SEBASTIAN FÖRTSCH
Applied Earth Observation

Human kind is facing an unprecedented Global Change. We seem to have a not inconsiderable influence on this state and we already know what we can do to mitigate the possible consequences. We are just beginning to understand, if, how and the extend to which these consequences are connected to the Global Change. It is not possible to know all details and there could be a need to adapt to new situations in shorter time steps. Earth Observation (EO) Data, especially satellite data, has a great potential to support us during this process. With the first Landsat satellite, launched in 1972, a new era of EO started. By now the 9th Landsat generation acquires data in the order of a few TB per day. All this data is publicly available. 
The next game changer is ESA's Copernicus program. Different recievers, sensitive to wavelengths between optical light and radar are mounted on different Sentinel satellites allowing for spatial resolutions between 9 m - 68 km and time resolutions (orbital repetition rate) of 1 h - 10 days. All the acquired data is subject to open data policies. Datacubes are common tools for storing and analyzing data, also for EO data today. The Open Data Cube (ODC) python library is an open source tool to manage satellite data and geospatial data. The aim is to lower the obstacles working with the data. This talk will give an overview covering essential parts from downloading satellite data to applying machine learning models in the context of land cover classification on this data,. The focus will be on the Copernicus mission maintained by the European Space Agency.