Tools and Languages for Machine Learning in Radar and Radio Astronomy

Project: Research

Project Details


NRF/STINT funded project with the University of Cape Town, South Africa. This project aims to advance the fields of radar and radio astronomy by applying specialized Machine Learning (ML) techniques to signal-processing and deploy these in modern antenna arrays and radio telescopes. The project is based on the cooperation between the Department of Computer Science, Lund University and the Department of Electrical Engineering, the University of Cape Town. The partners, building on common grounds in embedded systems and signal processing, bring together complementary expertise in ML and optimization techniques on one hand, and radar/radio astronomy applications and domain-specific languages on the other. The proposed collaboration combines training
interventions as well as collaborative research and field testing and involves both senior/junior researchers and graduate students. A total of four senior researchers, one post-doctoral fellow, two doctoral students, seven master students will be involved, working more than twenty months total at the partner academic institution. The project is planned to generate not only research results (publications, software tools, benchmarks) in areas of strategic relevance to both countries, namely AI/ML for Sweden and Astronomy for South Africa, but also to have an educational impact and facilitate experience exchange in higher-education between the two partner departments.

Layman's description

Radio astronomy and radar processing are data-intensive applications that can benefit from modern AI techniques including Machine Learning and Deep Learning. This project looks at how these techniques can be applied to antenna arrays similar to the Square Kilometer Array in South Africa.
Effective start/end date2019/01/292022/06/30

Collaborative partners


  • The Swedish foundation for International cooperation in research and higher education (STINT).

Free keywords

  • radar
  • radio astronomy
  • signal processing
  • machine learning