Fan C.-YGUO-DUNG JOHN SU2022-04-252022-04-25202120794991https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111451556&doi=10.3390%2fnano11081966&partnerID=40&md5=ab3d9d67b6e4b6a82da08a8b0658f18ahttps://scholars.lib.ntu.edu.tw/handle/123456789/607079Metasurface has demonstrated potential and novel optical properties in previous research. The prevailing method of designing a macroscale metasurface is based on the local periodic approximation. Such a method relies on the pre-calculated data library, including phase delay and transmittance of the nanostructure, which is rigorously calculated by the electromagnetic simulation. However, it is usually time-consuming to design a complex metasurface such as broadband achromatic metalens due the required huge data library. This paper combined different numbers of nan-ofins and used deep neural networks to train our data library, and the well-trained model predicted approximately ten times more data points, which show a higher transmission for designing a broad-band achromatic metalens. The results showed that the focusing efficiency of designed metalens using the augmented library is up to 45%, which is higher than that using the original library over the visible spectrum. We demonstrated that the proposed method is time-effective and accurate enough to design complex electromagnetic problems. ? 2021 by the author. Licensee MDPI, Basel, Switzerland.Broadband achromatic metalensDeep neural networksLocal periodic approximationMetasurfacejournal article10.3390/nano110819662-s2.0-85111451556