Skip to content
DraconiticResearch
Search Sources API
190,839 studies31 sourcesUpdated 32 min ago
Peer-reviewedCC BYLight Science & Applications

Machine learning-assisted highly efficient thermal management in function-oriented thermochromic smart windows

  • Zhengui Zhou1
  • Changyuan Chen1
  • Bin Li1
  • Rong Liu1
  • Shouqin Tian2
  • Bin Hu3,4
  • Yi Long5
5 affiliations
  1. 1Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
  2. 2State Key Laboratory of Advanced Glass Materials, Wuhan University of Technology, Wuhan, China. [email protected]
  3. 3Shenzhen Huazhong University of Science and Technology Research Institute, Shenzhen, China. [email protected]
  4. 4Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, China. [email protected]
  5. 5Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China. [email protected]
Open at sourcePDFDOICite

Abstract

Windows contribute significantly to energy inefficiency in electric vehicles and buildings, and the development of smart windows with customized optical responses catering to various purposes presents a significant challenge. Vanadium dioxide (VO 2 ) Fabry-Perot resonator has emerged as an effective device to modulate heat transfer passively to enhance energy-saving performance, with its efficacy highly limited by the complex interrelationship between the structure and multispectral selectivity. This study introduces a physics-guided neural network to design energy-efficient thermochromic smart windows for directional privacy protection (DPP). Guided by machine learning predictions, the VO 2 nanoparticle size- and spacer-controlled DPP smart window exhibits a targeted luminous transmission (<0.15) with both high modulation of near-infrared transmittance of 0.12 and longwave infrared radiation emissivity of 0.56, surpassing both commercial and the best-reported windows. When applied in electric vehicles and building envelopes, the DPP smart window demonstrated superior thermal management compared to commercial counterparts. This work provides a framework for the inverse design of function-oriented smart windows, advancing energy-efficient solutions for real-world applications.

Related

  1. Machine Learning‐Assisted Optimization of Iodide Electrolytes for Efficient Indoor Dye‐Sensitized Solar Cells with Engineered Photoanodes
    Valid Mwalukuku, Antonio Blanco, Cyril Aumaître +4
    Small SciencePeer-reviewedCC BYGeneral chemistryHAL
  2. Additive Manufacturing of Thermochromic Chitosan Hydrogels for Battery-Free Colorimetric Thermal Indication
    Jaewon Lim, Na Kyoung Kim, Jong Woo Hah +4
    PolymersPeer-reviewedCC BYFull textMaterials & polymersEurope PMC
  3. A CuO/ZnFe₂O₄ heterostructure as an efficient catalyst for NaBH₄-assisted reduction of chloramphenicol.
    Le Thi Hoa, Nguyen Thi Thu Huong, Le Quoc Viet +4
    Beilstein journal of nanotechnologyPeer-reviewedCC BYFull textOrganic chemistryEurope PMC
  4. Microwave-assisted activated carbon from waste compressed wood for efficient PFOS removal under neutral pH conditions
    Mona Ardebilipour, Mahdi Maleki Lonbar, Ghufran Redzwan +1
    Environmental Technology & InnovationPeer-reviewedCC BY-NC-ND8 citedEnvironmental chemistryOpenAlex
  5. Wide-Color-Span: Blue-Shifted Thermochromic D-A-D Fluorophores for Ratiometric Temperature Sensing
    Zheng-Kun Qin, Chi Feng, Meiqi Tang +4
    Molecules (Basel, Switzerland)Peer-reviewedCC BYFull textMaterials & polymersEurope PMCCrossref

Cite

BibTeXRIS
BibTeX
@article{zhou2026machine,
  title = {{Machine learning-assisted highly efficient thermal management in function-oriented thermochromic smart windows}},
  author = {Zhengui Zhou and Changyuan Chen and Bin Li and Rong Liu and Shouqin Tian and Bin Hu and Yi Long},
  journal = {Light Science \& Applications},
  year = {2026},
  month = jun,
  doi = {10.1038/s41377-026-02369-4},
  url = {https://doi.org/10.1038/s41377-026-02369-4},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Machine learning-assisted highly efficient thermal management in function-oriented thermochromic smart windows
AU  - Zhengui Zhou
AU  - Changyuan Chen
AU  - Bin Li
AU  - Rong Liu
AU  - Shouqin Tian
AU  - Bin Hu
AU  - Yi Long
PY  - 2026
DA  - 2026/06/22
JO  - Light Science & Applications
DO  - 10.1038/s41377-026-02369-4
UR  - https://doi.org/10.1038/s41377-026-02369-4
AB  - Windows contribute significantly to energy inefficiency in electric vehicles and buildings, and the development of smart windows with customized optical responses catering to various purposes presents a significant challenge. Vanadium dioxide (VO 2 ) Fabry-Perot resonator has emerged as an effective device to modulate heat transfer passively to enhance energy-saving performance, with its efficacy highly limited by the complex interrelationship between the structure and multispectral selectivity. This study introduces a physics-guided neural network to design energy-efficient thermochromic smart windows for directional privacy protection (DPP). Guided by machine learning predictions, the VO 2 nanoparticle size- and spacer-controlled DPP smart window exhibits a targeted luminous transmission (<0.15) with both high modulation of near-infrared transmittance of 0.12 and longwave infrared radiation emissivity of 0.56, surpassing both commercial and the best-reported windows. When applied in electric vehicles and building envelopes, the DPP smart window demonstrated superior thermal management compared to commercial counterparts. This work provides a framework for the inverse design of function-oriented smart windows, advancing energy-efficient solutions for real-world applications.
SN  - 2047-7538
SN  - 2095-5545
ER  -