Repository: https://github.com/VITObelgium/notebook-samples

Inside the notebook environment (notebooks.vgt.vito.be), these samples can be found under ~/Private/notebook-samples. You may want to run 'git pull' inside this directory to get the latest versions.

Quick start sample

Finds PROBA-V products and computes a histogram using the processing cluster.

https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/probav/QuickstartExample.ipynb

Keywords: catalog query, Spark, Python, histogram, matplotlib

 

R quick start

Users of the R programming language can use this sample to get started quickly with finding and reading PROBA-V data from inside their notebook or VM.

https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/probav/Reading%20PROBA-V%20using%20R.ipynb

Keywords: catalog query, raster, R

Time series analysis (cal/val)

  Uses MEP web services to retrieve time series from various products for a given point coordinate.

 https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/CalVal%20WCS%20Timeseries.ipynb

https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/probav/AERONET%20CalVal%20TSViewer.ipynb

Keywords: Time series, REST, WCS, calibration, validation

Time Lapses

Create time lapses using our data client library!

 

 

http://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/sentinel2/DataClient-Timelapse.ipynb

Keywords: Time series, Time lapse, Sentinel 2, Proba-V

Snow classification

Trains a machine learning classifier to classify snow pixels based on PROBA-V radiometry.

 

 

https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/probav/SnowDetection.ipynb

Keywords: Spark, Machine learning, Python, Seaborn, graphs, plotting

 

Trend analysis

  Takes all timeseries from the time series viewer application, and runs a naïve trend detection algorithm on them using Spark. This simple approach   gives  some nice results.

 

 

https://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/tools/timeseries/Trend%20Analysis.ipynb

 Keywords: SparkSQL, time series, Python, plotting, maps, pandas

BioPhysical parameters with Sentinel Toolbox Python bindings

Computes BioPhysical parameters using Sentinel 2 reflectance data. Nice demonstration on how snappy can be used and configured inside a notebook, and how it integrates with Python libraries.

http://nbviewer.jupyter.org/github/VITObelgium/notebook-samples/raw/master/datasets/sentinel2/Snappy-BioPhysical.ipynb

Keywords: Python, Snappy, BioPhysical parameters, Sentinel-2, plotting, numpy