Sentinel data and applications at Living Planet Symposium 2019

On the occasion of the Living Planet Symposium 2019, on Sunday 12 May 2019, RUS will provide 3 different half day hands-on training sessions where participants will access a Virtual Machine from their own laptop to exploit the open source toolboxes available in the RUS environment to download and process Sentinel-1, Sentinel-2, Sentinel-3 and Sentinel 5-P data.


Background

This year’s Living Planet Symposium 2019, which is usually held every three years, will take place on 13 - 17 May in Milan, Italy, and will focus on how Earth Observation gives a large contribution to science and society. 

Please note that the SAR and Optical data fusion for land applications training course is full!

RUS Training Courses

Exercise 1: SAR and Optical data fusion for land applications

A wide range of different and complementary data (RADAR, optical, IR) from Sentinel-1,2,3 and now also from Sentinel-5P are nowadays available with an open and free policy. For some applications, such as agriculture, the synergy between these data has been already shown. For several applications, there has been an increasing interest in jointly using both RADAR and optical data to compensate for the limitations of using single data products alone. The combination of the weather and illumination independence and the sensitivity to the size, density, orientation and dielectric properties of SAR sensors together with the multi-spectral information related to the leaf structure, pigmentation and moisture captured by optical sensors can provide greater insight and context in many areas of application.

This half-day tutorial will demonstrate the usage of Open Tools (ESA SNAP; QGIS; R) available within the RUS environment to run a supervised classification over an agricultural area using Sentinel1 GRD and Sentinel-2 products. Participants will be able to choose between two of the most relevant machine learning algorithms used for this purpose: Random Forest and Support Vector Machine (SVM).

A multi-temporal and multi-sensor pixel-based data fusion approach will be used in various scenarios to analyse the influence of different input data in the final classification accuracy. The data fusion will be implemented following two main strategies: fusion at feature level (fusion of images is done before applying the core processing task, e.g. classification) and fusion at decision level (fusion of products generated by the processing of separate sensors/times after applying the core processing task, e.g. classification)

Participants will get familiar with SAR and optical data pre-processing using batch processing in SNAP and its command-line implementation (GPT) as well as using existing R scripts implemented in a Graphical User Interface (GUI) within QGIS. 

Trainers: Miguel Castro, Tereza Smejkalova, Georgia Karadimou | Serco Italia

Duration: 3 - 4 hours

Software: SNAP, QGIS, R 


Exercise 2: Marine applications with Sentinel-3

This half-day hands-on session will illustrate large scale applications dedicated to ocean monitoring with Sentinel-3 level-2 data.

Under the influence of coastal winds, the upwelling phenomenon brings cold and nutrient-rich waters from the bottom of the ocean to the surface. Upwelling areas are of prime interest for economies, human beings living along the coasts and ocean biodiversity as they are the most productive regions of the oceans. Identifying upwelling phenomena is particularly interesting to monitor fishing in these regions. It can also help minimizing interactions between fishing boats and great cetaceans.

The SLSTR, OLCI and SRAL instruments on board Sentinel-3 mission respectively record Sea Surface Temperature (SST), Ocean Colour and Sea Surface Height (SSH). The combined analyses of these three products allow an efficient identification and monitoring of the upwelling phenomenon along different continental coasts of the Earth.

This session will mainly focus on the analysis of Ocean Colour and SST data with open tools SNAP and Panoply. An introduction to the processing of altimetry data with the BRAT Toolbox may be given at the end of the training if there is remaining time.

Trainers: Florian Poustomis | Noveltis

Duration: 3 - 4 hours

Software: SNAP, Panoply and/or BRAT


Exercise 3: Exploiting Sentinel-5P Data

Sentinel-5P is the last launched satellite of the Copernicus Sentinel program. Its main goal is to screen the Earth’s atmosphere and quantify different pollutants (CO, NO$_2$, SO$_2$, O$_3$, aerosols…) with a great accuracy and spatial resolution. It also provides with measurement continuity with precedent and ongoing atmospheric spatial missions (OMI, IASI and SCHIAMACHY).

This half day training will focus on the creation of Level-3 gridded products for a particular type of trace gas and/or aerosol in the atmosphere out of Level-2 Sentinel-5P data with the BEAT Toolbox. The participants will learn to monitor both daily pollution and polluting events based on the created Level-3 gridded products.

The trainees will first get familiar with the structure of S5P products and where the data of interest are according to the study field. Then they will learn how to create a world map of the pollution caused by a particular type of trace gas. They will also learn how to monitor and follow a polluting event thanks to the daily measurement of Sentinel-5P. They will eventually learn how to quantify the pollution in a city during distinct parts of the year.

Trainers: Simon Boitard | Noveltis

Duration: 3 - 4 hours

Software: BEAT Toolbox


Equipment

Attendees must bring their own laptop/mouse and will be provided with access to the RUS platform Virtual Machine.


Cost & Participation

Attendance to the training course is free of charge, however travel and accommodation expenses are excluded.

Confirmation e-mails to selected attendees will be sent by the end of April 2019.

Please note that you may attend only one of the three training sessions. Participation to the course is open to people registered to the Living Planet Symposium 2019 and matching RUS Conditions of use.


Max number of participants

Data fusion on Sentinel-1 and Sentinel-2 

Space is limited to 20 Participants on a first-come first-served basis.

Marine applications with Sentinel-3 

Space is limited to 20 Participants on a first-come first-served basis.

Exploiting Sentinel-5P Data 

Space is limited to 20 Participants on a first-come first-served basis.


Schedule

Data fusion on Sentinel-1 and Sentinel-2 

12 May 2019 →  In between 14:00 and 18:00 (Timetable to be defined)

Marine applications with Sentinel-3 

12 May 2019 →  In between 14:00 and 18:00 (Timetable to be defined)

Exploiting Sentinel-5P Data

12 May 2019 → In between 14:00 and 18:00 (Timetable to be defined)


Venue

MiCo - Milano Congressi

Mi.Co. Gate 2

Viale 20145, Viale Eginardo, 7, 20145 Milano MI ,Italy 

Metrostation: Portello

Training date

Sunday 12th of May 2019

Application opening - closing

Monday 25th of March 2019 - Friday 26th of April 2019
Apply now

Location

Mi.Co. Gate 2
viale 20145, Viale Eginardo, 7, 20145 Milano MI, Italy

Trainers

Florian Poustomis / Noveltis

Georgia Karadimou / Serco Italia S.p.A

Mahmoud El Hajj / Noveltis

Mathilde Cancet / Noveltis

Simon Boitard / Noveltis

Do you want to receive RUS news and new training info?

Subscribe to our mailing list