AI-created materials could cool cities and spacecraft

New materials developed using machine learning and artificial intelligence could, among other things, keep your house cooler and reduce energy bills.

Researchers from The University of Texas at Austin, Shanghai Jiao Tong University, National University of Singapore and Umea University in Sweden developed a new, machine learning-based approach for creating complex, three-dimensional thermal meta-emitters. The study has been published in the journal Nature.

Using this system, researchers developed more than 1,500 different materials that can selectively emit heat at various levels and in different manners, making them ideal for energy efficiency through more precise cooling and heating.

“Our machine learning framework represents a significant leap forward in the design of thermal meta-emitters,” said Yuebing Zheng, professor in the Cockrell School of Engineering’s Walker Department of Mechanical Engineering and co-leader of the study.

“By automating the process and expanding the design space, we can create materials with superior performance that were previously unimaginable.”

To test their platform, the researchers fabricated four materials for verification of the designs. They further applied one of the materials to a model house and compared it to commercial paints on the cooling effect.

After a four-hour midday exposure to direct sunlight, the meta-emitter-coated building roof came in between 5 and 20 degrees Celsius cooler on average than the ones with white and gray paints, respectively.

The researchers estimated that this level of cooling could save the equivalent of 15,800 kilowatts per year in an apartment building in a hot climate like Rio de Janeiro or Bangkok. A typical air conditioning unit uses about 1,500 kilowatts annually.

However, the applications go beyond improving energy efficiency in homes and offices. Using the machine learning framework, the researchers developed seven classes of meta-emitters, each with different strengths and applications.

Thermal meta-emitters could be deployed to help reduce the temperature in urban areas by reflecting sunlight and emitting heat in specific wavelengths. This would mitigate the urban heat island effect, where big cities have higher temperatures than surrounding areas due to a lack of vegetation and high levels of concrete.

In addition, thermal meta-emitters could be useful in space to manage the spacecraft’s temperature by reflecting solar radiation and emitting heat efficiently.

Beyond the applications in this research, thermal meta-emitters could become a part of many things we use daily. Integrating them into textiles and fabrics could improve cooling technology in clothing and outdoor equipment. Wrapping cars with them and embedding them into interior materials could reduce the heat that builds up when they sit in the sun.

The painstaking traditional process of designing these materials has held them back from mainstream adoption. Other automated options struggle to deal with the complexity in the three-dimensional hierarchical structure of the meta-emitters, limiting the outcomes to simple geometries such as thin-film stacks or planar patterns, with the performance coming in short on some measures.

“Traditionally, designing these materials has been slow and labor-intensive, relying on trial-and-error methods,” said Zheng. “This approach often leads to suboptimal designs and limits the ability to create materials with the necessary properties to be effective.”

The researchers will continue to refine this technology and apply it to more aspects of their field of nanophotonics—the interaction of light and matter at the tiniest scales.

“Machine learning may not be the solution to everything, but the unique spectral requirements of thermal management make it particularly suitable for designing high-performance thermal emitters,” said Kan Yao, a co-author of this work and a research fellow in Zheng’s group.