Cloud Segmentation, Denoising, and Compression Techniques for use on Sentinel-3 Satellite Data

Satellite images of the Earth's surface have a multitude of uses. However., this data comes with some inherent issues. One such issue is cloud coverage. We propose the use of image segmentation to identify clouds in images. Another problem is the size of the data., which must be transferred over the satellite's limited connection bandwidth. We propose several compression methods for reducing data size effectively. The data is of varying quality, so the use of noise removal techniques can improve the accuracy and usability of the data.

I. Introduction

There are 6 challenges in the 5th Annual Smoky Mountains Computational Sciences Data Challenge (SMCDC22). We selected Challenge 6: Sentinel-3 Satellite Datasets: OLCI & SLS TR as our REU proj ect. Sentinel- 3 Satellite is a dataset consisting of red-green-blue (RGB) images generated from the Sentinel-3 satellite via the Ocean and Land Color Instrument (OLCI). Using those images, we explored different kinds of methods to realize image segmentation, denoising, and compression.