Satellite imagery super-resolution with the DEEP Hybrid DataCloud

With the data adquired by the European Space Agency (ESA) satellites, such as Sentinel, equipped with the latest technologies in multi-spectral sensors, we face an unprecedented amount of data with spatial and temporal resolutions never reached before. Exploring the potential of this data with state-of-the-art Machine Learning techniques like Deep Learning, could potentially change the way we think about and protect our planet's resources. For this purpose we have integrated a super-resolution application from [Lanaras et al. 2018] to the DEEP Hybrid DataCloud Open Catalog [DEEP Catalog], to upscale low resolution (60m and 20m) bands from the Sentinel-2 satellite to full 10m resolution. In this way we hope to allow scientists with no machine learning background to use this service in an easy and transparent manner, without meddling with the code or the underlying ressources. We also hope to demontrate to potential users with this example how easy it is to integrate existing external code with our framework.