Reinforcement Learning-Based Inverse Design of Multilayer Particles
Computation · 10.04.2026 · 14 (4) · 91
DOI: 10.3390/computation14040091 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computation, online erschienen am 10.04.2026. Verfasst von Zhaohui Li und 2 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Multilayered particles possess exceptional optical properties and hold significant potential for applications in chemical analysis, life sciences, optical sensing, and photonic integration. In practical applications, however, it is often necessary to perform inverse design of multilayered particles with given optical characteristics to meet specific requirements, a process that remains time-consuming. To overcome this challenge, we propose a reinforcement learning-based method for the automated design of multilayered particles. Leveraging the self-learning capacity of reinforcement learning models in combination with an optical characteristics calculation model, the method iteratively determines particle parameters that fulfill the desired optical responses. This method effectively addresses the many-to-one parameter mapping problem in inverse design, eliminates the need for extensive pre-computations, and provides an innovative approach to the automated design of complex nanostructures.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, Z., Gao, F., & Liu, D. (2026). Reinforcement Learning-Based Inverse Design of Multilayer Particles. Computation, 14(4), 91. https://doi.org/10.3390/computation14040091
Vancouver
Li Z, Gao F, Liu D. Reinforcement Learning-Based Inverse Design of Multilayer Particles. Computation. 2026;14(4):91. doi:10.3390/computation14040091
BibTeX
@article{Li2026,
author = {Li, Zhaohui and Gao, Fang and Liu, Delian},
title = {Reinforcement Learning-Based Inverse Design of Multilayer Particles},
journal = {Computation},
year = {2026},
volume = {14},
number = {4},
pages = {91},
doi = {10.3390/computation14040091}
}
EUVIMED