Welcome to the InfoSci Platform
Reference Hub2
Satellite Imagery Noising With Generative Adversarial Networks

Satellite Imagery Noising With Generative Adversarial Networks

Mohamed Akram Zaytar, Chaker El Amrani
Copyright: © 2021 |Volume: 15 |Issue: 1 |Pages: 10
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859826|DOI: 10.4018/IJCINI.2021010102
Cite Article Cite Article

MLA

Zaytar, Mohamed Akram, and Chaker El Amrani. "Satellite Imagery Noising With Generative Adversarial Networks." IJCINI vol.15, no.1 2021: pp.16-25. http://doi.org/10.4018/IJCINI.2021010102

APA

Zaytar, M. A. & El Amrani, C. (2021). Satellite Imagery Noising With Generative Adversarial Networks. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(1), 16-25. http://doi.org/10.4018/IJCINI.2021010102

Chicago

Zaytar, Mohamed Akram, and Chaker El Amrani. "Satellite Imagery Noising With Generative Adversarial Networks," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.1: 16-25. http://doi.org/10.4018/IJCINI.2021010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Using satellite imagery and remote sensing data for supervised and 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 remote sensing data augmentation and make use of it in a world where satellite imagery represents a great resource to exploit in any big data pipeline setup. In this paper, the authors present a generative adversarial network (GANs) model that can generate natural atmospheric noise that serves as a data augmentation preprocessing tool to produce input to supervised machine learning algorithms.