The digital transformation of agriculture is no longer limited to collecting information from sensors, machinery, satellites, weather services and farm management systems. The real challenge is to transform heterogeneous data into trusted, interoperable and actionable knowledge that can support decisions in real agricultural environments. A previous AgriDataValue article presented the importance of agricultural data models and semantic interoperability, explaining how common standards allow information exchanged between different systems to retain a consistent meaning. Since then, the project has entered a more mature technological stage.

The focus is increasingly moving from defining how agricultural information should be represented to demonstrating how it can be securely exchanged, processed, analysed and validated across multiple pilot environments. The updated AgriDataSpace Reference Architecture strengthens the project’s technical foundation through closer alignment between the Agriculture Information Model and the IDS Information Model, improved security and data-protection mechanisms, and clearer infrastructure specifications for artificial intelligence, machine learning and federated learning. At the same time, the latest smart farming implementation and validation activities show how this technological foundation can be connected to practical agricultural challenges. Together, these developments demonstrate how AgriDataValue is evolving from an interoperability concept into an operational ecosystem for data-driven agriculture.

Moving beyond a single agricultural platform

One of the most significant developments is the evolution of AgriDataValue as a platform of platforms, rather than as a single centralised application. Agricultural data is naturally decentralised. Information may be stored in local farm-management applications, sensor platforms, research infrastructures, public databases, regional services or equipment supplied by different manufacturers. Requiring every participant to transfer all information into one central system would create technical, organisational and trust-related barriers. The updated architecture addresses this challenge through a multi-instance approach. Different AgriDataValue environments can support local, regional, national or European ecosystems while remaining connected through common interoperability mechanisms. This allows the ecosystem to grow horizontally while giving local actors greater control over their own infrastructure and data. The International Data Spaces layer supports communication and trusted exchange between these environments. The Agriculture Information Model, or AIM, preserves the domain-specific meaning of agricultural information. The two models have complementary roles. AIM describes concepts such as parcels, crops, observations, interventions, animals and alerts. The IDS Information Model describes how the related data products can be published, discovered and exchanged, including information about participants, access conditions and usage policies. This separation ensures that agricultural meaning is preserved while datasets remain discoverable and interoperable across different platform instances and external systems. As illustrated in Figure 1, AgriDataValue connects heterogeneous agricultural data sources with semantic models, secure data-sharing mechanisms and AI-enabled services, transforming raw information into practical value for agricultural stakeholders.

Secure, sovereign and AI-ready data

Interoperability is not only about connecting technical systems. Agricultural data may contain commercially valuable or sensitive information about production, resources, farm operations and business performance. Trust is therefore a fundamental condition for participation in an agricultural data ecosystem. The updated architecture reinforces a security-by-design approach in which protection mechanisms are integrated throughout the platform. Authentication, authorisation, access control, secure communication and traceability help ensure that information is exchanged only between authorised participants.

Data providers can remain in control of their resources and define the conditions under which information may be accessed and used. This is particularly important for encouraging farmers, businesses and public organisations to participate in data-sharing initiatives without losing control over their data. The architecture also combines cloud and edge environments. Some information can be processed close to the farm, sensor or machine, where reduced latency or additional privacy is needed. More demanding activities, such as model training, large-scale analytics or cross-pilot services, can use cloud infrastructure.

This combination creates a stronger technical foundation for AI-enabled agricultural services. Irrigation recommendations, frost warnings, pest-risk indicators and livestock alerts need to be processed and communicated while intervention is still possible. A technically accurate prediction delivered too late may provide limited operational value. By connecting interoperable data exchange with cloud and edge processing, AgriDataValue creates the conditions needed to turn agricultural data into timely recommendations and decision support.

Connecting requirements, architecture and practical use

Within this technological evolution, AgriDataValue brings together user needs, technical requirements, platform architecture and validation activities. A complex digital ecosystem cannot be developed only from the perspective of individual technical components. It requires continuous collaboration between technology partners, pilot organisations, researchers and end users.

The updated architecture and technical requirements reflect this collaborative approach. Feedback collected during pilot preparation, integration activities and early testing is used to refine the platform and ensure that its capabilities remain connected to real agricultural needs. Requirements are treated as a living set rather than as a static document. They continue to evolve as integrations progress, users interact with the solutions and new technical or operational constraints become visible. This iterative process helps bridge the gap between the project’s technological vision and solutions that can be deployed, tested and evaluated in practice. It also ensures that technical developments remain aligned with the needs of farmers, advisers, researchers and public authorities.

