# Machine learning approach to the detection of point sources in maps of the CMB temperature anisotropies

## TL;DR

This paper introduces a machine learning method using convolutional neural networks to detect extragalactic point sources in CMB temperature anisotropy maps, outperforming traditional techniques especially near the Galactic plane.

## Contribution

It presents a novel CNN-based approach for blind source detection in CMB maps, with region-specific training to enhance detection performance across different sky areas.

## Key findings

- CNN outperforms traditional methods like matched filter near the Galactic plane
- Region-specific training improves detection accuracy
- Achieves promising completeness and reliability levels

## Abstract

We propose a machine learning approach to the blind detection of extragalactic point sources on maps of the temperature anisotropies of the cosmic microwave background. Using realistic simulations of the microwave sky as seen by Planck, we train a convolutional neural network (CNN) that solves source detection as an image segmentation problem. We divide the sky into regions of progressively increasing Galactic foreground intensity and independently train specialized CNNs for each region. This strategy leads to promising levels of completeness and reliability, with our CNN substantially outperforming traditional detection methods like the matched filter in regions close to the Galactic plane.