The conference will be preceded by a 2-day summer school on 23 and 24 May 2023 with international lecturers providing an advanced training on latest AI-based technologies for processing multi source EO data, thereby enabling, for example, successful applications in precision agriculture and disaster management. Both PhD students and postdoctoral researchers are invited to apply for the training which will take place in the premises of the Luxembourg Institute of Science and Technology (41 rue du Brill – L-4422 Belvaux, Luxembourg).
Please apply by sending a motivation letter and a CV to firstname.lastname@example.org prior to 15 March 2023.
The candidates will receive a notification by 30 March 2023.
The availability of Earth Observation satellite systems has increased significantly in the last two decades, opening up a myriad of opportunities to respond to the challenges that our society is facing today, e.g. climate change, and to better understand our planet. Satellite constellations equipped with advanced and diversified sensors continue to be developed and already have the capacity to monitor the Earth more frequently, more precisely and with a higher level of detail than ever before. The data that these satellites record enable a multitude of applications due to a large spectrum of measurement frequencies, reaching spatial resolutions of up to tens of centimetres with an unprecedented sampling rate. It goes without saying that the availability of a large amount of data does not have any value per se, rather, there is a need to transform the data into understandable and quantitative estimates that have the potential to become game changers for our society. In this respect, machine-learning and deep-learning approaches can play an important role as they allow large data sets to be explored efficiently and new insights to be brought to many application fields.
Thus, the aim of this summer school is to provide useful information on the use of machine-learning and deep-learning approaches for interpreting and understanding Earth Observation (EO) data. The summer school is composed of an ensemble of theoretical lectures on state-of-the-art deep-learning approaches, as well as practical use cases sessions showing their potential and possible limitations when applied to specific applications. Hands-on sessions give practical information on how to set up and implement specific machine-learning models. The final goal is to bring the deep learning methodologies closer to the EO data problem and make a better use of both technologies. Participants will also be able to take advantage of the expertise of lecturers from the machine-learning, deep-learning and EO domains.
09.00 – 12.00 – Dr Benjamin PALMAERTS (ISSeP, Belgium)
14.00-17.00 – Dr Marco Chini (LIST, Luxembourg), Dr Yu Li (LIST, Luxembourg)
o Mapping of urban areas
o Floodwater mapping at a large scale
09.00-12.00 – Prof. Devis Tuia (EPFL, Switzerland)
14.00 – 17.00 – Prof. Claudio Persello (University of Twente, The Netherlands)
This school is intended for PhD students, engineers, and scientists that already have basic knowledge in the analysis of remote-sensing data.
Participants shall bring their own laptops to carry out the exercises.
For the summer school, the participation fees per person exclude VAT (VAT 3%).
The registration fee includes access to the summer school, the lunchs, coffee and refreshments.
Invoicing in case of non-participation:
LIST must be informed of all absences/cancellations in writing as soon as possible by sending a mail to email@example.com. In the absence of different specific conditions, all cancellations are free up to 14 days before the event. All cancellations made after this deadline shall result in the payment of a sum calculated in the following way:
|Number of days before the event||Fees payable by the client|
|14-5||50% of the registration fee|
|4-1||80% of the registration fee|