From architecture to real agricultural use cases

The project’s pilot activities provide the strongest evidence of its transition towards operational maturity. AgriDataValue includes 23 pilot sites representing different agricultural sectors and geographical contexts across Europe. These pilots generate crop, livestock and environmental data that can support model development, system testing and use-case validation. The use cases address challenges such as smart irrigation, weed detection, greenhouse management, crop-development prediction, disease and pest forecasting, livestock welfare monitoring and supply-chain traceability. The latest implementation phase is no longer limited to installing sensors or identifying available datasets. It examines more closely how each use-case objective can be achieved through combinations of sensor measurements, observations, external data sources and analytical models. This transition is important for scalability. A solution creates greater value when it can be reused or adapted across several agricultural contexts rather than remaining connected to one pilot site.

The cross-pilot approach supports this objective by promoting common use-case definitions, technical guidelines, data flows and evaluation criteria. Pilot teams can exchange lessons learned and identify opportunities to transfer solutions while still adapting them to local environmental, regulatory and operational conditions. In this way, AgriDataValue moves from isolated technological demonstrations towards an ecosystem in which models, data and best practices can be compared, adapted and reused.

User-driven validation and measurable impact

A technically advanced system creates value only when people can understand and use it effectively. AgriDataValue therefore applies an iterative validation process based on continuous feedback from pilot partners and end users. The objective is not only to verify whether individual components function correctly, but also to determine whether the deployed solutions are useful, understandable and reliable in daily agricultural activities. The project’s evaluation framework combines two complementary dimensions.

Impact Assessment examines how a technological intervention changes farming practices, decision-making or operational results.

Quality Validation evaluates the quality of the deployed solution, including data quality, visualisation, usability, AI-model performance and overall system behaviour.

The evaluation is longitudinal, meaning that it takes place throughout the lifecycle of the pilot rather than only at the end. Feedback can therefore be used to identify issues, refine requirements and improve the solution during implementation. Traditional methods, including interviews, questionnaires and usability testing, are combined with technological evidence such as system logs and platform-usage data. This creates a stronger basis for understanding both how the technology performs and how it is perceived by users. This approach is essential for responsible agricultural innovation. A highly accurate model may still have limited practical value when its results are difficult to locate, interpret or apply. By integrating farmers, advisers and pilot organisations into the evaluation process, AgriDataValue treats usability and user experience as essential parts of technical quality. The feedback collected during pilot implementation can also support scale-up. Lessons learned in one environment may inform improvements in another, reducing duplication and helping successful solutions reach a wider group of users.

Conclusion

AgriDataValue’s progress demonstrates that the future of digital agriculture depends on more than collecting larger volumes of information. Value emerges when data can be understood, trusted, securely exchanged and transformed into timely decisions. The updated reference architecture provides a scalable and interoperable foundation for a distributed agricultural data ecosystem. Its combination of semantic models, trusted data-space technologies, cloud and edge infrastructure and AI-ready processing supports the transition from raw information to practical agricultural intelligence. The pilot activities demonstrate how this foundation can be applied to real challenges, while the evaluation framework ensures that success is measured not only through technical indicators, but also through usability, impact and continuous improvement. By aligning technical requirements, architecture, pilot implementation and user validation, AgriDataValue supports the transition from an ambitious technological vision to an operational and measurable agricultural data ecosystem. The next challenge is no longer simply to demonstrate that agricultural systems can exchange information. It is to ensure that this exchange consistently produces knowledge that farmers, researchers, businesses and public authorities can trust and use.

References

1. AgriDataValue Consortium. Deliverable D1.4 – AgriDataSpace Reference Architecture Update. Version 1.0, 2025.
2. AgriDataValue Consortium. Deliverable D3.6 – Smart Farming Use Cases Implementation & Validation V2. Version 1.0, 2026.
3. AgriDataValue. Enhancing Agricultural Data Models and Semantic Interoperability. 17 March 2025.
4. International Data Spaces Association. International Data Spaces Reference Architecture Model – IDS-RAM.
5. DEMETER Project. Agriculture Information Model – AIM.
6. GAIA-X European Association for Data and Cloud. GAIA-X Trust Framework.

