A convolutional neural network for cosmic string detection in CMB temperature maps

We present in detail the convolutional neural network used in our previous work to detect cosmic strings in cosmic microwave background (CMB) temperature anisotropy maps. By training this neural network on numerically generated CMB temperature maps, with and without cosmic strings, the network can produce prediction maps that locate the position of the cosmic strings and provide a probabilistic estimate of the value of the string tension Gμ. Supplying noiseless simulations of CMB maps with arcmin resolution to the network resulted in the accurate determination both of string locations and string tension for sky maps having strings with string tension as low as Gμ = 5 × 10^-9, a result from our previous work. In this work we discuss the numerical details of the code that is publicly available online. Furthermore, we show that though we trained the network with a long straight string toy model, the network performs well with realistic Nambu-Goto simulations.