The reverse design of a tunable terahertz metasurface antenna based on a deep neural network

Abstract

The reverse design of a tunable terahertz metasurface antenna is proposed based on the deep neural network (DNN). To obtain the tunable properties of the terahertz antenna, the phase‐changed material vanadium dioxide (VO2) is introduced by controlling the voltage without changing the structures of the metasurface antenna. To improve the efficiency and accuracy of the terahertz antenna, the DNN is used to establish the relationship of amplitude and phase for the antenna unit. The prediction errors are below 10%. The radiation direction of the antenna can be changed from 0° to 52° by the VO2 with different states. The prediction error of angle is only 1° difference from the theoretical calculation. This reverse design method can be extended to other metasurface devices with improved efficiency and accuracy.

A reconfigurable graphene patch antenna inverse design at terahertz frequencies

“…In this case, depending on the circumstances, the antenna parameters may be fully adjustable or non-adjustable 28 , 32 . Although in 29 a is used as a reconfigurable component in the antenna, the proposed DNN outputs geometrical antenna parameters.…”

“…After learning, the designed model based on trained data can show a reasonable prediction as outputs for various given inputs in a fraction of a second. By taking advantage of this, DL was a suitable technique for inverse scattering problems 18,19 , design of metasurfaces [20][21][22] and metamaterials [23][24][25] , design of photonic structures 26,27 ,beamforming 28,29 , design of antennas [30][31][32] .The deep neural network (DNN) architecture has been evolving over the years with new techniques and advancements. We can mention some recent techniques that applied in electromagnetic fields 23,27,33 .…”

“…After learning, the designed model based on trained data can show a reasonable prediction as outputs for various given inputs in a fraction of a second. By taking advantage of this, DL was a suitable technique for inverse scattering problems 18,19 , design of metasurfaces [20][21][22] and metamaterials [23][24][25] , design of photonic structures 26,27 ,beamforming 28,29 , design of antennas [30][31][32] .…”

A Reconfigurable Graphene Patch Antenna Inverse Design at Terahertz Frequencies

“…After learning, the designed model based on trained data can show a reasonable prediction as outputs for various given inputs in a fraction of a second. By taking advantage of this, DL was a suitable technique for inverse scattering problems 18,19 , metasurface design 20,21 , beamforming 22,23 , design of antenna [24][25][26] .…”

“…In this case, depending on the circumstances, the antenna parameters may be fully adjustable or non-adjustable 22,26 . Although in 23 a VO 2 is used as a reconfigurable component in the antenna, the proposed DNN outputs geometrical antenna parameters.…”