This breakthrough in the creation of complex, three-dimensional thermal meta-emitters was created by researchers from the University of Texas, Austin, Shanghai Ziaoton University, National University of Singapore, and UMEA University in Sweden.
Using this system, researchers have developed over 1,500 different materials and are able to selectively release heat at different levels and different manners, making them suitable for energy efficiency through more accurate cooling and heating.
“Our machine learning framework represents an important leap in the design of thermal meta-emitters,” says Yuebbing Zheng, professor at Walker School of Mechanical Engineering at the Cockrell School of Engineering and co-leader of research published in nature. “By automating the process and expanding the design space, we can create materials with superior performance that we previously could not have imagined.”
To test their platform, researchers produced four materials for design verification. They also applied one of the materials to the model house and compared them to commercial paints with cooling effects. After 4 hours of daytime exposure to direct sunlight, the roofs of the meta-emitter-coated buildings went into an average of 5-20°C coolers than those with white and grey paint, respectively.
Researchers estimated that this level of cooling would save 15,800 kilowatt-hours a year in apartment buildings that are subject to hot climates. A typical air conditioning unit uses approximately 1,500 kilowatt-hours per year.
Actual applications for energy efficiency
According to the team, applications go beyond improving energy efficiency in homes and offices. Using a machine learning framework, researchers developed seven classes of meta emissions, each with different strengths and applications.
Thermal meta emitters can be deployed to help lower urban temperatures by reflecting sunlight and emitting heat at certain wavelengths, thereby alleviating the thermal island effect of cities where the city has a higher temperature than the surrounding area due to a lack of plants and concrete.
Additionally, applications include integrating them into textiles and fabrics, embedding them into the interior materials of the car, reducing the heat that accumulates when parked in the sun.
Overcoming traditional design challenges with AI
The team added that the traditional process of designing these materials is hindering them from mainstream adoption. Other automated options struggle to address the complexity of the three-dimensional hierarchical structure of meta-emitters, limiting the results to simple geometry such as thin film stacks and planar patterns.
“Traditionally, the design of these materials is slow, labor intensive and relies on trial and error methods,” Zheng said.
