Iterative Time-Domain Method for Resolving Multiple Gravitational Wave Sources in Pulsar Timing Array Data
Yi-Qian Qian, Soumya D. Mohanty, and Yan Wang
Phys. Rev. D, Jul 2022
The sensitivity of ongoing searches for gravitational wave (GW) sources in the ultra-low-frequency regime (10-9 Hz to 10-7 Hz) using pulsar timing arrays (PTAs) will continue to increase in the future as more well-timed pulsars are added to the arrays. It is expected that next-generation radio telescopes, namely, the Five-Hundred-Meter Aperture Spherical Radio Telescope (FAST) and the Square Kilometer Array (SKA), will grow the number of well-timed pulsars to O(103). The higher sensitivity will result in greater distance reach for GW sources, uncovering multiple resolvable GW sources in addition to an unresolved population. Data analysis techniques that can search for and resolve multiple signals present simultaneously in PTA data are, therefore, required. The multisource resolution problem in PTA data analysis poses a unique set of challenges such as nonuniformly sampled data, a large number of so-called pulsar phase parameters that arise from the inaccurately measured distances to the pulsars, and poor separation of signals in the Fourier domain due to a small number of cycles in the observed waveforms. We present a method that can address these challenges and demonstrate its performance on simulated data from PTAs with 102 to 103 pulsars. The method estimates and subtracts sources from the data iteratively using multiple stages of refinement, followed by a step that mitigates spurious identified sources by comparing the outputs from two different algorithms. The performance of the method compares favorably with the global fit approaches that have been proposed so far. In all the cases tested in this work, the fraction of sources found by the method that correspond to true sources in the simulated data exceeds 78% and 93% for a large-scale (with 103 pulsars and 200 sources) and a midscale (with 102 pulsars and 100 sources) PTA, respectively. The network signal-to-noise ratio of the recovered true sources reaches down to 16.43 for the large-scale and 9.07 for the midscale PTA.