In the mid-1960s, researchers first discovered pulsars, which emit regular bursts of radio waves and were initially considered enigmatic. It was later found that they were rotating neutron stars emitting radiation that was observed across a broad range of wavelengths, including gamma rays. Since then, gamma-ray astronomy has continued to be a field of active research, and a significant fraction of gamma-ray sources remain unidentified. The goal of this problem statement is to develop a machine learning model that can accurately classify gamma-ray sources based on their characteristics and properties, using data from various space-based observatories. Gamma-ray sources can be broadly classified into two types: AGNs and pulsars. The pulsars can be further classified as millisecond pulsars or young pulsars. Similarly some common types of AGNs include quasars, Seyfert galaxies, and blazars.
Train a model to classify different types of Gamma-ray Sources. We have used a logistic regression model to classify all the sub categories of pulsars and AGNs
Create a sky map of the classified sources. Skymap plottted using astropy.
To run this project, follow these steps:
- Download this google drive folder on your own device.
- extract it and run the notebook on jupyter.
Or
- If you use it on Google colab
- Mount your google drive
- And change the address of the read_csv() command to the directory of dataset on your own drive
That's it! You should now be able to see the project running in your browser.