Environmental Life Cycle Assessment (eLCA) has become an integral component of building certification systems and regulatory frameworks. However, existing approaches lack robust methodologies for evaluating the environmental implications of socially oriented design intents during early design stages. This gap limits architects and other early-phase stakeholders' ability to balance social and environmental sustainability effectively when making preliminary decisions. To address this challenge, the present study introduces a systematic methodology for eliciting socially oriented design intents from early design phases and quantifying their environmental impact through eLCA. The proposed framework categorises these design intents into three types: Addition, Removal, and Replacement, based on their impact on building design. Three case studies are presented to illustrate the application of this methodology across these categories. The findings demonstrate that the inclusion of socially oriented design intents can significantly influence a building's total CO2-equivalent emissions, either positively or negatively. By enabling early-stage assessment of such impacts, this research provides a foundation for more informed decision-making, supporting the integration of social and environmental objectives in building renovation projects.

The role of large language models (LLMs) in the architecture, engineering, and construction (AEC) sector has been increasing rapidly over the past few years, as they are being used as assistants, analyzers, and chat agents to optimize building designs through their context-based text-generation capabilities. In this paper, we present ProSpect, a software tool developed to capture architects' human-centered social design intentions (SDIs) by integrating building information modeling (BIM) and LLMs. The aim is to enable architects to clearly and explicitly integrate qualitative design intentions into BIM models. This work builds on our previously developed formalization framework, ProFormalize, which provides a domain-specific language to capture design intentions that particularly elicit human-centered criteria (e.g., curiosity and comfort). We present the development of ProSpect, following a co-creation approach and a case study-driven methodology that aim to empirically assess the validity of our framework and the usability of our software tool, comparing its LLM-based (latest) version with its wizard-based (previous) version. Our study shows that the LLM-based solution is more efficient at capturing and representing SDIs, achieving approximately 9% higher accuracy on trained prompts than on untrained ones.

Supporting designers in making effective renovation decisions is urgently needed to address the ever-growing climate crisis. This requires developing tools that bring insight into the enormous set of design options at hand, where the efficacy of candidate renovation design options is evaluated using (potentially computationally expensive) simulations. Thus, a systematic, goal-driven design process is required that ensures “design space” diversity and coverage, while making careful and effective use of highly informative but time consuming performance simulations. To this end, we define twelve new concepts based on scenario (dis)similarity that give designers insight about pairs of scenarios, clusters of scenarios, and pairs of clusters, and apply these concepts in an iterative, goal-driven design process. We evaluate a software implementation of our design concept analyser using a real renovation case of a large residential building in Denmark.

Human-centered qualities (e.g., privacy, sense of orientation, etc.) significantly impact the social sustainability of buildings and the well-being of their occupants. However, due to their subjective nature, such qualities are often implicit and are not documented properly during the planning phase of construction projects. While several types of design intentions are documented throughout the lifecycle of building projects, intentions that are socially oriented and target soft aspects that reflect occupants’ experience (e.g., comfort, well-being, etc.), are evidently missing from current digital building models, hence risking constructing uninhabitable or socially unsustainable buildings. Through an extensive interdisciplinary collaboration between building scientists, practicing architects, and computer scientists, this paper addresses this gap by introducing a formalization framework, “ProFormalize”, to capture social design intentions (SDIs) in digital building models. This work presents a novel approach to digitalize SDIs in buildings, bridging a critical gap between architectural design intentions and explicit digital representations. Following a case-study-driven approach and a co-creation-based methodology, we developed the framework aiming to establish the foundations for developing a decision-support software tool (plugin) that enables architects, who are directly involved in the research process, to integrate SDIs into digital building models. The expert feedback demonstrates that the framework can make implicit SDIs explicit, which enables architects to integrate them into digital building models. Expert feedback suggested that a software tool developed based on this framework can enhance decision-making due to the traceability and analyzability of digital models.

In architectural practice, social values are created through design choices made by architects. Integrating social intents, along with their corresponding design choices, into a design project has significant implications for the environmental impact of the building. This fac-tor is often inadequately addressed.This paper presents an initial study towards adopting a novel environmental life cycle assessment (eLCA) approach for assessing the environmental impact of social intents in building projects. The study focuses on exploring eLCA’s goal and scope setting through a methodological triangulation approach where the goal and scope are explored through various sources as follows: (a) a literature re-view of existing approaches within the building and construction industry, (b) narrative interviews and analysis with practicing architects, and finally (c) through a practical investigation carried out on social design intents from actual building projects. The preliminary findings indicate that incorporating social intentions into building projects yields significantly varying effects on the emissions of the building, contingent upon the specific design choices that facilitate these social intents. Furthermore, the findings underscore the necessity for additional research to reconcile the functional unit with the established units from other eLCA methodologies. Such an alignment is crucial for enabling a comprehensive evaluation of the impact magnitude of social intents within the entire building context.This work contributes to bridging the existing gap in the assessment of quantifiable environmental impacts versus qualitative intention-based social impacts, paving the way for more informed decision-making and socially sound, sustainable buildings.

