Design and validation of world-class multilayered thermal emitter using machine learning

Scientists designed a multilayered metamaterial that realizes ultra-narrowband wavelength-selective thermal emission by combining the machine learning (Bayesian optimization) and thermal emission properties calculations (electromagnetic calculation). The joint team then experimentally fabricated the designed metamaterial and verified the performance. These results may facilitate the development of highly efficient energy devices.

from Engineering and Construction News – ScienceDaily https://www.sciencedaily.com/releases/2019/03/190315100056.htm

via Tumblr http://ndbasilica.tumblr.com/post/183474371139