From Data to Trusted Data

Modern agriculture and food supply chains generate vast amounts of digital information. Sensors, farm management systems, laboratory analyses, logistics platforms and Artificial Intelligence models continuously produce great quantities of data that can improve productivity, sustainability and decision-making. One important aspect that is also a critical challenge in data governance can be summarized in one question: how can stakeholders trust that this information is authentic, has not been altered, and can be shared reliably across organizations and platforms? The AgriDataValue project (ADV) addresses this challenge by developing trusted and interoperable agricultural data ecosystems. Within this framework, the CHAINTRACK component leverages Blockchain technologies to support data certification, supply-chain traceability and interoperability across distributed systems. In this sense CHAINTRACK provides a technological foundation for data certification, supply-chain traceability and interoperability across distributed systems.

Building a Trusted Blockchain Infrastructure

The cornerstone of this trust framework is the implementation of a dedicated private Blockchain environment. It is based on an Ethereum-compatible architecture using a Proof-of-Authority (PoA) network with validator nodes and RPC nodes deployed through Kubernetes and Helm technologies. The architecture also supports several Blockchain platforms technologies, such as Ethereum, Polygon, Quorum and Avalanche.

Enhancing Supply-Chain Traceability

One of the most tangible applications of the ADV distributed ledger technology is supply-chain tracking. CHAINTRACK has implemented dedicated smart contracts and backend services designed to support traceability processes across agriculture chains. This allows creation of dedicated supply chains for specific user processes in relevant domains of activities. As for today, two of them have been produced, for meat and olive oil processes tracking. Through DLT-based recording mechanisms, stakeholders can create verifiable evidence that specific information existed at a given point in time. This approach can strengthen confidence in provenance data, processing records, quality certifications and other critical supply-chain information. Importantly, the system does not simply store business information. It combines business processes, databases and Blockchain certification procedures, creating an auditable trail that can be independently verified.

Supporting Trustworthy Artificial Intelligence

Another noteworthy innovation is the realization of an AI Model notarization capability. CHAINTRACK provides dedicated functionality for certifying trained AI models on Blockchain infrastructures.  As Artificial Intelligence becomes increasingly important in agriculture, for example in predictive analytics, crop monitoring, decision support and sustainability assessments, the governance of AI models is emerging as a critical topic. Stakeholders require mechanisms to verify that deployed AI models are authentic, untampered and correspond to approved versions. Blockchain-based notarization can contribute to these objectives by creating transparent records of model versions, digital fingerprints and related metadata. While distributed ledger technology is not a replacement for AI governance frameworks, it can serve as a complementary technology supporting transparency, integrity verification and reproducibility.

Generalized Data Notarization

CHAINTRACK AI notarization capability has been extended to support notarization of any digital asset (such as datasets, digital documents, contracts and others) that has been written in the ADV secure storage layer. This capability is highly relevant for data-driven agriculture, where trust in datasets is becoming increasingly important. Research organizations, technology providers, cooperatives and public bodies frequently exchange data whose provenance and integrity must be guaranteed. Blockchain-based notarization can provide an additional layer of confidence and security.

Inter-DLT Interoperability

One of the most forward-looking aspects added in CHAINTRACK is the strong focus on interoperability, declined in the domain of Blockchain services. Interoperability is often cited as one of the most important challenges for digital transformation in agriculture. Farmers, industry stakeholders, technology providers and public authorities typically operate independent systems that must exchange information securely and efficiently. CHAINTRACK tackles this challenge by exploring mechanisms capable of operating across multiple Blockchain environments. The available Inter-DLT functionalities enable cooperation with both external DLT ecosystems as well as with other instances of the ADV platform.

Looking Ahead

The available ADV Blockchain-based functionalities demonstrate how distributed ledger technologies can support trusted digital agriculture by providing a practical framework for enhancing trust in agriculture data ecosystems. As Europe continues to promote data-driven innovation, sustainability and digital sovereignty in agriculture, solutions that guarantee transparency, integrity and interoperability will become increasingly valuable. The ADV DLT infrastructure represents an important contribution to this vision, showing how trusted digital infrastructures can help transform raw data into reliable assets that support collaboration, innovation and value creation across the entire agricultural sector.

We are thrilled to share a new video presenting AgriDataValue Pilot #14. The pilot takes place in the Saint-Émilion region of southwestern France—a world-renowned, UNESCO World Heritage wine landscape where local wine growers are deeply committed to sustainable viticulture.

