The integration of digital technologies with Artificial Intelligence could serve as a strategic approach to achieving the goals set by the European Union, mainly concerning sustainability, carbon emission reduction, and digitalization in the construction sector. In this regard, this paper aims to examine the major trends in the application of AI integrated with digital technologies to boost the environmental sustainability of the built environment throughout its life cycle. A systematic literature review was conducted, in accordance with the PRISMA guidelines, inspecting the Scopus database from 2015 to 2025. After having applied specific exclusion and inclusion criteria, 102 studies have been examined to identify key trends and transformative innovations enhancing sustainable approaches for the built environment. The results have been systematized based on the phases of the building life cycle which are impacted most by AI-powered digital technologies, and on sustainability areas that are attracting the greatest attention. The main research gaps are identified in the limited exploration of renovation and end-of-life phases of the life cycle, in the lack of technologies interoperability, in data complexity and quality issues, in a lack of cost-effective solutions, and in limited regulation and standardization.

Building Energy Modelling (BEM) for existing buildings is constrained by the lack of reliable as-built Building Information Models (BIMs) and persistent BIM-to-BEM interoperability problems. This study proposes a semantic scan-to-Industry Foundation Classes (IFC) workflow that converts mobile indoor scans into a simplified IFC model for BEM preprocessing. Apple RoomPlan captures room-scale building elements, which are exported as JSON and converted into IFC 4×3 ADD2 using a Python-based converter. To address partial scans, the workflow generates closed analytical volumes, inferred walls and ceiling slabs, and metadata distinguishing measured from reconstructed geometry. It then automatically generates IfcSpace entities and IfcRelSpaceBoundary2ndLevel relationships. The workflow was evaluated using a historic university building. For the selected case-study area, processing from mobile scanning to initial VICUS Buildings import required 21 min, excluding subsequent manual verification of boundary conditions and assignment of thermophysical properties. Under identical construction stratigraphies and usage profiles, the scan-derived model produced a total heating-season demand 5.8% higher than the Revit reference model. These results indicate that partial semantic indoor scans can support the rapid preparation of structured IFC models for preliminary BEM applications.

To evaluate the energy and solar potential of the building stock and address feasibility studies of building retrofit interventions information standards are required to ensure proper data flow from building and urban models to simulation environments. Energy performance data are gathered from different information containers and therefore the result of simulations needs to be shared in BIM/GIS environments to better address energy policies and decision-making processes. Solar potential and energy retrofit estimation, developed by means of urban models (U-BEM) are too rough to support a decision-making process, even if at a feasibility stage. On the opposite, strategic decisions are defined with reference to large building stocks that require a U-BEM approach. To increase the reliability of this kind of simulations the study proposes to integrate U-BEMS with BIM-based data that are aggregated and published at urban scale as average performance indicators of built systems. The interoperability problem is analyzed both for simulation tools that need to manage this kind of data and openBIM/GIS platforms that need to share performance indicators and simulation results