Galaxy selection

Big Data classification/cleansing

This project involved both, Data Science and Data Engineering. The main task was to fetch raw data of hundreds of millions of unclassified space sources (Galaxies, stars, asteroids, and fake sources), load in a single data frame and apply a high level of cleaning where we can extract a particular type of galaxy only. This process presented a certain level of complexity from which I get to publish two scientific articles as main author and one as second author.

​

The end result was a catalogue of galaxies that is currently being used by the DESI survey, the biggest spectroscopic survey of all the time. Resulting catalogue is one of the four kind of galaxies DESI is observing.

​

Check this press post about me and my role within DESI.

​