Final Year Project

Project Title

Satellite-to-Satellite Image Translation

Description

Only a handful of satellites capture images for public use and are free to access. Among these, the available satellite data comes from a range of satellites, each having different sensors and optics. This creates a data sparsity problem, as the frequency of incoming relevant data ranges from 5 -16 days. This project aims to solve this problem by creating a machine learning algorithm that translates between Landsat-8 and Sentinel-2 to create a larger image dataset. Such satellite datasets can be used for a variety of purposes such as Agriculture (e.g., crop yield prediction), Asset Management (e.g., tracking construction work), Risk Assessment (e.g., flood detection) and Tracking Climate Change (e.g., wildfires & urbanization).