PROBA-V MEP takes it one step further with the Notebooks

By Jeroen Dries 10 April 2017

Have you ever read a paper showing nice graphs, without giving a clear explanation on how they were produced? Or do you want to share your code and results with your colleagues easily? And are you frustrated when it take days to rerun your code? Then we are happy to introduce the new Notebooks web application of PROBA-V MEP.

It offers a solution for all these problems, because it combines a browser based interactive programming environment with the power of our Hadoop processing cluster, connected to the full PROBA-V data archive.

A notebook application tailored for remote sensing users

The PROBA-V MEP (Mission Exploitation Platform) Notebooks web application lets you create and share documents that contain live code, equations, visualizations and explanatory text. It is based on the Open Source Jupyter notebooks application, and tailored to the needs of remote sensing users.
For programming, you can choose between the Python and R programming languages. We also include an ever growing list of software libraries such as GDAL, rasterio, pandas, numpy, matplotlib and seaborn so you can start immediately. It is even possible to install and upload your own packages and files. Check out some examples to get a better idea of what you can achieve.


Connecting valuable EO data with powerful processing power

But what makes this new application so special? It is the direct and easy access to the complete PROBA-V and SPOT-VGT archive, representing over 18 years of continuous  EO data. In order to make sure this remains an ‘interactive’ experience, we have added processing power: more than 1500 processing cores, combined with more than 4TB of memory, in the form of a Spark based processing cluster.
Everyone who wants to do research or develop applications with the PROBA-V and SPOT-VGT data can use this application free of charge.

Let’s get you started

To get you started, we’ve created a few examples that are available in a public repository and inside your personal Notebook environment once you’ve logged on. All the examples are well documented, so don’t hesitate to dive in and run them yourself if you’re interested.
Our sample gallery gives an overview, with the most important concepts used in each sample.
The highlights include: a quick start sample, doing distributed in a few lines of code,  another one uses the Spark machine learning library to train a classifier to detect snow in PROBA-V images, and finally, we analysed trends in the time series data used in our TSViewer app, which came up with some nice results!
Click here to register and get started with the new PROBA-V MEP Notebook application. 

MEP Notebooks, ready for your experiments

With the PROBA-V MEP Notebooks we bring the processing power to the EO data, and it’s available for your experiments for free. We are sure that this will stimulate innovation, and will result in valuable new insights in areas such as climate change, food security, etc. 


Like this article? Share it on
Jeroen Dries
An article by
Jeroen Dries
Senior R&D Professional / IT Architect
More info about Jeroen Dries

Related posts

Validation of iCOR for Sentinel-3 over land surfaces and new SNAP plug-ins
  • Image Processing ,
  • atmospheric correction ,
  • iCOR ,
  • Sentinel-3 ,
  • SNAP

Validation of iCOR for Sentinel-3 over land surfaces and new SNAP plug-ins

By Erwin Wolters 10.05.2021

After releasing the iCOR plug-in for Sentinel-3 Ocean and Land Colour Imager (iCOR4S3) in 2019, a thorough validation was performed using among others the..

Lees meer
Automated Service Builder on Proba-V MEP
  • PROBA-V ,
  • MEP

Automated Service Builder on Proba-V MEP

By Jeroen Dries 18.12.2020

For the last 1.5 years, we have been working on a proof of concept to simplify running your algorithms on our 100+ node cluster, and more easily share..

Lees meer
Annual 100 m land cover maps on a global scale!
  • Land use ,
  • PROBA-V ,
  • Copernicus ,
  • vegetation

Annual 100 m land cover maps on a global scale!

By Marcel Buchhorn 09.09.2020
At the beginning of 2020, we already showed you how we use PROBA-V observations to map annual land cover changes. After sharing these promising annual..
Lees meer