The Challenge: Spring frosts and climate volatility pose a severe threat to vine development, capable of destroying an entire harvest in a single event. While modern frost protection methods exist, they consume massive amounts of energy and water, making optimized resource use critical.

The Solution: Harnessing the power of data to master frost dynamics and prediction. By deploying weather stations and advanced soil/air sensors in frost-sensitive zones, the pilot monitors real-time temperature and humidity during critical stages like budburst. Integrating this field data with extensive historical records, machine learning models, and aerial thermal mapping allows the pilot to build precise frost risk maps and early prediction tools. This empowers wine growers to activate and place their protection systems with pinpoint accuracy, saving vital resources while safeguarding their yields.

Watch the full video insight here: https://www.youtube.com/watch?v=wSxxxgBYlu8

The Third Liaison Webinar for Horizon Europe sister projects, organised by AgriDataValue and the National Paying Agency under the Ministry of Agriculture of Lithuania, brought together European initiatives working on digital agriculture, Earth Observation, decision support systems, data sharing, and sustainable food systems.

Held online on July 3, 2026, the event proved highly valuable for knowledge exchange, engagement, and discussion. The webinar focused on sustainability, climate, and biodiversity, as the participating projects addressed topics including climate neutrality, agroecology, sustainability transitions, environmental monitoring, and biodiversity conservation. The following sister projects participated in the event: AgriDataValue, Carbonica, FarmBioNet, RURACTIVE, GEORGIA, Eco-Ready, and Smart-Era.  

The webinar highlighted the strong commitment of Horizon Europe sister projects to collaborate, exchange knowledge, and learn from one another by sharing best practices and lessons learned. A key takeaway from the discussions was that high-quality, accessible, and well-structured data is essential for the successful development and deployment of digital solutions, including AI and machine learning tools.

Overall, the Third Liaison Webinar demonstrated the value of cross-project collaboration in addressing the challenges facing modern agriculture. By bringing together expertise in soil health, circular economy approaches, consumer engagement, and data governance, the participating initiatives reinforced the importance of a coordinated approach to innovation. Together, these projects are helping shape a smarter, more resilient, and climate-neutral future for European agriculture.

We are honored to announce that AgriDataValue was invited by the European Commission to participate and present at the high-level online expert workshop, “Fostering AI uptake and scaling trusted AI solutions in agriculture,” held on June 24, 2026.

This prestigious event was jointly organized by the European Commission’s Directorate-General for Agriculture and Rural Development (DG AGRI) and the Directorate-General for Communications Networks, Content and Technology (DG CNECT). It served as a vital platform for structured exchange on accelerating AI adoption in the agri-food sector while strengthening European competitiveness and technological sovereignty.

The strategic importance of the event was highlighted by the active participation of leadership from both directorates. The workshop opened with introductory remarks from Catherine Geslain-Lanéelle (Director for Strategy & Policy Analysis, DG AGRI) and Thibaut Kleiner (Director for Future Networks, DG CNECT).

The webinar attracted a substantial audience of more than 280 participants, including representatives from EU institutions, farmers’ organizations, agri-tech providers, researchers, and policymakers.

AgriDataValue took center stage during Session 3: AI solutions in agriculture: benefits, maturity and scalability. Project Coordinator Dr. Theodore Zahariadis delivered a comprehensive presentation on the project’s innovations, showcasing their practical value for farmers and their potential for large-scale adoption across European agriculture.

The workshop focused on three principal objectives:

• – Presenting the state of play of AI uptake in the agricultural sector, highlighting developed use cases and their concrete benefits.
• – Discussing scalability and identifying the remaining technical, operational, and regulatory barriers to wider market uptake.
• – Gathering strategic input to shape future policy actions, initiatives, and stakeholder frameworks supporting the digital and data-driven transition of rural areas.

Concluding the session, Zoe de Linde (Deputy Head of Unit, DG CNECT) and Pierluigi Londero (Head of Data Governance, DG AGRI) outlined the next steps for integrating these expert insights into future EU data and AI initiatives.

The insights and discussions from this workshop will feed directly into a European Commission stakeholder input note to define priority use cases and infrastructure needs under the Apply AI strategy. AgriDataValue’s inclusion in this expert forum underscores the project’s significant role in shaping the future of trusted, sustainable, and data-driven smart farming in Europe.

We are thrilled to share a new video presenting AgriDataValuePilot #3.

