This project uses the k-means algorithm and the elbow method to identify potential star and galaxy clusters.

It first queries for astronomical data (star / galaxy coordinates) from the SIMBAD database

Bash shell scripting used to

• clean resultant data

C++ used to

• convert coordinates from RA and Dec (right ascension and declination) to x-y coordinates for 2D plotting
• use the elbow method (by running the clustering over a range of k values) to find the optimal number of clusters
• running k-means (where k is determined on the previous step) on the data and plotting it with gnuplot

Checkout our project source code on Github!

Some resultant plots: