AI-DAPT brings forward a data-centric mentality in AI, that is effectively fused with a model-centric, science-guided approach, across the complete lifecycle of AI-Ops, by introducing end-to-end automation and AI-based systematic methods to support the design, the execution, the observability and the lifecycle management of robust, intelligent and scalable data-AI pipelines that continuously learn and adapt based on their context. AI-DAPT will design a novel AI-Ops / intelligent pipeline lifecycle framework cross-cutting the different business, legal/ethics, data, AI logic/models, and system requirements while always ensuring a human-in-the-loop (HITL) approach across five axis: “Data Design for AI”, “Data Nurturning for AI”, “Data Generation for AI”, “Model Delivery for AI”, “Data-Model Optimization for AI”. AI-DAPT will contribute to the current research and advance the state-of-the-art techniques and technologies across a number of research paths, including sophisticated Explainable AI (XAI)-driven data operations from purposing, harvesting/mining, exploration, documentation and valuation to interoperability, annotation, cleaning, augmentation and bias detection; collaborative feature engineering minimizing the data where appropriate; adaptive AI for model retraining purposes. Overall, AI-DAPT aims at reinstating the pure data-related work in its rightful place in AI and at reinforcing the generalizability, reliability, trustworthiness and fairness of Al solutions. In order to demonstrate the actual innovation and added value that can be derived through the AI-DAPT scientific advancements, the AI-DAPT results will be validated in two, interlinked axes: I. Through their actual application to address real-life problems in four (4) representative industries: Health, Robotics, Energy, and Manufacturing; II. Through their integration in different AI solutions, either open source or commercial, that are currently available in the market.

The overall vision is to operationalise energy efficiency first principle in the practical context of buildings, towards the decarbonisation of the EU building stock, through: Electrified low-carbon technologies such as heat pumps for the electrification of the building thermal energy demand; Integration of RES & storage; Building digitalisation and intelligence with smart energy management systems. To achieve the ‘META BUILD of the building sector’, we will develop and demonstrate at TRL 6-8 highly cost-effective, integrated and replicable solutions (i.e. Heat Pumps coupled with RES and ES systems) for electrifying thermal energy demand in buildings. Social acceptance and strict adherence to energy efficiency measures will be ensured to promote a sustainable, efficient energy use and an affordable pathway to decarbonise the building-sector heating. A holistic approach addresses challenges throughout the building life cycle, including product manufacturing, energy solution design and engineering, construction, renovation, operation, and maintenance. META BUILD will deliver: KPI-driven assessment methodology & LCA analysis on building electrification; Decarbonisation as a service decision support tool; sound Business Models combined with energy efficiency and electrification; Advanced HP technologies, PVTs & other RES solutions, thermal & second-life battery storage systems; Interoperable framework for electrified ready buildings; Energy management services for RT-monitoring & performance analytics; Demand response, grid interaction & flexibility planning tools; Pro-active maintenance & controls services; Digital Twins for maintaining/enhancing the buildings’ performance; Blueprints & policy recommendations for replication & scalability. Focus will be given on both construction and renovation phases of a building, while META BUILD solutions will be demonstrated and replicated in different types of buildings including 6 Front Runners and 7 Replication Multipliers.

Significant challenges affecting the building and construction value chain are related to fragmentation and siloing. A systemic change is needed, catalysed by lifecycle perspectives, that will reveal interactions, opportunities, and threats. INBLANC will establish an open ecosystem focused on capitalising on the economy of building lifecycle data. This will be achieved through: The Accumulation framework, INBLANC prioritises low-cost data collection options and data extraction and inference, the consolidation of building information in Building Digital Logbook, as well as the creation and population of databases, interfaced with EU dataspaces through connectors. The Numeracy component will implement a Nexus strategy to map and operationalize interactions between different types of metrics: energy, human & societal, economy, environment & circularity and resilience, six Target Groups, encompassing the entire value chain, with focus on building owners and facility managers as actors with major decision-making capacity. The building lifecycle data Capitalisation toolset integrates high-added value services for the comprehensive management of: energy planning and operation, virtual facility management, quantified indoor health, low-carbon renovation planning and urban context integration. Actors in the ecosystem will be engaged across the value chain, through a holistic engagement strategy that will embed the project’s outcomes in current and future industrial, but also user needs. INBLANC will be demonstrated in six demo cases, reflecting six very different use-case scenarios, from heritage renovation, to education, to energy flexible neighbourhoods, public building portfolios, large scale health facilities and finally city-scale implementation. Through the ambitious demonstrations, feedback will be collected and incorporated into a system completion process to prove near-market readiness.