Stage Event: Internship Computing Group

Geplaatst op: 31-10-2019 | Solliciteren voor: 02-01-2020
Dwingeloo

ASTRON is the Netherlands Institute for Radio Astronomy. Its mission is to make discoveries in radio astronomy happen, via the development of novel and innovative technologies, the operation of world-class radio astronomy facilities, and the pursuit of fundamental astronomical research.

The ASTRON Research & Development division is responsible for the technical program. The program focuses on innovative instruments for existing telescopes as well as on developing technologies for future observing facilities.

Description of the ASTRON assignment

In modern radio telescopes such as LOFAR, System Health Management (SHM) systems are crucial for detection and identifying system errors. Due to the increasing scale and complexity of the systems involved, this is becoming more and more difficult. Machine learning approaches (AI) for clustering error features are currently being investigated, but these lack a good training set, example spectrograms with known features, a so-called ground truth.

The aim of this assignment is to create this ground truth, a dictionary of example spectrograms in which system errors are associated with typical patterns in the spectrogram images.

The student is expected to:

  • write Python code to read LOFAR spectrogram data,
  • to select and apply image filters to isolate image features,
  • to relate (with support from ASTRON) features to system errors, and
  • to create an initial system error dictionary.

For more information please contact M.Sc. Walter Jansen, Group Manager Computing, wjansen@astron.nl or dr. ir. Albert Jan Boonstra, Programme Manager Technical Research, boonstra@astron.nl and secretaryrd@astron.nl

You can send your CV and motivation to stage@astron.nl.

ASTRON

Nieuwsbrief

Innovatiecluster Drachten maakt gebruik van cookies.
Innovatiecluster Drachten gebruikt cookies onder andere om de website te analyseren, te verbeteren en voor social media doeleinden. Door gebruik te blijven maken van deze website of door op akkoord knop te drukken, geef je aan akkoord te zijn met het gebruik van cookies op de websites van Innovatiecluster Drachten.