Evolutionary Algorithms with Quantum Deep Field for Compounds with High Light Absorption for Organic Photovoltaics

カテゴリ：部門大会

論文No：SS1-3

グループ名：【C】2025年電気学会電子・情報・システム部門大会

発行日：2025/8/20

タイトル(英語)：Evolutionary Algorithms with Quantum Deep Field for Compounds with High Light Absorption for Organic Photovoltaics

著者名：Vasilevich Aleksandr（近畿大学）,葉山 大雅（近畿大学）,木原 泰一（近畿大学）,山田 山田（近畿大学）,大久保 貴志（近畿大学）,半田 久志（近畿大学）

著者名(英語)： Aleksandr Vasilevich (Kindai University),Taiga Hayama (Kindai University),Taichi Kihara (Kindai University),Takeshi Yamada (Kindai University),Takashi Ohkubo (Kindai University),Hisashi Handa (Kindai University)

キーワード：organic photovoltaics,Quantum Deep Field,chemical compounds,evolutionary algorithms

要約(日本語)：In this paper, we propose an approach for discovering organic compounds with high light absorption, suitable for organic thin-film solar cells. By fragmenting existing compounds into sub-compounds and reassembling them, we generate candidate structures in an evolutionary algorithm framework. To evaluate these candidates efficiently, we employ Quantum Deep Field (QDF), a deep learning method based on functional theory density, which reduces computational costs by roughly 99% compared to Gaussian16. This speedup enables large-scale evolutionary searches within a realistic timeframe. confirmed via Gaussian16, that the best-performing discovered compounds with QDF outperformed several conventional organic solar cell materials in terms of UV-Vis absorption intensity.

本誌掲載ページ：1769-1771p

原稿種別：英語

PDFファイルサイズ：1,237Kバイト