Redshift prediction of Fermi-LAT gamma-ray sources using catboost gradient boosting decision trees

The determination of distance is fundamental in astrophysics. Gamma-ray sources are poorly characterized in this sense, as the limited angular resolution and poor photon-count statistics in gamma-ray astronomy makes it difficult to associate them to a multiwavelength object with known redshift. Taking the 1794 active galactic nuclei (AGNs) with known redshift from the Fermi-LAT latest AGN catalogue, 4LAC-DR3, we employ machine learning techniques to predict the distance of the rest of AGNs based on their spectral and spatial properties. The state-of-the-art catboost algorithm reaches an average 0.56 R2 score with 0.46 root-mean-squared error, predicting an average redshift value of z(avg) = 0.63, with a maximum z(max) = 1.97. We use the shap explainer package to gain insights into the variables influence on the outcome, and also study the extragalactic background light implications. In a second part, we use this regression model to predict the redshift of the unassociated sample of the latest LAT point-source catalogue, 4FGL-DR3, using the results of a previous paper to determine the possible AGNs within them.

Automated summary

The determination of distance is crucial in astrophysics, but it is challenging for gamma-ray sources due to limited angular resolution and poor photon-count statistics. This study utilizes machine learning techniques to predict the distance of active galactic nuclei (AGNs) based on their spectral and spatial properties. The state-of-the-art catboost algorithm achieves an average R2 score of 0.56 and a root-mean-squared error of 0.46, accurately predicting the redshift of AGNs. The regression model is also applied to predict the redshift of unassociated sources in a different catalog.