This document is a deliverable of the SEDIMARK project, funded by the European Commission under its Horizon Europe Framework Programme. This document presents the “D6.4 Dissemination and Impact creation activities. Final version” deliverable, including all the carried out activities, communications and dissemination material, along with the final status of the Key Performance Indicators (KPIs) for such activities. Besides, it also includes the efforts that have been made for the cooperation with other projects and associations. Special emphasis will be put into the dissemination and communication activities carried out during the last eighteen months of the project, as previous actions were already reported on SEDIMARK_D6.3. The target audience for this document is manyfold, including the scientific community that will find a compendium of dissemination activities from where they can get into the project’s main outcomes or the EC to assess the impact raising activities that the project has executed.
During the project lifetime, a number of dissemination and communication activities have been carried out, reaching a large audience of variable types, including users, citizens, other research projects and the scientific community. These events span across online webinars to large exhibition venues, such as the Smart City Expo or IEEE CSCN 2025 conference. Besides, project members have participated to several cooperation activities, including workshops and panel discussion, so as to explore future means of collaboration. This includes the participation in Working Groups and different association events, such as the Data Spaces Support Centre (DSSC) Technical Working Group, the International Data Spaces Association (IDSA) or the Big Data Value Association (BDVA), as well as becoming members of important clusters, such as the ICT4WATER initiative. Finally, during the project, and mainly on the second half of it, which is the main focus for this deliverable, the scientific communication and dissemination has benefitted from the outcomes and results obtained within the technical activities, submitting and publishing several papers in conferences and journals.
It is worth highlighting that the online presence of SEDIMARK has been pushed forward, following a collaborative dissemination plan among all the partners, leading to the creation of multiple articles, multimedia content and social media posts to engage with the general public and disseminate project results. Furthermore, different dissemination materials have been produced, including brochures, videos and leaflets, facilitating the dissemination of the project at online and offline events.
Last but not least, hackathon activity has been organised in order to open the tools and services developed in the project to external participants so that it is possible to get valuable insights and feedback about the usability and evaluation of the SEDIMARK Marketplace, as well as better understanding the demands from those that might make use of the integrated project results.
D6.4 deliverable can be downloaded from here.
This document corresponds to the Deliverable D4.6 of the SEDIMARK project, named “Data sharing platform and incentives – Final version”. Its goal is to describe the SEDIMARK marketplace, a web frontend application constituting the entry point for users to the SEDIMARK ecosystem and all the functionalities it offers. It updates a previous Deliverable, SEDIMARK_D4.5 “Data sharing platform and incentives – First version”, submitted in December 2023, which described the Marketplace in an early development stage. This final version provides an up-to-date description of it, focusing on how users can navigate the web interface to access all features of SEDIMARK.
This document revolving around the graphical user interfaces of the SEDIMARK platform, it complements Deliverables SEDIMARK_D4.2 “Decentralized Infrastructure and Access Management - Final version” and SEDIMARK_D4.4 “Edge data processing and service certification – Final version”, which explain in greater details how the functionalities exposed in these interfaces actually work internally.
D4.6 deliverable can be downloaded from here.
In response to the growing demand for secure and transparent data exchange, the infrastructure of SEDIMARK Marketplace leverages cutting-edge technologies to establish a resilient network.
The decentralization approach ensures increased security, transparency, and user-centric control both over different types of assets and user identity information. The SEDIMARK Marketplace leverages distributed ledger technologies to establish a resilient and scalable infrastructure. The decentralized architecture of the marketplace is built on a robust distributed ledger employed for user identity management, as well as blockchain foundation, fostering tamper-resistant contracts.
This deliverable presents the final version of the Decentralized Infrastructure employed for the SEDIMARK Marketplace and the APIs that enable the functionalities satisfying the requirements and the objectives for the Project. It represents an important capstone for every stakeholder that plans to use the Marketplace for offering assets and consuming data and services. Here, after a careful examination and design process across all the partners of the project, the final version of the SEDIMARK Marketplace is shaped and consolidated. This document stems from the previous capstone realized with Deliverable SEDIMARK_D4.1 and Deliverable SEDIMARK_D3.4 in December 2023. The current deliverable builds upon the previous version, extending its scope and functionality. This document highlights the key differences, changes, and additions made since the last iteration, providing a clear overview of the enhancements and improvements implemented in this version. Additionally, each section of the current deliverable includes context and rationale for the updates, ensuring a comprehensive understanding of the project's evolution.
D4.2 deliverable can be downloaded from here.
On September the 15th the Special Session on “Technologies for trustworthy sharing of enriched and interoperable data in IoT-based data spaces”, organized by the SEDIMARK project, has been held as part of the during the IEEE Conference on Standards for Communications and Networking (held in Bologna, Italy).
The Special Session aimed to bring together experts in the areas of data management, data sharing, IoT, trust and machine learning and provide a floor for discussions on how various technologies (e.g. machine learning, artificial intelligence, semantics, DLTs, etc.) can help towards automating and improving the management, curation, enrichment, interoperability and sharing of data in IoT-based data spaces.
Four papers were accepted after thorough review from a panel of more than twenty experts who provided their reviews over the nine manuscripts that were submitted. The four papers, titled "Towards Efficient Structured Description Generation for Data Marketplace Offerings", "A Decentralised DLT-based Offering Management and Asset Sharing Framework for Data Marketplaces", "Optimizing Deep Learning for Edge Deployment via Weight Statistics Aware Network Pruning", and "Quantifying Energy-Accuracy-Latency Trade-offs in Cloud-Offloaded and On-Device TinyML Inference on IoT Devices", were presented by Dr. Tarek Elsaleh (from University of Surrey, UK), Mr. Victor González (from Universidad de Cantabria, Spain), Miss Sneha Hanumanthaiah (from University of Surrey, UK) and Dr. Horia Alexandru Modran (from Transilvania University of Brasov, Romania) respectively.
This session has been an excellent opportunity to present some of the key results from the project as the papers presented were all describing some of the latest results and outcomes from the project. More than 20 people attended the session where a lively discussion (e.g. on integration with other frameworks like TM Forum APIs, or on availability of the datasets used for AI-enabled data processing techniques presented) was established both at the questions and answers time after each paper presentation and at the end of the session when an open discussion was organized by the session chair.
During the next 23rd to 25th September 2025, the SEDIMARK: Data4Mobility Hackathon will take place in Santander, at the “Centro de Iniciativas Empresariales" (CIE).
Registration is open until noon 23rd September. Go and visit the following link to register yourself to this big opportunity:
As part of the SEDIMARK project, in which Santander City Council and the University of Cantabria are participating, a hackathon will be held inviting developers, designers, urban planners and data experts to explore the future of sustainable mobility in cities through the power of data. Participants will have access to the tools developed by the project to share real-world urban data and datasets, and they will be able to discover how the exchange of reliable data through the SEDIMARK Data Marketplace can drive innovation in mobility, the environment and urban planning.
The initiative has been organized to be ideal for developers, data scientists, researchers, and anyone interested in smart cities, sustainability, mobility, advanced data ecosystems, or SEDIMARK Data Market technologies. However, it will be open to anyone who were curious about exploring data applications and wants to develop innovative ideas using data as a foundation. The main objective for the SEDIMARK Data4Mobility Hackathon is to revolve around the data catalogues available in the Data Marketplace developed in the SEDIMARK project. These include real urban datasets related to sustainable mobility, places of interest in cities, traffic flows and air quality, not only in the city of Santander but also in other Spanish and European cities. Participants have had the opportunity to experiment with static and real-time data to jointly create services and ideas for smarter and more sustainable urban mobility.
Hackathon’s participants will be using the tools developed in the SEDIMARK project to search for and obtain the datasets available in the Data Marketplace that has been built as part of the project.
Technical training, documentation and details about the available datasets will be provided to participants at the beginning of the hackathon, examples from these datasets are:
In addition, during the hackathon, a team of developers from the SEDIMARK project will be available to answer questions and provide support to participants in all matters relating to the use of the tools and datasets of the SEDIMARK Data Marketplace, both on site and through telematic channels that will be made available for this purpose.
All the details can be found at the following document.
Last month we hosted our webinar: “Introduction to the SEDIMARK Toolbox”, bringing together stakeholders from research, industry, and policy to explore how secure, interoperable data marketplaces can be built on top of the Data Space concept.
💡 Highlights from the session:
An overview of the SEDIMARK platform and its role in enabling secure, privacy-preserving, and efficient data exchange.
A live demo using the water use-case to showcase our data/ML pipelines in action.
Engaging Q&A and open discussions on edge performance, decentralized architectures, and federated learning.
🙏 Special thanks to all attendees for your insightful questions and to our partners for their collaboration.
📬 Stay tuned for upcoming webinars and project updates — subscribe to our newsletter here: https://sedimark.eu/newsletter/
#DataSpaces #DataMarketplace #Interoperability #AI #Webinar #DigitalEurope
This report details the final architecture and tools developed within the SEDIMARK project for edge processing and services certification. The work focuses on providing the foundational components for managing the entire lifecycle of data and AI assets, from their creation and processing at the edge to their certification and exchange in the marketplace. The key contributions establish a framework for AI-driven modules that can be deployed at the data source, adhering to MLOps principles while managing complex edge-cloud interactions.
A primary achievement of this work is the development of an edge processing framework designed for resource-constrained environments. Key innovations include:
To address the challenges of managing AI models in a diverse ecosystem, the project has established a comprehensive MLOps strategy and a solution for model interoperability. By adopting MLFlow, SEDIMARK provides a standardized framework for the entire machine learning lifecycle. A critical innovation is the use of Keras Core to create framework-agnostic model descriptions. This allows models to be defined once and then seamlessly trained or used for inference across different backends like TensorFlow, PyTorch, and JAX, which is essential for fostering collaboration in federated learning scenarios where participants may use different tools.
Finally, to build a foundation of trust within the marketplace, a multi-faceted conformity evaluation Service has been designed. This service provides validation for all marketplace assets:
Together, these advancements in edge computing, MLOps, and certification provide the core technical infrastructure for a robust, transparent, and efficient decentralized data marketplace.
Deliverable D4.4 can be downloaded from here.
This report presents the design and implementation of the core technical enablers for the SEcure Decentralised Intelligent Data MARKetplace (SEDIMARK) platform. The project aims to address the limitations of centralized data markets by fostering a secure, trusted, and intelligent ecosystem based on Distributed Ledger Technology (DLT) and Artificial Intelligence (AI). The work detailed in this document establishes the foundational components for interoperability, AI-driven services, DLT-based trust, and distributed storage, advancing the platform from a Technology Readiness Level (TRL) of 5 toward demonstration in real-world scenarios.
A key contribution of this work is a comprehensive interoperability framework. At its core, the framework uses the NGSI-LD specification to create a common semantic language for data assets. This is supplemented by a Marketplace Information Model, which defines crucial marketplace concepts such as Self-Description, Offering, and Asset. This model builds upon existing standards like DCAT and ODRL by introducing the "Offering" concept, which allows multiple diverse assets—such as datasets, AI models, and services—to be bundled and transacted together. A suite of software components within the Interoperability Enabler handles data formatting, curation, quality annotation, and validation to ensure data adheres to FAIR principles.
The platform's intelligence is powered by a multifaceted AI Enabler. This component supports advanced local model training with techniques like the transformer-based CrossFormer for multivariate time-series forecasting and model optimization methods like pruning. For collaborative scenarios, the project introduces two frameworks for distributed training: deFLight, a dynamic and fully decentralized framework supporting gossip and federated learning, and Fleviden, a tool for orchestrating complex federated workflows. A significant innovation is the Offering Generator, which uses Large Language Models (LLMs) to automatically create standards-compliant, semantically rich marketplace offerings from unstructured metadata, lowering the barrier to entry for data providers.
Trust and security are ensured by a DLT infrastructure built on a private instance of the IOTA Tangle (Layer 1) and IOTA Smart Contracts (Layer 2). This two-layer architecture provides a non-repudiable ledger for managing participant identities, cataloguing offering metadata, and facilitating secure asset trading. To support the platform's digital assets, a robust Storage Enabler provides a distributed architecture using Minio for AI model storage and NGSI-LD brokers for scalable, interoperable storage of linked data.
D3.4 deliverable can be downloaded from here.
We recently held a hands-on, hybrid technical meeting in Paris dedicated to refining and optimizing the data and machine learning pipelines in SEDIMARK. The session brought together team members on-site and online to work through practical implementation details, address technical challenges, and identify improvements to enhance efficiency, interoperability, and security across the platform.
