Foundation models represent a paradigm shift in AI, exhibiting remarkable capabilities across multiple tasks. Their true potential lies in generalizing across diverse domains and modalities, a largely untapped frontier. DVPS advances this frontier by focusing on multimodal foundation models (MMFM), aiming to harness their capabilities across various application domains. DVPS emphasizes three core benefits of MMFM: label efficiency, compute reusability, and engineering efficiency. However, achieving these benefits in multimodal settings presents challenges such as modality-specific architecture and cross-modal alignment. To overcome these, DVPS aims to develop generalizable methods that work across diverse modalities and domains, creating a unified framework for MMFM development and integrating new modalities into existing models. The project focuses on generating foundational knowledge, delivering tested methods, and creating algorithms to expand MMFM capabilities across domains like cardiology, geo-intelligence, and language communication. DVPS also includes two "surprise domains" to drive innovation by challenging initial assumptions. Key objectives include the development of AutoDVPS, a toolkit for automated MMFM design, and the creation of DVPSBench, a benchmarking suite for evaluating MMFM across tasks and domains. DVPS aims to foster a European ecosystem for MMFM research, promoting transparency, fairness, and ethical compliance in line with European values. Through collaboration and open-source contributions, DVPS seeks to standardize and advance MMFM as a scientifically rigorous discipline.

HERACLES main objective is to design, validate and promote responsive systems/solutions for effective resilience of CH against climate change effects, considering as a mandatory premise an holistic, multidisciplinary approach through the involvement of different expertise (end-users, industry/SMEs, scientists, conservators/restorators and social experts, decision, and policy makers). This will be operationally pursued with the development of a system exploiting an ICT platform able to collect and integrate multisource information in order to effectively provide complete and updated situational awareness and support decision for innovative measurements improving CH resilience, including new solutions for maintenance and conservation. The HERACLES effectiveness will be ensured by the design and validation of manageable methodologies also for the definition of operational procedures and guidelines for risk mitigation and management. It will be validated in two challenging test beds, key study cases for the climate change impact on European CH assets. The strength of HERACLES solutions is their flexibility in evaluating a big quantity of different information that can be changed and tailored to the specific CH assets needs, guaranteeing in that way a general applicability. In this context, a fundamental role will be played by end-users, which will be active part in the project activities. HERACLES system will be designed and developed by accounting for the economic sustainability and future acceptance by the market and for the social and economic impact for public and local communities while respecting the integrity of CH and the value it hold for communities. Effective technological transfer of HERACLES outcomes to large companies, SMEs and end users, suitable dissemination, communication, education and training activities are also organized to disseminate vision and progresses obtained to different communities, in a vision of wide audiences awareness.

MESEO aims to design, prototype and demonstrate an open, flexible and scalable multi-mission EO End-to-End system for massive processing. It will improve performance bottlenecks either on board or on ground while ensuring Space data sovereignty. The main goal of the proposed approach is to improve quality of service and timeline reactivity by improving the End-to-End EO chain at different levels and processing edges while reducing communication bandwidth and incorporating new technology optimised in power consumption and processing capabilities. MESEO will promote a collaborative digital ecosystem enabled by an EO Coordinator Centre together with distributed and heterogeneous Processing Functions. Those Functions will be exported through harmonized interfaces which will ensure the data sovereignty. EO ecosystem players will register their products/services as exported Functions into the ecosystem. The EO Coordinator Centre will control which registered Processing Function to activate in a transparent manner for optimal End-to-End performance, from either timing or quality point of view, for a given End-User request. MESEO specifically addressed both upstream and downstream parts of the EO data processing value chain in a transparent manner. Performance enhancements analysis will tackle major bottlenecks on each link of the EO data processing running either on board or on ground. MESEO proposed innovations will address such bottlenecks. Green Deal related pilot applications (methane monitoring and crops classification) will serve to demonstrate the performance enhancements due to the proposed innovations.

Earth system models (ESM) show diverging estimates of ecosystem carbon (C) uptake which drives persistent uncertainty about future climate and limits the realization of policy mitigation goals. The CONCERTO project aims to strengthen the European research ecosystem by creating an innovative scientific collaborative framework that enhances our understanding, monitoring, and modelling of the terrestrial cycle (CC), and leads to reduced uncertainty and ESM convergence. This framework has three main elements: the exploitation of novel Earth Observation (EO) data, the innovation of process models fed by these data, and Data Assimilation (DA) and Machine Learning (ML) techniques. The consortium includes European experts and institutes active in these areas. CONCERTO will advance the representation of land cover, leaf area index (LAI) and management intensity through new maps of high resolution with layers relevant for the CC. The new management map will enhance the creation of a new biomass production map. Further, CONCERTO will prepare for the ingestion of FLEX data in land surface models (LSM) through DA, and exploit Sentinel-5P/TROPOMI HCHO indicative of biogenic volatile organic compound (VOC) emissions. As step towards moving away from prior (static) parameterizations, the novel P model will be used to ingest these new data sources. This will enhance understanding of ecosystems responses to climate extremes, fires, and vegetation recovery from them, and the parameterization of LSMs included in ESMs. Novel representations of the underrepresented processes of lateral carbon fluxes through outgassing of CO2 from rivers will be developed. Dedicated seasonal and climate experiments will demonstrate how improved representation of land surface processes benefit the accuracy and trustworthiness of global Earth System simulation. This will lead to better predictability of the influence of land management on the CC and underpin avenues towards carbon neutrality

Over the last decades, as a consequence of the effects of climate change, cultural heritage has been impacted by an increasing number of climate related hazards, posing new challenges to conservators and heritage managers. SHELTER aims at developing a data driven and community based knowledge framework that will bring together the scientific community and heritage managers with the objective of increasing resilience, reducing vulnerability and promoting better and safer reconstruction in historic areas. The first step to enhance resilience is associated to the improvement in understanding the direct and indirect impacts of climatic and environmental changes and natural hazards on historic sites and buildings, by linking concepts commonly used in disaster risk management and climate change adaptation with cultural heritage management, in order to provide inclusive and informed decision-making. Comprehensive disaster risk management plans need to be drawn up, based on the specific characteristics of cultural heritage and the nature of the hazards within a regional context, taking into account the diverse heritage typologies as well as the specific socioeconomic conditions, since this directly affect the vulnerability of such systems. By a deep understanding of the hazard, the exposure and the vulnerability of the historic area, the local dynamics and the provision of innovative governance and community based models, it is possible to provide useful methodologies, tools and strategies to enhance resilience and secure sustainable reconstruction. Due to the information complexity and the diverse data sources, SHELTER framework will be implemented in multiscale and multisource data driven platform, able to provide the necessary information for planning and adaptive governance. All the developments of the project will be validated in 5 open-labs, representative of main climatic and environmental challenges in Europe and different heritage’s typologies.