Satellite Imagery Noising With Generative Adversarial Networks

Using satellite imagery and remote sensing data for supervised self-supervised learning problems can be quite challenging when parts of the underlying datasets are missing due to natural phenomena (clouds, fog, haze, mist, etc.). Solving this problem will improve augmentation make use it in a world where represents great resource exploit any big pipeline setup. In paper, authors present generative adversarial network (GANs) model that generate atmospheric noise serves as preprocessing tool produce input machine algorithms.