GeoPython 2020

With the latest missions launched by ESA or NASA, such as Sentinel or Landsat, equipped with the latest technologies in multispectral sensors, we face an unprecedented amount of satellite data with spatial and temporal resolutions never reached before. Exploring the potential of this data with state-of-the-art Artificial Intelligence techniques such as “Deep Learning" could potentially change the way we understand the Earth system and how to protect its resources.

Supported by the eXtreme-DataCloud project, which aims at developing a scalable environment for data lifecycle management and computing and integrate different services and tools based on Cloud Computing resources to manage Big Data and under the umbrella of H2020 programme, one of the Use Cases in XDC project representing LifeWatch ERIC (the European Research Infrastructure for Ecosystems and Biodiversity) is developing a complete Python package to monitor the water quality of reservoirs and lakes. This complete solution enables data management along its life cycle, from the ingestion from different sources to the analysis and publication.

The python package includes diverse features to define different regions or reservoirs through their coordinates, as well as select other parameters such as the date, the satellite or the cloud coverage in the search for images. Furthermore, this package also enables options such as applying super-resolution or atmospheric corrections to images applying the latest deep learning techniques.

This package is integrated within a user-friendly system based on Jupyter notebooks on a cloud computing environment. Thanks to Docker technology, users access to their private environment with cloud storage and processing orchestration to compute complex analysis, including preprocessing, super-resolution, etc.