SDL AI and ML for Remote Sensing

SDL AI and ML for Remote Sensing

Mission

The Simulation and Data Lab (SDL) Artificial Intelligence (AI) and Machine Learning (ML) for Remote Sensing (RS) leads to increase the visibility on interdisciplinary research between applications from RS and advanced computing technologies and parallel programming. This includes high-performance and distributed computing, quantum computing and specialized hardware computing. The SDL works together with the "Simulation and Data Lab RS" of the Icelandic HPC community (University of Iceland) and the High-performance and Disruptive Computing in Remote Sensing (HDCRS) working group of the Geoscience and Remote Sensing Society (GRSS). Furthermore it collaborates with other international universities in joint activities that include research projects, teaching courses, community support and supervision of students at different academic levels.

Team

Prof. Dr. -Ing. Gabriele Cavallaro

Head of Simulation and Data Lab (SDL) Artificial Intelligence and Machine Learning for Remote Sensing

  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Building 14.14 /
Room 3001
+49 2461/61-3858
  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Building 16.3 /
Room 401
+49 2461/61-1497

Surbhi Sharma

Member of the Division "Federated Systems and Data"

  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Building 14.14 /
Room 3001
+49 2461/61-1502
  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Building 14.14 /
Room 3001
+49 2461/61-1234
  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Building 14.14 /
Room 3001
+49 2461/61-1234

Projects

The SDL is involved in different projects where it conducts co-design work and activities with applications from remote sensing.

Adaptive Multi-Tier Intelligent Data Manager for Exascale (ADMIRE)

The EU project ADMIRE will create an active I/O stack that dynamically adjusts computation and storage requirements through intelligent global coordination, elasticity of computation and I/O, and the scheduling of storage resources along all levels of the storage hierarchy.

Centre of Excellence for Research on AI- and Simulation-Based Engineering at Exascale (CoE RAISE)

The EU project CoE RAISE will be the excellent enabler for the advancement of European multi-physics and/or multi-scale applications on industrial and academic level and a driver for novel intertwined AI and HPC technologies.

European Pilot for Exascale (EUPEX)

The objectives of the EU project EUPEX are: (1) co-design a modular Exascale-pilot system, (2) build and deploy a pilot hardware and software platform integrating European technology, (3) demonstrate the readiness and the scalability of the pilot technology towards Exascale and (4) prepare applications and European users to efficiently exploit the future Exascale machines.

Hybrid Quantum-Classical Processing Workflows in Modular Supercomputing Architectures for Data-Intensive Earth Observation Applications

This project is in collaboration with the Φ-lab at the European Space Agency and it aims at developing hybrid quantum-classical processing workflows with HPC systems and quantum computing for Earth Observation applications.

Last Modified: 21.04.2022