07-30, 12:50–13:00 (UTC), Red Track
Currently, satellites generate data of the Earth in an unprecedented
amount.
These datasets need to be processed in a fast and user friendly way to
derive comprehensive information. This talk shows how we use the
Earth System Data
Lab to handle Sentinel-1 time
series for the detection of deforestation.
The EarthSystemDataLab.jl allows you to handle geospatial raster data
easily and fast. You can load data which is too large for your RAM
directly from disk in small enough chunks so that it can be
paralllelized without you thinking too much about it.
The EarthSystemDataLab establishs a data cube workflow, where low-
dimensional functions are applied to higher dimensional cubes by
functional extension. This means, that user defined functions can act
along a particular subset of the input dimensions and loop then across
all other input dimensions to get a new data cube which has the
unspecified dimensions as well as the output dimensions of the user
defined function.
We are going to show how we used the EarthSystemDataLab.jl package for
the time series analysis of Sentinel-1 data.
received his diploma in mathematics
from the University of Leipzig in 2014. He is a PhD student at the
Friedrich-Schiller University Jena where he works on the analysis
of hyper-temporal SAR time series from Sentinel-1