Spending too much on air conditioning this summer? AI can help.
Researchers from Texas, China, Singapore, and Sweden used machine learning to create more than 1,500 new cooling materials, the University of Texas reported. The tiny, three-dimensional structures called meta-emitters reflect light to help keep surrounding areas cool. When the most promising microstructures were tested on the roof of a building under direct sunlight for four hours, the roof measured between five and 20 degrees Celsius cooler than the ones of surrounding buildings.
“Our machine learning framework represents a significant leap forward in the design of thermal meta-emitters,” said mechanical engineering professor Yuebing Zheng. “By automating the process and expanding the design space, we can create materials with superior performance that were previously unimaginable.”
Major cities globally are experiencing more frequent and intense heat waves, and climate change remains an ongoing threat. Integrating the meta-emitters into residential homes and crowded urban areas could reduce the level of heat the buildings absorb, decreasing the cost of cooling. Researchers also envision incorporating them into clothes and cars to help avoid overheating, as well as on spacecrafts to deflect damaging radiation.