Estimating the redshift and associated uncertainty of Fermi-LAT extra galactic sources

Predicting the redshifts of sources in the 4LAC-DR3 catalog and estimating the associated uncertainty with the help of variational inference.

Getting started

git clone https://github.com/abhimanyu911/redshift-regression-with-uncertainty.git pip install -r requirements.txt

Models used

Results in comparison to other algorithms

Sample predictions

Prediction summary

Please cite the manuscript incase you happen to use any of our code

Manuscript

``` @article{10.1093/mnras/stad3622, author = {Gharat, Sarvesh and Borthakur, Abhimanyu and Bhatta, Gopal}, title = "{Estimation of redshift and associated uncertainty of Fermi/LAT extragalactic sources with Deep Learning}", journal = {Monthly Notices of the Royal Astronomical Society}, volume = {527}, number = {3}, pages = {6198-6210}, year = {2023}, month = {11}, abstract = "{With the advancement of technology, machine learning-based analytical methods have pervaded nearly every discipline in modern studies. Particularly, a number of methods have been employed to estimate the redshift of gamma-ray loud active galactic nuclei (AGN), which are a class of supermassive black hole systems known for their intense multi-wavelength emissions and violent variability. Determining the redshifts of AGNs is essential for understanding their distances, which, in turn, sheds light on our current understanding of the structure of the nearby universe. However, the task involves a number of challenges, such as the need for meticulous follow-up observations across multiple wavelengths and astronomical facilities. In this study, we employ a simple yet effective deep learning model with a single hidden layer having 64 neurons and a dropout of 0.25 in the hidden layer on a sample of AGNs with known redshifts from the latest AGN catalogue, 4LAC-DR3, obtained from Fermi-LAT. We utilized their spectral, spatial, and temporal properties to robustly predict the redshifts of AGNs as well quantify their associated uncertainties by modifying the model using two different variational inference methods. We achieve a correlation coefficient of 0.784 on the test set from the frequentist model and 0.777 and 0.778 from both the variants of variational inference, and, when used to make predictions on the samples with unknown redshifts, we achieve mean predictions of 0.421, 0.415, and 0.393, with standard deviations of 0.258, 0.246, and 0.207 from the models, respectively.}", issn = {0035-8711}, doi = {10.1093/mnras/stad3622}, url = {https://doi.org/10.1093/mnras/stad3622}, eprint = {https://academic.oup.com/mnras/article-pdf/527/3/6198/54023038/stad3622.pdf}, }

```