The pilot takes place at the Vilscini 1 farm in the Zemgale region of Latvia—one of the area’s largest and most modern grain farms, managing over 2,000 hectares.

The Challenge: Plant diseases are a massive threat to crop yield and quality, heavily driven by unpredictable weather conditions.

The Solution: Merging traditional farming wisdom with cutting-edge tech.
By combining physical field observations and laboratory analysis with real-time data from on-site meteorological stations and soil sensors, the pilot integrates this information into advanced predictive models. This allows farmers to assess disease risk early, optimize crop management, reduce losses, and drive forward sustainable agriculture.

Watch the full video insight here: https://www.youtube.com/watch?v=pz6J2kgg2Tc&t=2s

Climate change is increasing the frequency and complexity of weather-related risks across agricultural systems. Farmers are facing a growing combination of challenges, including droughts, heatwaves, frost events, and changing rainfall patterns. At the same time, these hazards are becoming more difficult to anticipate because they are influenced by multiple environmental factors that interact over time. Traditional risk assessments often rely on a limited number of indicators, such as air temperature or rainfall totals. While these metrics remain important, they do not always capture the full picture of how climate-related impacts develop in agricultural environments. As climate conditions become more variable, there is a growing need for approaches that can integrate different types of environmental information and transform them into actionable insights.

Within the AgriDataValue project, innovative data-driven methodologies are helping to address this challenge by combining sensor observations, climate records, and environmental indicators to improve the understanding and prediction of climate risks.

Looking Beyond Single Indicators

Agricultural systems are influenced by a wide range of environmental conditions that rarely operate in isolation. A damaging event is often the result of several factors acting together rather than a single threshold being exceeded. For example, frost damage is commonly associated with low temperatures. However, the severity of an event may also depend on atmospheric moisture, humidity levels, surface wetness, crop development stages, and local environmental conditions. Similarly, drought impacts are not determined solely by how much rain falls over the course of a year. Temperature increases, seasonal rainfall distribution, and soil moisture dynamics all play important roles in determining water availability for crops.

Recognizing these interactions is essential for improving risk assessment. By bringing together multiple sources of environmental information, it becomes possible to better understand the conditions that lead to crop stress and damage.

Combining Data to Better Understand Climate Risks

One of the key lessons emerging from recent analyses is that environmental data becomes significantly more valuable when different sources are considered together. Weather observations, sensor measurements, and historical climate records can each provide important insights on their own. However, when combined, they reveal relationships and patterns that would otherwise remain hidden. Accordingly, this integrated approach makes it possible to detect environmental conditions associated with increased climate risk, identify combinations of factors that contribute to crop vulnerability, understand how conditions evolve before a damaging event occurs, improve the accuracy of risk assessments and early warning systems and support more targeted and informed management decisions.

Rather than focusing on a single measurement, the methodology considers the broader environmental context in which agricultural production takes place.

Understanding Spatial Variability

Climate risks are rarely distributed evenly across agricultural landscapes.

Even within the same production area, environmental conditions can vary considerably due to differences in elevation, slope, exposure, soil characteristics, and local microclimates. As a result, some locations may consistently experience higher levels of risk than others.

Data analytics can help identify these patterns by analysing observations collected across multiple monitoring points. This makes it possible to distinguish areas that are repeatedly more vulnerable from those that are naturally more protected.

Such information is particularly valuable for farmers and land managers because it supports more precise interventions. Instead of applying the same measures everywhere, resources can be directed toward the locations where they are likely to have the greatest impact.

Learning from Historical Events

Historical climate records provide another important source of knowledge.

By analysing past events and comparing them with current environmental conditions, it becomes possible to identify recurring patterns and better understand how risks develop over time. This allows decision-support systems to recognise situations that resemble previous damaging events and provide earlier indications of potential problems.

The approach is particularly relevant in the context of climate adaptation. As more data becomes available, historical knowledge can be continuously enriched, enabling more robust risk assessments and improving the ability to anticipate future events.

Revealing Long-Term Climate Trends

In addition to supporting the detection of short-term hazards, integrated data analysis can also help identify long-term changes in climate behaviour.

Recent assessments have highlighted several important trends affecting agricultural systems:

• – Increasing average temperatures;
• – Greater variability in rainfall patterns;
• – More frequent periods of water stress;
• – Longer and less predictable drought seasons;
• – Greater occurrence of compound climate risks.

