AI-enabled design of extraordinary daytime radiative cooling materials
Source abstract
Abstract
Here we developed an artificial intelligence (AI)–based deep generative model, combined with a one-dimensional convolutional neural network (1D-CNN), for the inverse design of extraordinary passive daytime radiative cooling (PDRC) materials in a probabilistic manner. This AI-enabled strategy delivered a comprehensive solution for the one-to-many mapping problem of inverse design by predicting the optical properties—specifically, the refractive index (n) and extinction coefficient (k)—of hypothetical new materials. We then used the Kramers–Kronig relations and Lorentz–Drude model to validate the predicted results, and discovered a new record-breaking PDRC material that provided a decrease of approximately 79 K relative to ambient temperature and of approximately 12 K relative to that provided by the conventional ideal selective emitter under conditions of perfect insulation and a perfect electric conductor substrate. This AI-extrapolated approach toward extraordinary PDRC materials provides new guidelines for designing PDRC materials and connects the gap between ideal selective emitters and real materials.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Thermal Radiation and Cooling Technologies · Urban Heat Island Mitigation · Building Energy and Comfort Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (23)
Show source-provided references
1. Passive radiative cooling below ambient air temperature under direct sunlight10.1038/nature13883 ↗
2. Passive radiative cooling design with broadband optical thin-film filters10.1016/j.jqsrt.2017.03.046 ↗
3. Colored, daytime radiative coolers with thin-film resonators for aesthetic purposes
4. Application of constrained optimization to the design of quasi-rugate optical coatings10.1364/AO.47.005103 ↗
5. The design of ultra-broadband selective near-perfect absorber based on photonic structures to achieve near-ideal daytime radiative cooling10.1016/j.matdes.2017.10.077 ↗
6. Photonic structure textile design for localized thermal cooling based on a fiber blending scheme10.1021/acsphotonics.6b00644 ↗
7. Daytime radiative cooling using near-black infrared emitters10.1021/acsphotonics.6b00991 ↗
8. Hierarchically porous polymer coatings for highly efficient passive daytime radiative cooling10.1126/science.aat9513 ↗
9. Inverse molecular design using machine learning: generative models for matter engineering10.1126/science.aat2663 ↗
10. Advances and challenges in deep generative models for de novo molecule generation10.1002/wcms.1395 ↗
11. Deep learning for molecular generation10.4155/fmc-2018-0358 ↗
12. Deep learning for molecular design—a review of the state of the art10.1039/C9ME00039A ↗
13. Inverse design of solid-state materials via a continuous representation10.1016/j.matt.2019.08.017 ↗
14. Data-driven approach to encoding and decoding 3-D crystal structures
15. Radiative cooling to deep sub-freezing temperatures through a 24-h day–night cycle10.1038/ncomms13729 ↗
16. Optimizing the Drude-Lorentz model for material permittivity: examples for semiconductors
17. Lucarini · 2005 · vol. 110
18. Introduction to the maxwell garnett approximation: tutorial10.1364/JOSAA.33.001244 ↗
19. Macleod · 2010
20. Passive radiative cooling below ambient air temperature under direct sunlight10.1038/nature13883 ↗
21. The HITRAN 2008 molecular spectroscopic database10.1016/j.jqsrt.2009.02.013 ↗
22. A correlation coefficient for modal vector analysis
23. A novel selective emissivity spectrum for radiative sky cooling10.1016/j.solmat.2021.111380 ↗