TY - JOUR

T1 - Deep Q-network to produce polarization-independent perfect solar absorbers

T2 - a statistical report

AU - Sajedian, Iman

AU - Badloe, Trevon

AU - Lee, Heon

AU - Rho, Junsuk

N1 - Funding Information:
This work was financially supported by the National Research Foundation (NRF) grants (NRF-2019R1A2C3003129, CAMM-2019M3A6B3030637, NRF-2019R1A5A8080290, NRF-2018M3D1A1058997) funded by the Ministry of Science and ICT (MSIT), Republic of Korea. Acknowledgements
Publisher Copyright:
© 2020, The Author(s).

PY - 2020/12/1

Y1 - 2020/12/1

N2 - Using reinforcement learning, a deep Q-network was used to design polarization-independent, perfect solar absorbers. The deep Q-network selected the geometrical properties and materials of a symmetric three-layer metamaterial made up of circular rods on top of two films. The combination of all the possible permutations gives around 500 billion possible designs. In around 30,000 steps, the deep Q-network was able to produce 1250 structures that have an integrated absorption of higher than 90% in the visible region, with a maximum of 97.6% and an integrated absorption of less than 10% in the 8–13 µm wavelength region, with a minimum of 1.37%. A statistical analysis of the distribution of materials and geometrical parameters that make up the solar absorbers is presented.

AB - Using reinforcement learning, a deep Q-network was used to design polarization-independent, perfect solar absorbers. The deep Q-network selected the geometrical properties and materials of a symmetric three-layer metamaterial made up of circular rods on top of two films. The combination of all the possible permutations gives around 500 billion possible designs. In around 30,000 steps, the deep Q-network was able to produce 1250 structures that have an integrated absorption of higher than 90% in the visible region, with a maximum of 97.6% and an integrated absorption of less than 10% in the 8–13 µm wavelength region, with a minimum of 1.37%. A statistical analysis of the distribution of materials and geometrical parameters that make up the solar absorbers is presented.

KW - Deep Q-learning

KW - Perfect solar absorbers

KW - Reinforcement learning

KW - Statistical analysis

UR - http://www.scopus.com/inward/record.url?scp=85088874292&partnerID=8YFLogxK

U2 - 10.1186/s40580-020-00233-8

DO - 10.1186/s40580-020-00233-8

M3 - Article

AN - SCOPUS:85088874292

SN - 2196-5404

VL - 7

JO - Nano Convergence

JF - Nano Convergence

IS - 1

M1 - 26

ER -