Machine Learning-Guided Development of Advanced Radiative Cooling Paints
|Interdisciplinary Areas:||Data and Engineering Applications, Micro-, Nano-, and Quantum Engineering, Power, Energy, and the Environment
Air conditioning accounted for 11% of the total commercial electricity usage and 16% of residential electricity usage, equating to 113.6 million metric tons of carbon dioxide emission in 2019. On the other hand, nationwide there are 14 million households without access to air conditioning, especially the underprivileged communities. Record-breaking heat waves in recent years have caused many losses of lives. Radiative cooling is a passive cooling method that can provide cooling by both reflecting the solar radiation and emitting infrared heat to deep space without energy input, hence greatly saves energy, reduces the carbon emission, and cools down our planet. Recently, Prof. Xiulin Ruan and co-workers have invented the whitest radiative cooling paints that can cool surfaces below the ambient temperature under direct sunlight, earning a Guinness World Record title of the “World’s Whitest Paint”. Built upon our previous success, the goal of this project is to design and experimentally demonstrate advanced radiative cooling paint technologies. We will perform multiscale simulations and design of ultrawhite, colored, and dynamic radiative cooling paints. Machine learning models will be developed to enable accelerated prediction and high-throughput materials screening. The predicted materials will be fabricated, characterized, and tested for validation and demonstration. The project is built upon Professors Xiulin Ruan and Guang Lin’s combined expertise on radiative cooling materials and machine learning.
The candidate is expected to have earned (or will earn in the near future) a PhD degree in Mechanical Engineering, Electrical Engineering, Materials Science and Engineering, Chemical Engineering, Physics, or other related fields. Relevant previous research experience and scientific publications are desired. The candidate should also have excellent writing and speaking skills.
Xiulin Ruan, firstname.lastname@example.org, Professor, School of Mechanical Engineering, https://engineering.purdue.edu/NANOENERGY/
Guang Lin, email@example.com, Professor, Department of Mathematics (primary appointment), Professor, Department of Statistics, Professor, School of Mechanical Engineering, https://www.math.purdue.edu/~lin491/
Andrea Felicelli, Ioanna Katsamba, Fernando Barrios, Yun Zhang, Ziqi Guo, Joseph Peoples, George Chiu, and Xiulin Ruan, “Thin layer lightweight and ultrawhite hexagonal boron nitride nanoporous paints for daytime radiative cooling,” Cell Reports Physical Science 3, 101058 (2022).
Xiangyu Li, Joseph Peoples, Peiyan Yao, and Xiulin Ruan, "Ultrawhite BaSO4 Paints and Films for Remarkable Daytime Subambient Radiative Cooling," ACS Appl. Mater. Interfaces, 13, 21733-21739 (2021).
Xiangyu Li, Joseph Peoples, Zhifeng Huang, Zixuan Zhao, Jun Qiu, and Xiulin Ruan, “Full Daytime Sub-Ambient Radiative Cooling in Commercial-like Paints with High Figure of Merit”, Cell Rep. Phys. Sci. 1, 100221 (2020).
Wei Deng, Siqi Liang, Botao Hao, Guang Lin, and Faming Liang, "Interacting Contour Stochastic Gradient Langevin Dynamics," International Conference on Learning Representations (ICLR), 2022.
Wei Deng, Xiao Zhang, Faming Liang, and Guang Lin, "An Adaptive Empirical Bayesian Method for Sparse Deep Learning," Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).