SUMMER SCHOOL: AI technologies for processing multi-source Earth Observation (EO) data

Join us for a 3-day summer school hosted by LIST, featuring top international experts delving into cutting-edge AI technologies for processing multi-source Earth Observation (EO) data.

In recent years, Earth Observation satellite systems have become increasingly accessible, opening up a wealth of opportunities for addressing pressing global issues like climate change and enhancing our understanding of our planet's complexities.

With the development of satellite constellations equipped with advanced sensors, Earth monitoring has become more frequent, precise, and detailed than ever before. The data captured by these satellites offer vast potential for various applications, thanks to their wide range of measurement frequencies and spatial resolutions reaching up to tens of centimeters.

However, simply having access to vast amounts of data isn't enough; it's crucial to translate this data into actionable insights that can drive meaningful societal change. Machine learning and deep learning techniques are instrumental in efficiently analyzing large datasets and uncovering new insights across various application domains.

Don't miss out on this opportunity to learn from experts and explore the transformative potential of AI in Earth Observation

*upon request Summer School participant will benefit from a special price to attend the LEO DAY conference.

Objectives

The objective of this summer school is to offer valuable insights into the application of machine learning and deep learning techniques for interpreting Earth Observation (EO) data.

The program comprises a series of theoretical lectures delving into the principles behind cutting-edge deep learning approaches, alongside practical sessions featuring use cases that highlight their potential and potential limitations within specific applications.

Hands-on workshops will provide practical guidance on setting up and deploying various machine learning models. Ultimately, the aim is to bridge the gap between deep learning methodologies and EO data challenges, optimizing the utilization of both technologies. Participants will benefit from the expertise of instructors spanning machine learning, deep learning, and EO domains.

Programme

TIMING TOPIC
DAY 1 | 10 June 2024
Afternoon session
14:00-17:00 Dr Marco CHINI, Lead Research and Technology Associate, Environment Dept, LIST
Introduction to Earth Observation data (SAR, Optical)
Deep Learning and Earth Observation to support:
o Floodwater mapping at large scale
o Natural disasters monitoring
DAY 2 | 11 June 2024
Morning session
9:00-12:00 Prof. Claudio Persello, Associate Professor, University of Twente
- Introduction to Machine Learning concepts
- Deep learning: principle and architectures
- Convolutional Neural Networks for various image analysis tasks
Afternoon session
14:00-17:00 Prof. Claudio Persello, Associate Professor, University of Twente
Deep Learning and Earth Observation to support:
o Mapping smallholder farms
o Automated extraction of cadastral boundaries 
o Mapping slums and deprived urban areas
o Extraction of geometric building information
o Large-scale glacier mapping
DAY 3 | 12 June 2024
Morning session
9:00-12:00 Prof. Paolo Gamba, Prof. of Telecommunications and Remote Sensing, University of Pavia
Deep Learning and Earth Observation to support:
o Unsupervised clustering for the fusion of heterogeneous sensors for change detection in urban areas
o Deep learning for 2D/3D change using VHR SAR sequences and semantic recognition of the temporal change pattern
Afternoon session
14:00-17:00 Dr. Yu Li, Research and Technology Associate, Environment Dept, LIST
Hands-on session: setting up and implementing ML models

 

Share this page:

Practical Infos

Dates: 10-11-12 June 2024

Location: Youth Hostel Luxembourg city | 2, rue du Fort Olisy L-2261 Luxembourg

Pricing: Standard 230 € HT | Student 200 € HT (Student card will be requested)

Applications:

Motivation letter and CV

To: event@list.lu

Deadline: 10 May 2024.

 

Contact

 Marco CHINI
Marco CHINI
Send an e-mail