Developing automatic line identification algorithms in the era of Large Surveys

The VLA Orion A Large Survey (VOLS) large project will perform the deepest survey at subarcsecond resolution of the Orion A molecular cloud with the Karl G. Jansky Very Large Array (PI: G. Busquet, see  https://vols.fqa.ub.edu).  The superb sensitivity of the VLA combined with the large field of view of VOLS (~1 deg x 0.5 deg) requires a new strategy to identify regions of line emission. The VOLS project includes the emission lines of OH and CH3OH masers, 18 Hydrogen Radio Recombination lines and the line thermal emission of HC5N and SO molecules. The goal of this Master Thesis is to develop automatic algorithms based on Deep Learning/Machine Learning techniques to identify regions of line emission in the visibility domain. This is crucial for the next generation of radio interferometers such as the Square Kilometre Array (SKA) or the next generation VLA (ngVLA), which will perform deep surveys over large areas in the sky being 10 times more sensitive than the current radio facilities.