Modeling of planar dual-band microstrip patch antenna using Gaussian process regression

Gaussian process (GP) regression, a structured supervised learning alternative to neural networks for the fast modeling of antenna characteristics, is applied to modeling S
₁₁
and gain against frequency of a dual-band microstrip patch antenna with separate tuning strips on a three-layer substrate. Since the two frequency bands of the antenna are relatively narrow, the function underlying the variation of S
₁₁
with four geometry variables and frequency is challenging to map. Predictions using large test data sets yielded results of an accuracy comparable to the target moment-method-based full-wave simulations; highly favourable mean square errors were obtained. The GP methodology has various inherent advantages that include ease of implementation and the need to learn only a handful of (hyper) parameters.