If you’ve ever complained about rising electricity bills, artificial intelligence is already coming to your rescue.
Researchers from the University of Texas at Austin, the University of Shanghai Jiao Tong, the National University of Singapore, and Umea University in Sweden have designed a new machine learning-based approach for creating complex, three-dimensional thermal meta-emitters.
The team has developed more than 1,500 different materials capable of emitting heat at various levels in different manners. These characteristics make them ideal for attaining energy efficiency through precise cooling and heating.
Yuebing Zheng, a co-leader on this study, shed light on how these materials can be created.
The test process
“By automating the process and expanding the design space, we can create materials with superior performance that were previously unimaginable,” he stated.
The researchers made four different materials to test their designs. They used one of these materials to coat a model house and compared it with regular white and grey paints. After four hours of direct midday sunlight, the roof with the special coating was 5 to 20 degrees Celsius (nine degrees to 36 degrees Fahrenheit) cooler than the roofs with regular paint.
According to the researchers, this level of cooling can save around 15,800 kilowatts per year in an apartment building in a hot climate. A typical air conditioner uses about 1,500 kilowatts annually.
More than energy savers
The researchers haven’t designed these applications to be mere energy savers. Using machine learning, they’ve developed seven classes of meta-emitters, each with different strengths and applications.
These thermal emitters can be used to mitigate temperature in metro cities by reflecting sunlight and emitting heat in specific wavelengths. This could help reduce the urban heat island effect, where large cities become hotter than nearby areas because of less vegetation and lots of concrete.
Outside Earth, thermal meta-emitters might also help control spacecraft temperatures by reflecting sunlight and releasing heat effectively.
In daily use
Meta emitters can also be used in things of daily use. They can be used in fabrics and textiles to improve the cooling technology for clothing and outdoor equipment. They can also be used to wrap cars and embed them into interior materials that could reduce the heat that builds up when they sit in the sun.
The slow and careful, traditional way of designing these materials has stopped them from becoming widely used. Other automated methods have trouble handling the complex 3D structures of the meta-emitters, so they can only create simple shapes like thin layers or flat patterns, which don’t perform as well comparatively.
“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.”
A peek at the future
The researchers will work on refining this technology and applying it to more aspects 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.
This study was published in the journal Nature.