MILCANN: A tSZ map for galaxy cluster detection assessed using a neural network

We present the first combination of a thermal Sunyaev-Zel’dovich (tSZ) map with a multi-frequency quality assessment of the sky pixels based on artificial neural networks with the aim being to detect tSZ sources from submillimeter observations of the sky by Planck . We present the construction of the resulting filtered and cleaned tSZ map, MILCANN. We show that this combination leads to a significant reduction of noise fluctuations and foreground residuals compared to standard reconstructions of tSZ maps. From the MILCANN map, we constructed a tSZ source catalog of about 4000 sources with a purity of 90%. Finally, we compare this catalog with ancillary catalogs and show that the galaxy-cluster candidates in our catalog are essentially low-mass (down to M 500  = 1014  M ⊙ ) high-redshift (up to z  ≤ 1) galaxy cluster candidates.