Figure 2From: CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial NetworksPixel intensity distribution of 1000 generated maps (red circles) compared to those of 1000 validation maps (black squares). The GAN is able to emulate the distribution of intensities in the maps. The Kolmogorov–Smirnov test of similarity of these distributions yields a p-value >0.999Back to article page