Answers are grounded in this paper and cite their sources.
Computational modeling demonstrates accurate multi-beam reflectarray gain curve prediction using QueryFieldNet, indicating viable deep learning surrogates for antenna beamforming.
This study proposes QueryFieldNet for predicting two orthogonal principal-cut wide-angle gain curves of fixed-θ-grid multi-beam reflectarrays. The balanced seven-point θ-grid dataset {−45°,−30°,−15°,0°,15°,30°,45°} contains 19 × 19 phase maps, 1- to 5-bit phase quantization, and one to four intended beams. QueryFieldNet combines periodic phase inputs, multi-scale 2D residual encoding, cross-attention decoding with 181 Fourier-θ queries, intended-beam metadata supervision, and beam-basis residual refinement. Three proposed metrics, Multi-Beam HPBW RMSE, Multi-Beam Main-Lobe RMSE, and Beam-Peak RMSE, quantify the local −3 dB, −10 dB, and peak-gain errors around each intended beam. Across three runs, the final QueryFieldNet obtains bit-wise macro-averaged RMSE 3.240±0.143, MAE 1.975±0.134, R20.99792±0.00017, Multi-Beam HPBW RMSE 1.872±0.015, Multi-Beam Main-Lobe RMSE 2.134±0.047, and Beam-Peak RMSE 1.730±0.065. The aggregate local-window values combine both principal cuts; for ϕ=90°, they represent target-centered local errors rather than physical intended-beam HPBW or peak measurements. These results concern an array-factor-level synthetic benchmark; full-wave and measurement-based validation remain future work.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: