From Semantic Interoperability towards Data Spaces

From Semantic Interoperability towards Data Spaces

• 1.
  From Semantic Interoperability towards DataSpaces Dr. Raul Palma Head of Data Analytics and Semantics Department Poznan Supercomputing and Networking Center Realising Data Spaces – Purpose, Challenges and Opportunities 28/09/2022
• 2.
  Place Pilot icon Interoperability challenges inAgTech sector Source: Accenture The rapid advances of IoT technologies, AI and Big Data, among others, have boosted the adoption of smart farming practices. This, however, has led to an explosion of data, generated by a wide range of different systems and platforms that rarely interoperate. Some of the key challenges hampering the seamless exchange and integration of the data produced or collected by those systems include: Availability of data in different formats and represented according to different models Insufficient interoperability mechanisms that enable the connection of existing agri-food data models
• 3.
  Place Pilot icon DEMETER functional architecture overview Mechanismsto integrate and deploy solutions the common language to exchange data.
• 4.
  Place Pilot icon DEMETER Agriculture Information Model- AIM AIM follows a modular approach in a layered architecture: realized as a suite of ontologies and associated JSON-LD contexts enabling both the specification of formal semantics, and a simple adoption and implementation by tech providers, plus a set of SHACL shapes enabling validation of data at the semantic level. implemented in line with best practices, reusing existing standards and well-scoped models establishes alignments between base models to enable their interoperability and the integration of existing data AIM aims to establish the basis of a common agricultural data space, enable the interoperation of different systems, and the analysis of data produced by those systems in an integrated manner
• 5.
  Place Pilot icon Layers of the DEMETER Agriculture Information Model(AIM)
• 6.
  Place Pilot icon Types ofdata represented via AIM AIM represents a wide variety of data types that are generic or are specific to the agrifood domain, such as : • Farm data (e.g., field data, field status, soil data, Crops/treatment/fertilisation data, farm input data, energy consumption data, ...) • Earth Observation Data (e.g., satellite data, remote sensing imagery, soil maps, vegetation indices, such as NDVI, EVI, NDRE, NDMI) • Meteorological data (e.g., temperature, humidity, wind speed/direction, solar radiation, pressure, etc.) • Agricultural machinery data (e.g., engine data, fuel consumption, emissions, exhaust gas, NOx- conversion, exhaust temperatures, ...) • Representation of data quality metrics • Field Operations data (irrigation, fertilisation, soil tillage) • Livestock data • Traceability data (transport) • Financial farm data, benchmarking data and KPIs • Farmer information
• 7.
  Place Pilot icon Semantic Interoperabilityvia AIM AIM provides the basis to enable a semantic interoperability data space: it defines the data elements (concepts, properties and relations) relevant to agri applications, including the semantics associated to the information exchanged. AIM establish (semantic) mapping to the various standards/ontologies FIWARE Saref4Agri INSPIRE and FOODIE ADAPT AGROVOC EO standards ISO standards Units Ontologies
• 8.
  Place Pilot icon Reuse large repositoryof Linked Data related to agriculture with over 1 billion triples DEMETER Data Pipelines AIM
• 9.
  Place Pilot icon From common semanticdata models to standard APIs q The semantic data models provide the common language (lingua franca) to represent data, with explicit semantics, so that different components can understand and validate it q The data pipelines allow the harmonization of data according to those models in order to enable an integrated view over different data source q However, different components normally implement different APIs that expose or consume the data q -> need for standardized APIs
• 10.
  Place Pilot icon Key characteristicsof a data space - EU view A secure and privacy-preserving IT infrastructure to pool, access, process, use and share data. A data governance mechanism, comprising a set of admin and contractual rules that determine the rights to access, process, use and share data in a trustful, transparent manner and in compliance with existing legislation. Data holders are in control of who can have access to their data, for which purpose and under which conditions it can be used. Presence of (vast amounts of) data that are made available on a voluntary basis and that can be reused against remuneration or for free, depending on the data holder’s decision. Participation by an open number of organisations/ individuals in full respect of competition rules and ensuring non-discriminatory access for all participants Doris Marquardt, AGRI/F2 Joël Bacquet, CNECT/E4 6 September 2022 IT infrastructrue data governance access control big data open participation
• 11.
  Place Pilot icon Leveraging previous experiencesto build data space for agriculture Doris Marquardt, AGRI/F2 Joël Bacquet, CNECT/E4 6 September 2022
• 12.
  Place Pilot icon Preparatory actions forData Spaces - Agriculture Data Space Step 1: Preparatory action: Co-ordination and Support Action (CSA) à selected proposal for agriculture: AgriDataSpace - start 1st October 2022. • Expected outcomes: • Inventory of existing platforms • Proposed design approach based on scenarios • Governance scheme • Blue-print for the data space • Interim results used for the development of the implementation action • Input to the work of the data space support centre Step 2: First implementation project à Call in 2024
• 13.
  Place Pilot icon AgriDataSpace q Understandingand mapping the data sharing landscape (e.g., European Code of Conduct) q Develop building blocks for profitable and responsible data space in agriculture (governance models, business models, legislative framework) q Develop a conceptual reference architecture for a common data space framework iand a reference technology canvas q analyse existing data models, vocabularies (e.g., AIM) q look into the best data interoperability solutions (technical & API, semantic etc.) q Engage stakeholders in various activities for evaluation and validation q Develop a roadmap towards implementation of the EU Agriculture Data Space
• 14.
  Place Pilot icon AgriDataSpace
• 15.
  Place Pilot icon All Datafor Green Deal (AD4GD) Aims to co-create and shape the EU Green Deal Data Space as an open hub for FAIR data and standards- based services that support the key EU priorities Main focus on interoperability concepts that bridge the semantic and technology gaps Enable the combination and integration of data from different sources Demonstrate and validate the approach in three pilots, involving intl. organizations, scientists and researchers, citizens, decision makers and solution providers Building blocks for Data Spaces, IDSA
• 16.
  For more informationvisit: www.h2020-demeter.eu or Email us at: info@h2020-demeter.eu rpalma@man.poznan.pl