RAIDO is a powerful framework solution designed to develop trustworthy and green artificial intelligence (AI). Trustworthy AI focuses on ensuring the reliability, safety, and unbiased optimization and deployment of AI systems, particularly in critical applications such as healthcare, farming, energy, and robotics. On the other hand, Green AI involves the development and deployment of energy-efficient and environmentally sustainable AI technologies, leading to reduced environmental impact and improved resource management. RAIDO provides an array of automated data curation and enrichment methods, including digital twins and diffusion models, to create high-quality, representative, unbiased, and compliant training data. It also offers various data- and compute-efficient models and tools to create energy-efficient Green AI, such as few- and zero-shot learning, dataset and model search, data and model distillation, and continual learning. To ensure the transparency, explainability, and reliability of the optimized AI models and data handling processes, RAIDO uses various XAI methods, decentralized blockchain, feedback-based reinforcement learning, novel KPIs, and visualization techniques. Additionally, the innovative AI orchestrator optimizes related tasks and processes, reducing the overall energy consumption and environmental footprint of the models during both development and deployment. RAIDO emphasizes the development of dynamic interfaces that support the appropriate AI paradigms (central, distributed, dynamic, hybrid) and enable seamless adaptation to the needs of the use situation. Furthermore, RAIDO will be evaluated through four real-life demonstrators in key application domains, such as smart grids, computer vision-based smart farming, healthcare, and robotics, showcasing notable societal and market impact.

The overall aim of NANCY is to introduce a secure and intelligent architecture for the beyond the fifth generation (B5G) wireless network. Leveraging AI and blockchain, NANCY enables secure and intelligent resource management, flexible networking, and orchestration. In this direction, novel architectures, namely point-to-point (P2P) connectivity for device-to-device connectivity, mesh networking, and relay-based communications, as well as protocols for medium access, mobility management, and resource allocation will be designed. These architectures and protocols will make the most by jointly optimizing the midhaul, and fronthaul. This is expected to enable truly distributed intelligence and transform the network to a low-power computer. Likewise, by following a holistic optimization approach and leveraging the developments in blockchain, NANCY aims at supporting E2E personalized, multi-tenant and perpetual protection.

The EU-INTERCHANGE project aims to create a Digital Ocean Twin encompassing wave, ocean, biogeochemistry, and nearshore models to evaluate Climate Change impacts across Europe and the Pan-Arctic region. Customized models will be developed to assess mitigation and adaptation strategies, focusing on coastal resilience, impacts of Sea Level Rise, and Blue Economy sectors such as aquaculture and marine renewables. Indicators for marine ecosystem health, blue growth, coastal resilience and societal impacts of Climate Change will be formulated, and used in unique fully automated tools. A large ensemble database spanning from 1995 to 2100, including emission scenarios SSP1 (2.6°C) and SSP2 (4.5°C) using CMIP6 data, will be developed, optimized per European Basin and scale, for all European Seas and the Arctic region. A transparent fully open-source automated service for statistical analysis and reporting will be released to aid decision-making for various stakeholders and applications like coastal protection, marine renewables, food, and tourism. Furthermore, an automated dynamic and statistical downscaling tool will be developed, requiring minimal user expertise but offering the potential for higher fidelity data (<500m), for coastal areas that require further analysis. The novel datasets, both hindcast and forecasts, will seamlessly integrate into COPERNICUS and be openly accessible along with model configurations, fostering collaborative research and informed decision-making regarding Climate Change impacts on marine environments.

EmergeNOW uses digital, molecular tools for rapid CBS, HLB detection, enabling early warning at EU import points. Consortium introduces novel tools and autonavigated robots for inspectors: a) on-site Phyllosticta citricarpa (P.c) and Candidatus Liberibacter’ (Ca. L) species rapid detection a molecular tool based on Recombinase Polymerase Amplification kits, b)Fluorescent Array-based Sensing Technology for P.c and Ca.L rapid detection, c) Artificial Intelligence- powered mobile apps for rapid CBS and HLB image analysis detection integrated with low-cost hyperspectral imagers, d) UAVs for AI-based RGB and hyperspectral imaging of abiotic and biotic symptom response of CBS and HLB and similar to these; e) Autonomous Mobile Robots for HLB and CBS AI imaging symptoms detection discriminate from abiotic stress. Also, deployment plans are in place for detecting the vector Diaphorina citri (ACP), Trioza erytreae (T.e ), and Cacopsylla citrisuga (C.c) by: f) e-Nose sensors, g) AI - based robotic traps for real time detection and monitoring, and h) AI-powered mobile apps for their early detection. Τhese systemic innovations could be incorporated in the EFSA Survey Cards. Digital tools link in systemic alert system with blockchain, ML analytics and will enable informed decisions for import control. Focusing on showcasing real problem scenarios, the developed tools and methods will be initially tested and optimised in biosecure enviroments at Plant Health Centers (PHC) and afterwards validated in citrus orchards in USA (CBS, HLB, ACP), Uganda (CBS, HLB, T.e), Vietnam (HLB, ACP, C.c), and in Cyprus (ACP). The optimised tools will be demonstrated in authorized Border Control Posts in Greece, Italy, Spain and Cyprus.

E-SPFdigit will bring novel onsite digital tools already at TRL5 under systemic innovation, which will be further deployed, upscaled, field-tested and demonstrated to TRL7-8, in viticulture and horticulture applications in Greece and Spain in soil-contaminated areas (located near mines, offensive industries, highways, floodwaters). E-SPFdigit brings novel developed: i) MIP-based electrochemical sensors coupled with SPME for on-site monitoring and analysis of dedicated to PFAS targeted molecules, ii) Multiplex organic Surface Plasmon Resonance optical biosensors for onsite pesticides residues monitoring and analysis, iii) IDE-based electrochemical sensors for onsite detection and quantification of heavy metals & micronutrients, and iv) UVC LED -based nutrient analysers for soil water content in-situ and real time monitoring. The AI-driven onsite digital tools will be model calibrated using machine learning algorithms to improve error distribution of a predictive model, ensuring reliability. Also, E-SPFdigit brings an edge-based remote sensing framework via a robust autonomous mobile robot self-navigating and a heavy-duty unmanned aerial vehicle for in-field detection of soil parameters regarding the aforementioned chemical and biological stressors. Finally, to predict pesticide and fertiliser and other chemical contaminants impacts on crop-soil-microbiome nexus, the project will use on-field real-time digital ground sensors combined with Earth Observation data and causal machine learning. All the onsite digital tools will be interconnected with a Decision Support Systems with blockchain and cybersecurity mechanisms enabling informed decisions and automated decision making for IPM and INM, enhanced with automated decision making for immediate soil management practices.