compatible radiative heat dissipation multilayer film structure proposed in this study is relatively simple and holds significant potential for practical applications.

Graphical abstract: Inverse design of multilayer film compatible with infrared stealth and radiative heat dissipation through deep reinforcement learning

Supplementary files

Article information

Article type
Paper
Submitted
13 Apr 2025
Accepted
02 Jun 2025
First published
06 Jun 2025

J. Mater. Chem. C, 2025,13, 13827-13835

Inverse design of multilayer film compatible with infrared stealth and radiative heat dissipation through deep reinforcement learning

T. Xiao, H. Ji, Z. Zeng, P. Long and S. Jin, J. Mater. Chem. C, 2025, 13, 13827 DOI: 10.1039/D5TC01520K

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