Optimal SKA antenna configuration using genetic algorithms

The Square Kilometre Array (SKA) is a radio telescope designed to operate between 70MHz and 10GHz. Due to this large bandwidth, the SKA will be built out of different collectors, namely antennas and dishes to cover the frequency range adequately. In order to deal with this bandwidth, innovative feeds and detectors must be designed and introduced in the initial phases of development. Moreover, the required level of resolution may only be achieved through a novel configuration of dishes and antennas. Due to the large collecting area and the specifications required for the SKA to deliver the promised science, the configuration of the dishes and the antennas within stations is an important question. This research investigates the applicability of machine learning techniques to determine an optimum configuration for the elements within an aperture array station. Genetic algorithms are primarily used to search a large space of optimum layouts. Fitness functions based on estimates of the main lobe to maximum side lobe ratio, the side lobes fall off rate, the main lobe area to side lobes area ratio as well as the kurtosis of residuals from polynomial fits of the main beam, are employed.