Index – Digital Innovations in Architecture, Engineering and Construction
BIM and Data Integration: A Workflow for the Implementation of Digital Twins
This paper presents a methodological and operational workflow for the implementation of Digital Twins (DT) in the construction sector through the integration of Building Information Modeling (BIM) and Internet of Things (IoT) systems. The research addresses the growing need for structured data management across the lifecycle of built assets, emphasizing the transition from static BIM models to dynamic, data-driven environments capable of supporting real-time monitoring and decision-making.
The proposed framework combines federated BIM models (in IFC format) with real-time sensor data collected from IoT devices, enabling the creation of a unified information system where geometric, semantic, and environmental data converge (Fig. 1, p. 826). The workflow is structured into six phases—creation, communication, aggregation, analysis, insight, and action—defining a progressive integration between physical assets and digital environments. Data collected from sensors (e.g. temperature and humidity) are processed through edge computing systems and integrated into the Snap4City platform, where they are visualized via dashboards and linked to BIM components (Figs. 6–7, pp. 831–832).
The results demonstrate that the integration of BIM and IoT enables the development of digital twins that support facility management, predictive maintenance, and performance monitoring. While artificial intelligence is identified as a future extension for data analytics and predictive evaluation, the current contribution focuses primarily on data integration, interoperability, and visualization. The study highlights both the potential and the limitations of current DT implementations, particularly regarding semantic interoperability and data standardization.
New Representation Tools in VR and Holographic View
This paper investigates the development of advanced representation tools based on virtual reality and holographic visualization to enhance the communication, interpretation, and understanding of architectural and cultural heritage models. The research addresses the limitations of traditional two-dimensional and screen-based representations, proposing immersive and multi-user environments as more effective means for conveying spatial complexity to both expert and non-expert audiences.
The methodology is based on the integration of 3D modeling workflows (Revit, Rhino, SketchUp) with real-time visualization environments developed in Unity, using Unity Reflect to preserve geometric and semantic data throughout the pipeline (Fig. 3, p. 813). The system supports both VR headsets and holographic tables, enabling immersive single-user experiences and collaborative multi-user interaction. Several custom tools are implemented, including annotation systems for collaborative review, dynamic section planes for real-time spatial analysis (Fig. 9, p. 816), and heatmap visualizations that map quantitative parameters onto model components (Fig. 11, p. 818).
Results demonstrate that immersive and holographic visualization significantly improve spatial perception, data interpretation, and collaborative workflows, particularly in educational and design contexts. The study highlights the potential of integrating real-time engines and extended reality technologies into architectural representation pipelines, while emphasizing that these tools act primarily as enhanced visualization and interaction systems rather than generative or analytical AI processes.
Visual Programming for a Machine Semi-Automatic Process of HBIM Models Geometric Evaluation
This paper presents a semi-automatic methodology for evaluating the geometric reliability of HBIM models through the integration of visual programming techniques within BIM environments. The research addresses the challenge of reconciling the parametric standardization of BIM with the geometric complexity and uniqueness of historical architecture, focusing on the need to quantify deviations between survey data and digital models.
The proposed workflow is based on the comparison between point clouds derived from architectural surveys and corresponding HBIM elements, using a Visual Programming Language (VPL) implemented in Dynamo. As illustrated in the operational pipeline (Fig. 3, p. 798), the method involves the import of point cloud data and model geometries, computation of normal vectors, projection of points onto model surfaces, and calculation of distances to evaluate geometric deviation. These values are then classified according to predefined reliability thresholds, generating a Level of Accuracy (LoA) and automatically updating model parameters within the BIM environment. Visualization outputs (Figs. 7–9, pp. 799–801) enable the identification of low, medium, and high reliability zones through color-coded mapping.
Results demonstrate that the proposed approach significantly reduces the time required for reliability assessment and supports iterative model refinement through semi-automated feedback. The study highlights the potential of integrating algorithmic processes within HBIM workflows to improve transparency, reproducibility, and accuracy in heritage modeling, while emphasizing the interpretative nature of digital reconstruction and the importance of explicitly declaring model reliability.
Hybrid AI-Based Annotations of the Urban Walls of Pisa for Stratigraphic Analyses
This paper proposes a hybrid methodology for the semantic annotation and stratigraphic analysis of architectural heritage, combining supervised machine learning techniques with photogrammetric 3D modeling. The research aims to support the interpretation of complex masonry structures by integrating 2D image-based classification with 3D spatial representations.
The workflow involves the acquisition of photogrammetric datasets, followed by supervised classification of images using a Random Forest algorithm trained on manually annotated samples. As illustrated in the workflow diagram (Fig. 2, p. 783), semantic information related to lithotypes and construction layers is first propagated across the entire image set and subsequently transferred to the 3D point cloud through 2D–3D reprojection. This process enables the creation of semantically enriched 3D models, preserving the relationship between geometric data and interpretative annotations.
