| 학회 | 한국재료학회 |
| 학술대회 | 2021년 가을 (11/24 ~ 11/26, 경주 라한호텔) |
| 권호 | 27권 2호 |
| 발표분야 | 특별심포지엄 5. 첨단 메타물질 심포지엄-오거나이저: 한성옥(KIER), 이학주(KIMM) |
| 제목 | Inverse design and forward modelling in nanophotonics using deep-learning |
| 초록 | Recent introduction of deep learning into nanophotonics has enabled efficient inverse design process [1]. Once the deep learning network is trained, it allows fast inverse design for multiple design tasks. In this talk, we show several inverse designing nanophotonic structures using deep learning [1-9]. We firstly discuss inverse design methods that increase the degree of freedom of design possibilities. These attempts include designing arbitrary shapes of nanophotonic structures, that are not limited to pre-defined structures [2], and designing both types of materials and structural parameters simultaneously [3]. In order to design arbitrary shapes of structures, cross-sectional design images are designed by generative model. Also, for simultaneous design of materials and structural parameters, we developed a novel objective function that combines regression and classification problems. After then, we also discuss optimizing nanophotonic structures using deep learning. We use reinforcement learning to optimize structure parameters. Using reinforcement learning, an agent learns parameter space of an environment through the exploration and exploitation of the reward. After learning, the agent can provide the optimized design parameters from its own experience. Several meta-devices including dielectric color filter [4], high efficiency hologram [5], perfect absorber [6-8], plasmonic structures [9], dielectric gratings [10, 11] and microwave antenna [12] are designed using this method. References 1. S. So, T. Badloe, J. Noh, J. B. Abad, J. Rho, “Deep learning enabled inverse design in nanophotonics”, Nanophotonics 9, 1041-1057, 2020. 2. S. So, J. Rho, “Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks”, Nanophotonics 8, 1255-1261, 2019. 3. S. So, J. Mun, J. Rho, “Simultaneous inverse design of materials and parameters of core-shell nanoparticle via deep-learning: Demonstration of dipole resonance engineering”, ACS Applied Materials and Interfaces 11, 24264-24268, 2019. 4. I. Sajedian, T. Badloe, J. Rho, “Optimization of colour generation from dielectric nanostructures using reinforcement learning”, Optics Express 27, 5874-5883, 2019. 5. I. Sajedian, H. Lee, J. Rho, “Double-deep Q-learning to increase the efficiency of metasurface holograms”, Scientific Reports 9, 10899, 2019. 6. T. Badloe, I. Kim, J. Rho, “Biomimetic ultra-broadband perfect absorbers optimized with reinforcement learning”, Physical Chemistry Chemical Physics, 22 2337-2342, 2019 7. T. Badloe, I. Kim, J. Rho, “Moth-eye shaped on-demand broadband and switchable perfect absorbers based on vanadium dioxide”, Scientific Reports 10, 4522, 2020 8. I. Sajedian, H. lee, J. Rho, “Design of high transmission color filters for solar cells directed by deep Q-learning”, Solar Energy 195, 670-676, 2020. 9. I. Sajedian, J. Kim, J. Rho, “Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks”, Microsystems and Nanoengineering 5, 27, 2019. 10. S. So, Y. Yang, T. Lee, J. Rho, “On-demand design of spectrally sensitive multi-band absorbers using an artificial neural network”, Photonics Research 9, B153-B158, 2021 11. S. So, D. Lee, T. Badloe, J. Rho, “Inverse design of ultra-naoorwband selective thermal emitters designed by artificial neural networks”, Optical Materials Express 11, 1863-1873, 2021 12. J. Noh et al., “Design of transmissive metasurface antenna using deep neural networks”, Optical Materials Express 11, 2310-2317, 2021 |
| 저자 | 노준석 |
| 소속 | 포항공과대 |
| 키워드 | <P>Deep learning; Artificial intelligence; Metamaterials; Nanophotonics; Nanofabrication</P> |
