• Akanksha Thakur
• Satish pawar

Both image creation and picture aesthetic translation have been accomplished using Generative Adversarial Networks (GAN). The Generative Adversarial Networks may possibly to be one of the most prominent AI algorithms One of the most notable achievements in the present improvement has been the introduction of GAN, an AI technology that makes computers creative of AI, which can build AI application new resourceful and powerful. Generative adversarial networks, or GANs, are a revolutionary way for putting computers against each other that shows promise for enhancing AI accuracy and automatically designing products that traditionally need human ingenuity. A GAN is a machine learning (ML) model that pits two neural networks against each other to improve prediction accuracy. In this study, we suggest utilizing the Generative Adversarial Network (GANs) approach to improve and eliminate noise from satellite photos. We use the GAN training process, which is purposefully progressive, for picture production. Sentinel-2 is an open-source earth-observation satellite. It provides multi spectral data with excellent time resolution (13 bands) and spatial resolution of 10m. The goal of this work is to use GANs to analyze and noise-free satellite images.

Real world image de-noising, Generative Adversarial Network Method, Image de-noising, Machine learning, Satellite Images.

"REVIEW OF IMAGE DENOISING USING THE GENERATIVE ADVERSARIAL NETWORKS (GAN) METHOD FOR SATELLITE IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.a765-a781, June-2022, Available :http://www.jetir.org/papers/JETIR2206090.pdf

"REVIEW OF IMAGE DENOISING USING THE GENERATIVE ADVERSARIAL NETWORKS (GAN) METHOD FOR SATELLITE IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppa765-a781, June-2022, Available at : http://www.jetir.org/papers/JETIR2206090.pdf