Freiburg 2019 – scientific programme

Sessions | Days | Selection | Search | Updates | Downloads | Help

FM: Fall Meeting

FM 82: Quantum & Information Science: Neural Networks, Machine Learning, and Artificial Intelligence III

FM 82.4: Talk

Thursday, September 26, 2019, 15:00–15:15, 3044

Analyzing VLBI Data Using Neural Networks — •Kevin Schmidt — TU Dortmund

Very long baseline interferometry (VLBI) allows the observation of distant astronomical objects with the highest resolution. In this technique, the data of several radio telescopes are combined to achieve an effective diameter equal to the greatest distance between the telescopes.

Radio interferometers measure visibilities depending on the baseline between the individual telescopes. Since they are distributed only sparsely, much visibility space remains uncovered. This lack of information causes noise artifacts in the recorded data. In recent decades, various implementations of the CLEAN algorithm (Clark, 1980) have been used to remove these artifacts from radio images. With the increasing data rates of modern radio telescopes, faster solutions have to be found to analyze the observations in a reasonable time.

A new and faster approach is using neural networks. This presentation gives an overview of the first results.