Results, shown in the classification outputs (Figs. 4–6, pp. 786–788), demonstrate that the method effectively identifies different construction phases and material layers, particularly in cases with clear colorimetric variation. However, limitations arise in areas with homogeneous textures, where classification accuracy decreases. The study highlights the potential of hybrid AI-based annotation systems to enhance stratigraphic analysis and heritage documentation, while emphasizing the need to integrate additional geometric features to improve robustness.
Documentation Procedures for Rescue Archaeology Through Information Systems and 3D Databases
This paper presents a methodological framework for the documentation, management, and interpretation of rescue archaeology data through integrated information systems and three-dimensional databases. The research addresses the critical challenge of preserving archaeological memory in contexts where excavation processes inherently lead to the destruction of physical evidence.
The proposed approach combines integrated survey techniques—including terrestrial laser scanning, photogrammetry, and UAV acquisition—with the development of a structured digital archive linking stratigraphic data, textual records, and 3D models. As illustrated in the workflow diagrams (Fig. 3–5, pp. 767–769), multi-temporal point clouds and photogrammetric models are aligned and processed to reconstruct excavation phases, enabling the visualization of stratigraphic evolution over time. A key contribution is the implementation of a three-dimensional GIS environment in which each stratigraphic unit is semantically defined and associated with database records through a one-to-one relationship, allowing query-based interaction and thematic visualization (Fig. 10, p. 775).
The system supports in situ data acquisition through digital forms and mobile devices, improving the efficiency and accuracy of documentation under time-constrained conditions. Results demonstrate that integrating 3D models with relational databases enhances data accessibility, interpretability, and long-term preservation, while enabling multi-scalar analysis from stratigraphic detail to urban context. The study concludes that three-dimensional information systems can act as dynamic repositories of archaeological knowledge, bridging survey data, archival records, and interpretative processes.
Artificial Intelligence and Virtual Reality in the Simulation of Human Behavior During Evacuations
This paper investigates the integration of artificial intelligence and virtual reality for the simulation of human behavior in emergency evacuation scenarios. The research focuses on the use of game engines and agent-based modeling to reproduce dynamic interactions between individuals and built environments under hazardous conditions.
The methodology combines three-dimensional architectural modeling, real-time simulation environments, and AI-driven behavioral models. As described in the workflow (pp. 755–756), architectural spaces are modeled and imported into Unreal Engine, where virtual agents are endowed with physical and behavioral properties. Agent movement is governed by social force models, allowing the simulation of individual decision-making processes influenced by environmental stimuli, obstacles, and crowd dynamics. The system supports real-time interaction and visualization, enabling the testing of evacuation scenarios under varying conditions such as fire location and spatial configuration. Results demonstrate that immersive simulation environments can support predictive analysis, training, and design evaluation, while also highlighting the limitations of current models in capturing complex human behavior and decision-making processes during emergencies.
Preliminary Study on Architectural Skin Design Method Driven by Neural Style Transfer
This paper explores the application of neural style transfer as an AI-assisted method for architectural skin design, aiming to enhance formal diversity and support conceptual design processes. The research investigates how convolutional neural networks can extract and recombine content and style features from different visual sources to generate alternative façade design proposals.
The methodology is based on the neural style transfer approach introduced by Gatys et al., implemented using a pre-trained VGG-19 network. As illustrated in the workflow diagram (Fig. 2, p. 744), the process defines content and style loss functions to iteratively optimize an output image that combines structural features from a content image with stylistic attributes from a reference image. The study applies this method to multiple sets of architectural images, including traditional Chinese buildings, modernist architecture, and urban skylines, combined with stylistic references such as Notre Dame, landscape painting, and science-fiction imagery. Results demonstrate that style transfer can generate diverse and visually suggestive façade configurations, supporting architects in the early design phase by providing rapid exploratory variations. However, the generated outputs remain conceptual and require further interpretation and development, highlighting the role of AI as a tool for inspiration rather than a deterministic design system.
Monitoring Systems Design with Real Time Interactive 3D and Artificial Intelligence
This paper presents a methodological framework for the design and simulation of monitoring systems for cultural heritage, integrating real-time interactive 3D environments and artificial intelligence techniques. The research focuses on preventive conservation, proposing a workflow that combines multiscalar digitization, semantic annotation, and AI-driven analysis to detect and predict the evolution of degradation phenomena.
The methodology is structured into three main phases: (i) detailed digital acquisition of the architectural artifact through integrated survey techniques (TLS, photogrammetry, and image-based methods); (ii) construction of an information-rich 3D model, semantically annotated and enriched with diagnostic data (thermal, material, and colorimetric); and (iii) simulation of monitoring systems within a real-time interactive environment using Unreal Engine 5. As illustrated in the workflow diagram (Fig. 1, p. 722), the system enables the placement of virtual sensors and the generation of synthetic datasets through simulated damage patterns. These data streams are used to train machine learning models for anomaly detection, which are integrated with natural language–based AI systems to support user interaction and decision-making. The results demonstrate the potential of combining digital twins, simulation environments, and AI to design and test monitoring infrastructures prior to on-site implementation, while highlighting the challenges related to data integration, model accuracy, and real-world validation.