Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials
Abstract A hyperbolic metamaterial absorber has great potential for improving the performance of photo-thermoelectric devices targeting heat sources owing to its broadband absorption. However, optimizing its geometry requires considering numerous parameters to achieve absorption that aligns with the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83167-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559467246747648 |
|---|---|
| author | Kenta Hamada Hui-Hsin Hsiao Wakana Kubo |
| author_facet | Kenta Hamada Hui-Hsin Hsiao Wakana Kubo |
| author_sort | Kenta Hamada |
| collection | DOAJ |
| description | Abstract A hyperbolic metamaterial absorber has great potential for improving the performance of photo-thermoelectric devices targeting heat sources owing to its broadband absorption. However, optimizing its geometry requires considering numerous parameters to achieve absorption that aligns with the radiation spectrum. Here, we compare three algorithms using deep reinforcement learning for the optimization of a hyperbolic metamaterial absorber. By analyzing the absorption spectra obtained from the three algorithms with limited number of datasets, we assessed the prediction accuracy of each algorithm. Our findings indicate that relying on a single algorithm for optimization, particularly with a small number of datasets, can lead to misestimations in structural optimization. This underscores the importance of using multiple algorithms to ensure accurate and reliable optimization results. Finally, by utilizing the optimal algorithm, we achieved to increase the power generation of the metamaterial thermoelectric conversion by five times. |
| format | Article |
| id | doaj-art-cd8ac4fe9d96480cbeb936cc2088b969 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cd8ac4fe9d96480cbeb936cc2088b9692025-01-05T12:28:46ZengNature PortfolioScientific Reports2045-23222024-12-0114111310.1038/s41598-024-83167-zComparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterialsKenta Hamada0Hui-Hsin Hsiao1Wakana Kubo2Division of Advanced Electrical and Electronics Engineering, Tokyo University of Agriculture and TechnologyDepartment of Engineering Science and Ocean Engineering, National Taiwan UniversityDivision of Advanced Electrical and Electronics Engineering, Tokyo University of Agriculture and TechnologyAbstract A hyperbolic metamaterial absorber has great potential for improving the performance of photo-thermoelectric devices targeting heat sources owing to its broadband absorption. However, optimizing its geometry requires considering numerous parameters to achieve absorption that aligns with the radiation spectrum. Here, we compare three algorithms using deep reinforcement learning for the optimization of a hyperbolic metamaterial absorber. By analyzing the absorption spectra obtained from the three algorithms with limited number of datasets, we assessed the prediction accuracy of each algorithm. Our findings indicate that relying on a single algorithm for optimization, particularly with a small number of datasets, can lead to misestimations in structural optimization. This underscores the importance of using multiple algorithms to ensure accurate and reliable optimization results. Finally, by utilizing the optimal algorithm, we achieved to increase the power generation of the metamaterial thermoelectric conversion by five times.https://doi.org/10.1038/s41598-024-83167-zHyperbolic metamaterialsDeep reinforcement learningAlgorithmMetamaterial thermoelectric conversion |
| spellingShingle | Kenta Hamada Hui-Hsin Hsiao Wakana Kubo Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials Scientific Reports Hyperbolic metamaterials Deep reinforcement learning Algorithm Metamaterial thermoelectric conversion |
| title | Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| title_full | Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| title_fullStr | Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| title_full_unstemmed | Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| title_short | Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| title_sort | comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials |
| topic | Hyperbolic metamaterials Deep reinforcement learning Algorithm Metamaterial thermoelectric conversion |
| url | https://doi.org/10.1038/s41598-024-83167-z |
| work_keys_str_mv | AT kentahamada comparisonofalgorithmsusingdeepreinforcementlearningforoptimizationofhyperbolicmetamaterials AT huihsinhsiao comparisonofalgorithmsusingdeepreinforcementlearningforoptimizationofhyperbolicmetamaterials AT wakanakubo comparisonofalgorithmsusingdeepreinforcementlearningforoptimizationofhyperbolicmetamaterials |