Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling
Passive daytime radiative cooling (PDRC) has emerged as a promising, electricity-free cooling approach that reflects sunlight while radiating heat through the atmospheric transparent window. However, the design and optimization of PDRC materials remain challenging, requiring significant time and res...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/95 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589094609223680 |
|---|---|
| author | Changmin Shi Jiayu Zheng Ying Wang Chenjie Gan Liwen Zhang Brian W. Sheldon |
| author_facet | Changmin Shi Jiayu Zheng Ying Wang Chenjie Gan Liwen Zhang Brian W. Sheldon |
| author_sort | Changmin Shi |
| collection | DOAJ |
| description | Passive daytime radiative cooling (PDRC) has emerged as a promising, electricity-free cooling approach that reflects sunlight while radiating heat through the atmospheric transparent window. However, the design and optimization of PDRC materials remain challenging, requiring significant time and resources for experimental and numerical modeling efforts. In this work, we developed a machine learning (ML)-driven approach to predict scattering efficiency in the wavelength of 0.3–2.5 μm, with the aim of eventually optimizing the microstructural design of PDRC materials. By employing ML models such as linear regression, neural networks, and random forests, we aimed to predict and optimize the scattering efficiency across different pore sizes and mixed-pore-size configurations. As a result, the random forest model demonstrated superior prediction performance with minimal error, effectively capturing complex, non-linear interactions between material features. We also leveraged data transformation techniques such as one-hot encoding for generative predictions in mixed-pore-size configurations. The presented ML-driven platform serves as a valuable open resource for PDRC researchers, facilitating the rapid and cost-effective optimization of PDRC materials and accelerating the development of sustainable cooling technologies. |
| format | Article |
| id | doaj-art-0943e7bca7a04e3eb6c9d7368e9eaa9f |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-0943e7bca7a04e3eb6c9d7368e9eaa9f2025-01-24T13:22:00ZengMDPI AGAtmosphere2073-44332025-01-011619510.3390/atmos16010095Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative CoolingChangmin Shi0Jiayu Zheng1Ying Wang2Chenjie Gan3Liwen Zhang4Brian W. Sheldon5School of Engineering, Brown University, Providence, RI 02912, USAData Science Institute, Brown University, Providence, RI 02912, USADepartment of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USASchool of Engineering, Brown University, Providence, RI 02912, USADepartment of Mechanical, Aerospace & Biomedical Engineering, UT Space Institute, University of Tennessee, Knoxville, TN 37388, USASchool of Engineering, Brown University, Providence, RI 02912, USAPassive daytime radiative cooling (PDRC) has emerged as a promising, electricity-free cooling approach that reflects sunlight while radiating heat through the atmospheric transparent window. However, the design and optimization of PDRC materials remain challenging, requiring significant time and resources for experimental and numerical modeling efforts. In this work, we developed a machine learning (ML)-driven approach to predict scattering efficiency in the wavelength of 0.3–2.5 μm, with the aim of eventually optimizing the microstructural design of PDRC materials. By employing ML models such as linear regression, neural networks, and random forests, we aimed to predict and optimize the scattering efficiency across different pore sizes and mixed-pore-size configurations. As a result, the random forest model demonstrated superior prediction performance with minimal error, effectively capturing complex, non-linear interactions between material features. We also leveraged data transformation techniques such as one-hot encoding for generative predictions in mixed-pore-size configurations. The presented ML-driven platform serves as a valuable open resource for PDRC researchers, facilitating the rapid and cost-effective optimization of PDRC materials and accelerating the development of sustainable cooling technologies.https://www.mdpi.com/2073-4433/16/1/95machine learningpredictionradiative coolingmaterials structure optimizationscattering efficiency |
| spellingShingle | Changmin Shi Jiayu Zheng Ying Wang Chenjie Gan Liwen Zhang Brian W. Sheldon Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling Atmosphere machine learning prediction radiative cooling materials structure optimization scattering efficiency |
| title | Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling |
| title_full | Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling |
| title_fullStr | Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling |
| title_full_unstemmed | Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling |
| title_short | Machine Learning-Driven Scattering Efficiency Prediction in Passive Daytime Radiative Cooling |
| title_sort | machine learning driven scattering efficiency prediction in passive daytime radiative cooling |
| topic | machine learning prediction radiative cooling materials structure optimization scattering efficiency |
| url | https://www.mdpi.com/2073-4433/16/1/95 |
| work_keys_str_mv | AT changminshi machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling AT jiayuzheng machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling AT yingwang machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling AT chenjiegan machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling AT liwenzhang machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling AT brianwsheldon machinelearningdrivenscatteringefficiencypredictioninpassivedaytimeradiativecooling |