A team of scientists from the University of Texas, Shanghai Jiao Jong University, the National University of Singapore, and Umea University used artificial intelligence (AI) to develop complex 3D thermal meta-emissions that can be applied to homes or clothing, for example, to provide passive cooling.
The researchers used a machine learning approach to develop about 1.500 different materials that can emit heat in different ways at different levels. The scientists describe the method in the study “Supra-band and band-selective thermal meta-emitters via machine learning,” or “Ultrabroadband and band-selective thermal meta-emitters by machine learning", which has been published in Nature.
In principle, these materials are suitable for passively cooling objects coated with them by reflecting the sun's heat. This can lead to significant energy savings, as houses coated with post-emission material will no longer need to be cooled with energy-intensive air conditioning systems.
Using conventional methods, developing meta-emitters was a lengthy process based on trial and error. Even automated methods were quite slow, as they could not adequately render the complex three-dimensional structures of meta-emitters. They could only create simple shapes and thin layers or flat patterns. This often led to less than perfect designs that were not efficient enough.
On the other hand, the AI-based method that has now been developed has led to an expansion of the design space, so that “materials with excellent performance” that were previously “unthinkable” can be produced.
Energy savings through post-emissions
From the 1500 materials suggested by the AI, the scientists selected the four most promising ones for production and testing in practice and “dressed” a model house with them. Using the meta-emitters is similar to applying paint. The roof of the house was exposed to four hours of direct midday sun and was between 5 and 20 °C cooler than roofs without this coating.
Scientists estimate that a typical residential building in hot climates can save about 15.800 kW of electricity per year from the active cooling provided by an air conditioning system, which will greatly reduce costs.
The researchers have divided meta-emitters into seven categories so that they can be better matched to different application areas depending on their specific strengths and weaknesses.
Some of these post-emitters could be used, for example, to reduce temperatures in large cities during the summer heat, by reflecting sunlight from buildings and surfaces and emitting the heat at certain wavelengths. They could also be used to coat clothing to keep the wearer cooler. The same applies to cars or spacecraft, for example, which are exposed to the sun and need to be kept cool.
DOI: https://doi.org/10.1038/s41586-025-09102-y
Although the press releases will range from very select to rare, I said I'd pass...because sometimes the editors hide.
