DaFAB AI Project

Co-Design of innovative services (hierarchical extraction of features) and advanced BD/AI technologies (novel hardware processing technique) to serve a large range of applications in their exploitation of Copernicus & associated databases and help them to evolve towards the edge/cloud/HPC computing continuum

Objective 1

Advanced AI techniques for feature extraction from Copernicus Images

Objective 2

Upbring and Optimising Semantic Interlinking of Copernicus Metadata

Objective 3

Provide a Unified and Searchable Catalog of Interlinked Earth Observation Metadata

Objective 4

Optimize Federated Workflow Execution Across Multiple Data Silos

Objective 5

Co-Design of Pilot Products and Services

Objective 6

Accelerate the competitiveness of the EU-Space ecosystem via upstreaming to open-source projects, communicating and disseminating DaFab’s results to industry, academia, and standardization bodies.

Recent News & Events

Recent News & Events

Read more

Harnessing the Power of Rucio for the DaFab Project: A Leap Towards Advanced Metadata Management

By Dimitris Xenakis, Martin Barisits on July 1, 2024

Introduction In the realm of both scientific research and production environments, efficiently managing and utilizing metadata is crucial. Metadata serves as the backbone for data discovery, organization, and retrieval, enabling effective data usage across various fields. This is particularly important in areas like Earth Observation (EO), where vast amounts of satellite data need to be processed and analysed to monitor and understand our planet. The DaFab project, an ambitious initiative, aims to enhance the exploitation of Copernicus data through advanced AI and High-Performance Computing (HPC) technologies.

Continue reading

Read more

Orchestration of Workflows in converged Cloud and HPC environments

By Georgios Saloustros on June 25, 2024

Multi-Site Workflow Orchestration in the DAFAB Project DAFAB will design and implement a workflow orchestration system that enhances multi-site application deployment and data discovery. The workflow system will enable applications to express their computations as a graph and declare the data needed at each step in a high-level query language. Workflows will then execute across multiple sites, whether cloud-based (Kubernetes) or high-performance computing (Slurm) environments. By enabling transparent data access and seamless execution of workflow stages, this system shifts the burden of application deployment and data discovery to the platform itself, significantly accelerating development timelines.

Continue reading

Read more

Job offer at CERN

on March 7, 2024

CERN is offering a position in the Rucio development team at CERN. Rucio is an open-source scientific data management system responsible to manage the data of some of the biggest scientific data producers in the world. Experiments such as ATLAS, CMS, Belle II, DUNE, and many others rely on Rucio, which manages world-wide distributed data in the exa-byte range. More information at: https://jobs.smartrecruiters.com/CERN/743999972065373-software-engineer-in-distributed-systems-ep-adp-co-2024-34-grap

Continue reading

Read more

Job offer at JSI

on March 6, 2024

JSI is looking for a talented and motivated Software Engineer is sought to join the team and contribute to cutting-edge projects in the field of particle physics and Earth observation data processing. The successful candidate will play a crucial role in developing and optimizing neural network architectures, such as Spike Neural Networks (SNNs), for non Von-Neumann computing platforms, as outlined in our recent project, while also contributing to other aspects of our research and development efforts.

Continue reading