論文 Generative-AI-assisted knowledge-based augmented exploration in nanophotonics

Masanobu Iwanaga SAMURAI ORCID (Research Center for Electronic and Optical Materials/Optical Materials Field/Nanophotonics Group, National Institute for Materials Science) ; Keisuke Watanabe SAMURAI ORCID (Research Center for Materials Nanoarchitectonics (MANA)/Semiconductor Materials Field/Photonics Nano Engineering Group, National Institute for Materials Science)

コレクション

引用
Masanobu Iwanaga, Keisuke Watanabe. Generative-AI-assisted knowledge-based augmented exploration in nanophotonics. Science and Technology of Advanced Materials-Methods. 2025, 5 (1), 2596940-2596940. https://doi.org/10.1080/27660400.2025.2596940

説明:

(abstract)

It is generally difficult to obtain valuable scientific findings without sufficient background knowledge or experience. Exploiting generative AI (genAI) and reliable computational method(s) strategically is expected to reduce the difficulty and attain scientific findings beyond human knowledge and experience. Here, we introduce a new approach that initially relies on a substantial amount of scientific literature to eliminate hallucinations, prepares metadata from the literature using genAIs, conducts retrieval augmented generation using a genAI, implements genAI-driven generations of concrete candidates of nanostructures, and evaluates the candidates quantitatively, which contain extended sets of structural parameters, by implementing a scientifically established simulation method. This genAI-assisted nonempirical approach has been applied in the field of nanophotonics, enabling the exploration of single-layer circular dichroic (CD) all-dielectric metasurfaces in telecom bands. We successfully revealed single-layer perfect CD metasurfaces, which have never been attained so far. The perfect CD metasurfaces are thin with subwavelength thickness in the near-infrared bands, are feasible in a semiconductor nanofabrication process, and significantly enlarge degrees of freedom in light-wave manipulations for telecom applications.

権利情報:

キーワード: generative AI, retrieval augmented generation, nonempirical exploration, nanophotonics, chiral metasurface, circular dichroism

刊行年月日: 2025-12-31

出版者: Informa UK Limited

掲載誌:

  • Science and Technology of Advanced Materials-Methods (ISSN: 27660400) vol. 5 issue. 1 p. 2596940-2596940

研究助成金:

  • NIMS AI-use Research Project Generative AI-use Research Project
  • JSPS KAKENHI JP24K01389

原稿種別: 出版者版 (Version of record)

MDR DOI:

公開URL: https://doi.org/10.1080/27660400.2025.2596940

関連資料:

その他の識別子:

連絡先:

更新時刻: 2025-12-19 16:31:37 +0900

MDRでの公開時刻: 2025-12-19 14:11:32 +0900

ファイル名 サイズ
ファイル名 Iwanaga_Watanabe_STAM-M5(2025)2596940.pdf (サムネイル)
application/pdf
サイズ 10.1MB 詳細