The LESIA/Observatoire de Paris is seeking candidates for a 2-years post-doc position at LESIA on Machine Learning for Radio-astronomical Transients, Times series and Spectrograms.
The position is open for 2021 at LESIA, Observatoire de Paris
Organization: LESIA, Observatoire de Paris
Street Address : 5, place Jules Janssen
Zip/Postal Code: 92190
The position is open within the MINERVA project (Machine Learning for Radioastronomy at Observatoire de Paris). This project federate efforts to analyse large set of data coming from various fields of astrophysics.
Radioastronomy is experiencing an exponential increase of observational data volumes with the development of giant interferometers (LOFAR, ALMA, NenuFAR, SKA). These instruments produce huge and numerous two and four-dimensional datasets (among the 2D-spatial, 1D temporal and 1D spectral coordinates, depending on observation mode). Facing these daily TB-scale data (PB-scale with SKA), machine learning methods for source and event detection and classification open up new paths for data exploitation and new discoveries. In parallel, machine learning methods have undergone algorithmic developments that bring them to a high level of maturity.
The goal of this project is to perform pilot implementation of blind search of specific events (data mining in time domain) and automatic detection of known but unpredictable transient events. The project implementation will include optimisation techniques, physical processes modelling, adequate data preconditioning, etc. The developed algorithms will be integrated in new data analysis pipelines of aforementioned large astronomical infrastructures.
The key scientific goal is the real time (or near real time) detection of radio frequency transients coming from solar system objects and beyond. The scientific applications cover bleeding-edge astronomical topics such as Exoplanets, Fast Radio Bursts or Gravitational Waves, as well as more applied domains such as Space Weather, or the study of solar system planetary magnetospheres.
The successful candidate will have access to datasets from NenuFAR, the Nançay Decameter Array, and LOFAR. He or she will be integrated into NenuFAR team, and will participate to the science and technical meetings of this project. He or she will have access to computing resources dedicated to MINERVA (a dedicated server with GPUs), with the support of a research engineer from Obs Paris IT department. The new algorithms will be trained and tested against existing data collections and event lists.
Applicants should have at least an engineer diploma in the field of Machine Learning or a PhD in physics, astronomy, or computer science by the time of the appointment. Experience in Astronomy is not mandatory. We encourage applications from candidates with a strong expertise in either the manipulation or the development of state-of-the-art Machine Learning methods. Experience with manipulating images and data cubes will also be considered. Skills in one or several programing languages (e.g. Python, Fortran, C++) are necessary.
The Observatoire de Paris maintains a lively visitor program and hosts regular workshops and conferences throughout the year. The successful candidate will be immersed in an internationally visible research environment in the Paris and Meudon Campuses, with rich intellectual and computational resources.
The main office of the successful candidate will be located in Meudon.
The appointment is for 2 years with a salary including French social security benefits. Funding will also be allocated for travel.
Applicants should submit a CV (max. 2 pages), a publication list (if applicable), a short review of previous works (2 pages), a statement of research interests (2 pages) and reference letters. Applications should be sent via email (see above).
For full consideration materials must be received before June 30st, 2021. Applications received later will be considered until position is filled.
Included Benefits: French national medical insurance, Maternity/Paternity leave, Lunch subsidies, Family supplement for children, Participation to public transport fees, Pension contributions
Send your application to: firstname.lastname@example.org, Object : MINERVA Application