Construction sites are among the most dangerous workplaces due to their complex, dynamic, continuously changing work environment. Many existing workplace safety planning techniques rely on two-dimensional drawings and manual expertise. Such efforts are cumbersome as safety plans quickly become outdated as construction work progresses. There has been significant research into automated safety planning, yet no community-wide standard exists for objectively measuring and comparing automated safety assessment efficacy. To address this, an automated performance assessment framework is proposed. It evaluates input solutions regarding newly formalized quantitative soundness, completeness, and spatial correctness indicators. The ground truth of the deadliest hazard falls-from-height is collected through a workshop with domain experts. We validate the proposed framework in a case study, where the performance of our previously developed automated safety planning algorithm is assessed by our new performance assessment framework. The results yield valuable insights into the importance of automated evaluation frameworks that can convince practitioners to invest in human-assisted Prevention through Design and Planning strategies.

The construction industry records more hazards compared to any other sector. Protective equipment, such as guardrail systems, is essential for protecting workers from deadly falls but may quickly become incompliant after installation. Yet, many construction projects do not have the resources to dedicate personnel to perform the inspection as frequently as needed. Therefore, this paper proposes an automated rule-based inspection and compliance-checking system that can assist the responsible personnel in detecting faulty guardrails in live work environments. The classification approach utilizes safety design and mimics the steps of human guardrailing compliance assessment, which enforces simplicity and transparency, allowing the human domain expert to remain in control. Even under scarce data availability, this first-of-a-kind classification approach is reliable and scalable and successfully classifies 21 predefined and 9 validation scenarios of guardrail systems for fall protection.

Life cycle assessment (LCA) is rapidly evolving in the EU and around the world, and it is used to calculate and assess the environmental impact of buildings throughout their life cycle. Many EU countries have decided to add new embodied carbon regulations in their building codes, and thus, the calculation of environmental impact is becoming mandatory. We present a decision support system based on Building Information Modelling (BIM) that provides architects and engineers with streamlined LCA information on highly uncertain designs at an early stage. The system is designed to be extremely simple and easy to comprehend, and it executes LCA calculations fast enough for real-time use. Our key contribution is to elaborate, comprehensively implement, and evaluate the new sustainability opportunity metric (SOM) that we had briefly introduced in our earlier work. Assigned to BIM model components, the metric intends to identify sustainability opportunities and risks by quickly evaluating numerous independent building elements despite early-stage design uncertainty. In this paper, we demonstrate the first fully integrated toolchain and tools prototypes as a plug-in for Revit. We develop the tool to conduct visualisation and usability experiments, and empirically evaluate it on five complex BIM-based high-rise projects.

Sustainability is a major driving force in today’s society as it serves as a guiding principle in decision-making towards a better and sustainable future. In practice, the concept of sustainability has been concretised through the development of the three pillars of sustainability: social, environmental, and economic. It is commonly acknowledged that the social pillar is the least developed and that the pillar needs more streamlined and applicable definitions, frameworks and approaches. Within the building and construction industry, the sustainability of buildings is typically assessed based on building certification systems. The aim of this article is to compare the definitions and approaches to social sustainability in the existing academic literature and prevailing social sustainability-focused building certification systems (i.e., BREEAM, LEED, DGNB, and WELL). This is done through a systematic review of the academic literature using the PRISMA (The Preferred Reporting Items for Systematic Reviews and Meta-Analyses)-framework and an in-depth investigation of the assessment criteria in the building certification systems, focusing on the values assessed rather than benchmark values and assessment methods. The paper concludes that while there is no commonly agreed-upon definition or approach to social sustainability, there is a consensus in parts of the academic literature that social sustainability has an overarching perspective that is comparable to an absolute concept. This absolute approach is not present in the certification systems, so they neither ensure nor improve overarching social sustainability. Instead, they are designed to improve selected social values and contribute to social sustainability by focusing on specific and concretised social values.

