Project Overview

STELAR is a 3-year Horizon Europe project running from September 2022 to August 2025. STELAR aims to design, develop and evaluate a Knowledge Lake Management System (KLMS) – a platform and set of tools that aim to enable simple and intelligent data discovery, AI-ready data, and semantic interoperability in smart agriculture and food safety applications.

Tackling a Disorganised Data Space in Today’s Agriculture

Data Discovery
Barriers

Finding the right data is challenging - data spaces hold large amounts of data of various types and formats from diverse sources, and with varying quality

Data Interoperability Barriers

Integrating data is challenging - different sources follow different schemas and taxonomies, they refer to domain-specific entities using non-standardized names, and have different spatial or temporal resolutions

Data Annotation
Barriers

Preparing data for Machine Learning is challenging - for data to be AI-ready, annotation and labelling require domain knowledge and expertise, which has a high cost in terms of time and effort of domain experts

STELAR's Path Towards FAIR and AI-ready DATA

ROAD TO DEVELOPING A KNOWLEDGE LAKE MANAGEMENT SYSTEM (KLMS) FIT FOR TODAY’S AGRIFOOD DATA NEEDS

Dr Dimitris Skoutas

Principal Researcher at Athena Research Center
and STELAR Project Coordinator

“Today’s data spaces, such as agrifood, contain large volumes and a variety of data, with varying quality. Data is only as worthwhile as the ease with which it can be used. Users are facing difficulties in meeting their needs due to data stored in different places and forms, as well as subpar dataset search capabilities underusing the revolutionising potential of AI and machine learning. STELAR is developing a system consisting of a platform and set of tools for improved data discovery, linking and annotation, with pilot applications in the agrifood data space.”