D-NAVIO (meaning Digital-Ship) is an advanced digital twin project that aims to develop a next-generation digital “clone of ships” through an Intelligent Digital Twin (IDT) system. Integrating explainable Artificial Intelligence (XAI) and self-healing technologies, D-NAVIO focuses on large, complex vessels. The project aligns with the global mission to enhance maritime safety, protect property, improve environmental efficiency, and facilitate the transition to autonomous ships by incorporating interdisciplinary knowledge from automation, aviation, and the space industry. D-NAVIO’s “System-of-Systems” approach enables real-time monitoring and analytics through two pilot use cases: 1) COLUMBIA’s large passenger/cruise ship, and 2) DANAOS Shipping’s large cargo/container ship. These pilots will identify missing requirements and propose advanced methods for forecasting, preventing, and managing faults, failures, and hazards throughout a ship’s operational phase. Through its multi-pillar approach, D-NAVIO goes beyond the state-of-the-art to offer specific and tangible, cutting-edge innovations: 1) D-NAVIO XDTLib: An Extensible Digital Twins Library for Waterborne Systems, 2) D-NAVIO HYDRA: A Hybrid and Adaptive Risk Assessment Framework, 3) D-NAVIO Failures Reporting System: A “memory of failures” system, 4) D-NAVIO Cybersecurity Assessment Toolkit, 5) DYNAMO: Dynamic Cloning for Maritime Applications, and 6) Analysis of Reliability Regimes for critical systems. D-NAVIO’s innovative solutions, grounded in interdisciplinary collaboration and input from shipyards, shipbuilders, system designers, maritime engineers, equipment manufacturers, IT experts, operators, class societies, and regulators, will establish a smart platform that revolutionizes risk assessment and hazard management. This will not only enhance safety during design, construction, and sea trials but will also ensure operational resilience and cost-effectiveness throughout the life cycle of large ships.

The FF-IPM project targets three highly polyphagous fruit fly (FF) species (Tephritidae) that cause devastating losses in the fresh fruit producing industry, the Mediterranean fruit fly (Ceratitis capitata), a serious emerging pest in northern temperate areas of Europe, the Oriental fruit fly (Bactrocera dorsalis) and the peach fruit fly (B. zonata) two major new (invasive) pests, which pose an imminent threat to European horticulture. The project aims to introduce in-silico supported prevention, detection and Integrated Pest Management (IPM) approaches for both new and emerging FF, based on spatial modelling across a wide range of spatial levels, novel decision support systems, and new knowledge regarding biological traits of the target species, fruit trading and socioeconomics. FF-IPM introduces a fundamental paradigm shift in IPM towards “OFF-Season” management of FF by targeting the overwintering generation when population undergoes significant bottlenecks, preventing, this way, population growth later in season. “ON-Season” control approaches will be generated for different spatial scales considering both existing and developed by FF-IPM tools and services. Innovative prevention tools to track FF infested fruit (e-Nose) and rapidly identify intercepted specimens (Rapid-Molecular-Pest-ID tools) in imported commodities and at processing industries will be produced. Species specific e-trapping systems for the three-target FF will be advanced and employed by novel detection strategies based on spatial modelling. Both “ON and OFF-Season” IPM approaches and detection strategies will be validated in selected locations in eight different countries. FF-IPM generated data on FF response under stress conditions, overwintering dynamics, establishment and dispersion patterns of low population densities combined with advanced spatial population modeling are expected to contribute towards understanding drivers of emerging and new pests under climate change scenarios.