中国物理B ›› 2025, Vol. 34 ›› Issue (9): 90702-090702.doi: 10.1088/1674-1056/adeb5c

• • 上一篇    下一篇

Inverse design of directional hybrid nanoantennas using neural networks

Ru-Lin Guan(管如林)1,2, Deng-Chao Huang(黄登朝)1,2,†, Ya-Qiong Li(李雅琼)1,2, Chen Wang(王晨)1,2, and Bin-Zi Xu(徐彬梓)1,2   

  1. 1 Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, College of Electrical Engineering (College of Integrated Circuits), Anhui Polytechnic University, Wuhu 241000, China;
    2 Anhui Engineering Research Center of Vehicle Display Integrated Systems, School of Integrated Circuits, Anhui Polytechnic University, Wuhu 241000, China
  • 收稿日期:2025-04-03 修回日期:2025-07-01 接受日期:2025-07-03 出版日期:2025-08-21 发布日期:2025-08-28
  • 通讯作者: Deng-Chao Huang E-mail:huangdengchao@ahpu.edu.cn
  • 基金资助:
    artificial neural network|Kerker condition|nanosphere nanoantenna|high-order plasmon modes

Inverse design of directional hybrid nanoantennas using neural networks

Ru-Lin Guan(管如林)1,2, Deng-Chao Huang(黄登朝)1,2,†, Ya-Qiong Li(李雅琼)1,2, Chen Wang(王晨)1,2, and Bin-Zi Xu(徐彬梓)1,2   

  1. 1 Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, College of Electrical Engineering (College of Integrated Circuits), Anhui Polytechnic University, Wuhu 241000, China;
    2 Anhui Engineering Research Center of Vehicle Display Integrated Systems, School of Integrated Circuits, Anhui Polytechnic University, Wuhu 241000, China
  • Received:2025-04-03 Revised:2025-07-01 Accepted:2025-07-03 Online:2025-08-21 Published:2025-08-28
  • Contact: Deng-Chao Huang E-mail:huangdengchao@ahpu.edu.cn
  • Supported by:
    Project supported by the Key Research Projects of Colleges and Universities in Anhui Province (Grant No. KJ2021A0492), the Pre-research Project of the National Natural Science Foundation, AnHui Polytechnic University (Grant Nos. Xjky2022042 and Xjky2022048), the Testing Technology and Energy Saving Device Anhui Provincial Laboratory Open Fund (Grant No. JCKJ2022A09), the Joint Opening Project of Anhui Engineering Research Center of Vehicle Display Integrated Systems and Joint Discipline Key Laboratory of Touch Display Materials and Devices in Anhui Province (Grant No. VDIS2023B02), and the Science and Technology Project of Wuhu (Grant No. 2023jc05).

RichHTML

0

PDF (PC)

34

赞

摘要： Controlling the directionality of quantum emitter (QE) radiation is crucial for advancing nanophotonic devices, yet designing compact, single nanoantennas for this purpose remains challenging with traditional methods due to computational demands and optimization complexity. This paper introduces a neural-network-based inverse design approach to efficiently optimize single core-shell nanosphere antennas and their derivatives — notched core-shell structures and dimers — for highly directional QE emission. We systematically compare the radial basis function (RBF), support vector regression (SVR), and backpropagation neural network (BPNN) algorithms. Our results demonstrate BPNN's superior performance in accurately mapping nanoantennas' geometric and material parameters to their far-field radiation characteristics. Subsequent BPNN-driven optimization confirms that all three investigated structures (single core-shell, notched core-shell, and dimer) can achieve robust directional emission. This is accomplished by precisely exciting higher-order electric and magnetic multipoles engineered to possess equal amplitudes and opposite phases, thereby facilitating directional radiation from QEs and enabling more efficient nanophotonic device design.

关键词: artificial neural network, Kerker condition, nanosphere nanoantenna, high-order plasmon modes

Abstract: Controlling the directionality of quantum emitter (QE) radiation is crucial for advancing nanophotonic devices, yet designing compact, single nanoantennas for this purpose remains challenging with traditional methods due to computational demands and optimization complexity. This paper introduces a neural-network-based inverse design approach to efficiently optimize single core-shell nanosphere antennas and their derivatives — notched core-shell structures and dimers — for highly directional QE emission. We systematically compare the radial basis function (RBF), support vector regression (SVR), and backpropagation neural network (BPNN) algorithms. Our results demonstrate BPNN's superior performance in accurately mapping nanoantennas' geometric and material parameters to their far-field radiation characteristics. Subsequent BPNN-driven optimization confirms that all three investigated structures (single core-shell, notched core-shell, and dimer) can achieve robust directional emission. This is accomplished by precisely exciting higher-order electric and magnetic multipoles engineered to possess equal amplitudes and opposite phases, thereby facilitating directional radiation from QEs and enabling more efficient nanophotonic device design.

Key words: artificial neural network, Kerker condition, nanosphere nanoantenna, high-order plasmon modes

中图分类号:  (Neural networks, fuzzy logic, artificial intelligence)

  • 07.05.Mh
42.25.-p (Wave optics) 73.20.Mf (Collective excitations (including excitons, polarons, plasmons and other charge-density excitations)) 73.20.Mf (Collective excitations (including excitons, polarons, plasmons and other charge-density excitations))