Bonn 2020 – wissenschaftliches Programm

Die DPG-Frühjahrstagung in Bonn musste abgesagt werden! Lesen Sie mehr ...

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 1: AKPIK I

AKPIK 1.7: Vortrag

Mittwoch, 1. April 2020, 18:00–18:15, H-HS XII

Reconstructing Interferometric Data Using Neural Networks — •Felix Geyer and Kevin Schmidt — TU Dortmund

Radio interferometry is used to monitor and observe distant astronomical sources and objects with high resolution. Especially Very Long Baseline Interferometry allows to achieve the highest resolutions by combining the data of multiple telescopes. This results in an effective diameter corresponding to the greatest distance between two telescopes. The taken data consists of visibilities, which depend on the baselines between the telescopes. Because the distribution of these baselines is sparse, the sample of visibilities is incomplete. This influences the reconstruction of the image of the observed source in a negative way. A new and fast approach to reconstruct missing data reasonable is using neural networks. A critical component of a neural network is the loss function, which is different for each individual underlying task. One approach for the loss function in case of image reconstruction for high resolution images is called 'Perceptual Losses' (Johnson et al., 2016). This talk gives an overview of the first results of applying this loss function to reconstruct radio interferometric data.