DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 신종화 | - |
dc.contributor.author | Kim, Myungjoon | - |
dc.contributor.author | 김명준 | - |
dc.date.accessioned | 2024-07-26T19:31:32Z | - |
dc.date.available | 2024-07-26T19:31:32Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1052019&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321132 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 신소재공학과, 2023.2,[viii, 72 p. :] | - |
dc.description.abstract | Recent advances in nanofabrication enable the manufacture of arbitrary-shaped optical metasurfaces. The carefully designed free-form metasurfaces display advanced photonic performance which cannot be achieved by traditional optics. However, the design of free-form metasurfaces incurs an expensive cost. Here, we demonstrate that free-form metasurfaces can be optimized rapidly by employing both adjoint-based optimization and physics-informed deep learning. In particular, the design method of metamask for proximity field nanopatterning enables the generation of unachieved patterns. In addition, we propose symmetry-encoded convolutional neural networks to reflect physical characteristics of periodic metasurfaces. The proposed deep learning models can replace optical simulators for measurements of physical properties. Combining adjoint-based optimization and physics-informed deep learning, the inverse design process can be significantly accelerated. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 메타표면▼a역설계▼aAdjoint 방법▼a근접장 나노패터닝▼a물리기반 딥러닝 | - |
dc.subject | Metasurface▼aInverse design▼aAdjoint method▼aProximity field nanopatterning▼aPhysics-informed deep learning | - |
dc.title | Inverse design of free-form metasurfaces: from adjoint-based optimization to physics-informed deep learning | - |
dc.title.alternative | 자유형상 메타표면 역설계: Adjoint 방법 기반 최적화와 물리기반 딥러닝 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :신소재공학과, | - |
dc.contributor.alternativeauthor | Shin, Jonghwa | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.