Dig the Radio Sky with Neural Networks
This internship is to join the MINERVA project (Machine Learning for Radioastronomy at the Observatoire de Paris). This project federates astrophysicists interested in a variety of astrophysical phenomena.
In the perspective of SKA, radio-astronomy is experiencing a rebirth in its low-frequency domain. However, this new age is also facing an explosion of volumes of observational data. This is particularly true with the development of giant interferometers (LOFAR, ALMA, NenuFAR, SKA). These instruments produce very large and highly dimensional datasets. In this context, traditional methods of source detection and classification reach their limits. In parallel, machine learning methods have undergone algorithmic developments that bring them to a high level of maturity for these tasks.
Artificial Intelligence – The MINERVA team has recently won the second SKA data challenge (focussed on source detection and identification in a large 3D synthetic cube). The team developed specialized convolutional neural networks (CNN) to achieve this goal. Our team has also applied his own methods to the first SKA data challenge dataset (focussed on source detection and classification in 2D images) which produces very promising results that need to be exploited.
Galaxy survey and Observations – The MINERVA team is also involved in LoTSS (the LOFAR Two-metre Sky Survey: a high-resolution 120-168 MHz survey of the entire northern sky). This survey opens an unprecedented view on the radio sky and its population of radio-galaxies. However, source detection and classification is still an on-going work. In particular the cross-matching with galaxy catalogues in the optical domain still encounters problems because of the different morphology of the objects at different wavelengths.
The goal of this internship is to perform a pilot implementation of the new methods developed by the MINERVA team in the context of the SKA data challenges. The fellow mission will be to adapt and apply these methods on real observational data, namely the LoTSS fields. The ultimate goal is to release a new catalogue of radio sources, with a classification based on their morphology. To achieve this goal, the internship fellow will have access to computing resources (GPUs) dedicated to MINERVA.
We encourage applications from candidates with knowledge in either the manipulation or the development of state-of-the-art Machine Learning methods. Skills with manipulating images and data cubes will also be considered. A good level in Python and C/C++ programming languages is mandatory.