These findings demonstrate that climate vulnerability is influenced not only by individual extreme events but also by gradual changes that accumulate over time.

Understanding these trends is essential for designing effective adaptation strategies and ensuring the long-term resilience of agricultural production systems.

From Data Collection to Decision Support

The value of agricultural data lies not simply in collecting information but in transforming that information into knowledge that can support decision-making.

By integrating environmental observations, climate indicators, historical records, and analytical methods, it becomes possible to move from reactive responses toward more proactive risk management. Farmers, advisors, and agricultural organisations can gain a clearer understanding of emerging threats and take action before impacts become severe.

This transition from data collection to climate intelligence is a key objective of AgriDataValue. By unlocking the value of diverse data sources, the project contributes to the development of practical tools that support resilience, sustainability, and informed decision-making across the agricultural sector. The work carried out within AgriDataValue demonstrates that combining environmental data, climate information, and advanced analytics can provide a deeper understanding of agricultural vulnerability and support more effective adaptation strategies.

By turning data into actionable intelligence, these approaches help pave the way toward more resilient, sustainable, and climate-ready agriculture.

As part of the project’s research activities, and specifically within Use Case 3.1: Disease Forecasting and Detection, a field demonstration was conducted in Messinia, Greece, at the AgriDataValue pilot site.

The field demonstration, organized by the NILEAS Producers Group in a traditional olive grove, showcased how advanced digital technologies can enhance the early detection and management of olive anthracnose (Colletotrichum gloeosporioides). The event demonstrated the value of real-time monitoring and predictive analytics in providing growers with timely warnings, enabling them to optimize the timing of crop protection measures and improve disease management practices.

Use Case 3.1 leverages SynField smart agriculture systems to collect and analyze real-time data for monitoring disease epidemiology and supporting early disease detection. Through the AgriDataValue framework, predictive models are developed to forecast and identify diseases affecting fruit trees. By integrating IoT-based weather, soil, and leaf wetness sensors, the system continuously monitors key environmental parameters, including microclimatic conditions and canopy moisture, and generates automated disease risk indices to support farmers’ decision-making.

The AgriDataValue (ADV) project was presented at the 6ᵗʰ Congress of Geographical Information Systems and Spatial Analysis in Agriculture and Environment, held at the Agricultural University of Athens from 19–21 May 2026.

The congress brought together researchers, institutions, and technology providers working on Geographic Information Systems (GIS), spatial analysis, remote sensing, and precision agriculture applications. Within this context, AgriDataValue showcased its approach to integrating geospatial intelligence, IoT data, and advanced analytics into modern agricultural management.

The presentation highlighted how GIS technologies play a central role in the AgriDataValue ecosystem, supporting the collection, visualization, and analysis of agricultural and environmental data. Through the use of spatial data infrastructures, satellite imagery, sensor networks, and AI-driven analytics, the project aims to improve decision-making, resource efficiency, and environmental monitoring in agriculture.

In parallel, Synelixis sponsored the event and participated in the congress exhibition area with a dedicated stand, where AgriDataValue brochures, roll-up banners, and SynField devices utilized within the project were presented to participants and the broader audience of the congress. The stand offered visitors the opportunity to learn more about the practical implementation of smart farming technologies and their contribution to data-driven agricultural management.

More information about the congress is available at:
6ᵗʰ GIS Congress Official Website

AgriDataValue was recently featured at the regional event, “Presentations of Innovative and Research Capabilities in the Agri-Food Sector – Experiences from the Implementation of Research and Innovation Projects in the Region of Central Greece during the 2014–2020 Programming Period,” organized by the Region of Central Greece.

The event was held on Thursday the 14th of May 2026 and brought together key stakeholders to explore how research and innovation can drive sustainable development across the agri-food sector. Discussions centered on critical themes, including the circular bioeconomy, food authenticity and traceability, sustainable food systems, and the digital transformation of agriculture.

Within this framework, AgriDataValue was presented, by NKUA, as a flagship example of ongoing European research and innovation. The presentation highlighted the project’s deployment of cutting-edge technologies—such as Artificial Intelligence (AI), IoT sensors, satellite data, and smart data-driven tools—to advance precision agriculture, sustainable resource management, and intelligent decision support systems.

Furthermore, the session illustrated how these advancements directly contribute to boosting productivity, enhancing food quality, and strengthening the overall competitiveness and sustainability of the agri-food sector throughout Central Greece.