Metamaterials are artificial materials engineered to have non-naturally occurring properties, and they’re best known as materials for invisibility cloaks often featured in sci-fi novels or games. By accurately designing artificial atoms smaller than the wavelength of light, and by controlling the polarization and spin of light, researchers obtain new optical properties that aren’t present in nature. Nevertheless, the current course requires a lot of trial and error to find the right materials. Such efforts are time-consuming and inefficient; artificial intelligence (AI) might present a solution to this problem.
The research group of Prof. Junsuk Rho, Sunae So and Jungho Mun of Department of Mechanical Engineering and Department of Chemical Engineering at POSTECH have developed a design with a higher degree of freedom that allows researchers to decide on supplies and design photonic buildings arbitrarily by using deep learning. Their findings are revealed in several journals together with Applied Materials and Interfaces, Nanophotonics, Microsystems & Nanoengineering, Optics Express, and Scientific Reports.
AI could be trained with a vast amount of data, and it can learn designs of various metamaterials and the correlation between photonic structures and their optical properties. Utilizing this training process, it can present a design method that makes a photonic construction with desired optical properties. As soon as trained, it could provide the desired design promptly and efficiently.
Prof. Rho and his group taught an AI system to design arbitrary photonic constructions and gave a new stage of freedom of the design by categorizing kinds of supplies and including them as a design issue, which made it attainable to design applicable supplies for relevant optical properties. Analysis of metamaterials obtained via this design technique revealed that they had an identical optical property predicted by the artificial neural network.
The resulting metamaterials will be utilized in the display, safety, and military technologies. On this regard, the introduction of AI to the design method is expected to make significant contributions to the technological development of metamaterials.