The construction industry is among the most hazardous industries, and its continuously changing and complex environment results in a labour-intensive task of planning and preventing hazards. Current manual safety planning procedures cannot keep up with construction progress. This leads to unplanned durations and an increased responsibility for the individual workers to analyse and act accordingly to an emerging situation. This work proposes an automated approach to identifying and measuring the amount of struck-by falling object hazard exposure to construction tasks and their assigned work crews. Additionally, falling objects can originate from activities not foreseen or planned due to planning resolution (e.g. crane lift paths or temporarily impassable access routes). Therefore, it is investigated how to extend the current practices of safety analysis in both the planning and construction stages using building information modelling artificial intelligence and sensor techniques. The proposed strategy is to identify hazard sources and subjects based on their topology and nature in a spatio-temporal analysis. The proposed combinatorial analysis approach is validated in a case study performed on a real construction project in Finland. It yields new insights, which can be necessary for construction sequence decisions and convincing workers to improve their safety behaviour.

We present a modified ground-and-solve approach based on the clingo Answer Set Programming (ASP) system to perform non-monotonic spatial reasoning tasks, Clingo2DSR. Our system is distinct from previous research integrating ASP with space in that it deals with complex real-world data and numerous time steps. Clingo2DSR is composed of (i) an input language defining spatial entities, functions, and relations; (ii) an external geometry database for performing spatial computations and checking spatial constraints; and (iii) a theory-based solving approach coupling symbolic ASP with external sources for sound and fast model search. We demonstrate our system on three real building models, in the context of architectural design, submitted for analyses and queries where spatial components play an important role.

Safety planning is currently a manual and labor-intensive task. As a response, there has been active research on automated safety planning approaches. With the emergence of digital twins and the increased temporal resolution of updates on the status of a construction site, automated approaches for safety analysis will be necessary to exploit this increasing quantity of data. Nevertheless, creating a digital representation of the construction site and performing safety planning is computationally complex and intensive. It is not feasible to re-compute the safety assessment of the entire construction situation from scratch for every change that occurs. This work presents a novel approach to capture incremental localized changes happening in the construction situation, that is, when one or more elements are constructed, but the rest of the site remains unchanged. The changes are captured in a graph-based structure where the affected safety elements can efficiently and rapidly be extracted, facilitating a targeted re-computation. This work also demonstrates other benefits of the graph, such as improved decision support for construction planning.

Over the past few years, the AECO Industry has undergone a shift toward digital transformation, with a growing trend towards adopting innovative technologies such as Digital Twin (DT). DT offers a wide range of applications throughout the building development process. However, some specific factors impede its widespread adoption in the building industry. This study aims to systematically review the available literature on the building project development process from the perspective of DT, with a particular focus on predictive simulations, i.e., co-sims. The review provides a comprehensive overview of drivers and barriers to DT adoption through an analysis of 147 studies between 2013 and 2023. The research identifies seven external and 41 internal drivers, including efficient project management and monitoring, predictive maintenance, and the collection and visualization of real-time data, all of which contribute to improved decision-making processes and reduced operational expenses. Further, the study identifies nine external and 31 internal barriers that impede the adoption of DT in the building development process. These barriers encompass challenges such as a high initial investment cost, a scarcity of a skilled workforce, difficulties in data interoperability, and resistance to change within the organization. A key outcome of the literature review is having identified the opportunity to exploit technologies developed in the automotive sector that enable a seamless integration of specialized simulator models in building development processes, resulting in collaborative simulations. Thus, we propose the concept of a Building Simulation Identity Card (BSIC) to be pursued in future research that would enable stakeholders to address the challenges of collaboration, cooperation, coordination, and communication by creating a common vocabulary to effectively facilitate the adoption of DT in the building's development process.

The construction industry faces significant safety challenges due to dynamic work environments. Automated safety analysis tools offer superior spatial and temporal resolution compared to manual methods, yet industry adoption still needs to be improved. At the same time, construction project scheduling and planning have received much attention in research and industry. However, decision-making in construction scheduling often does not take the impacts of a given plan on safety into account, due to a lack of information and knowledge extraction capabilities. This study aims to bridge the current silo nature of the two domains through a knowledge representation of safety analysis and scheduling information. Leveraging the concepts of Digital Twins, comprehensive automated safety analysis, and knowledge representation, this study focuses on enabling decision-makers to obtain further insight into their domain and, equally important, how decisions in project planning can impact safety planning and vice versa. This work proposes a framework for knowledge extraction, a graph structure for knowledge storage and sharing, and the extraction of query building blocks to transform identified natural language questions into queries that can be used on the proposed graph representation. The queries are tested and interpreted in a case study, revealing appealing knowledge about domain decisions' cross-domain impact.

This paper presents a new approach for supporting renovation designers in exploring the vast landscape of renovation scenarios. The approach integrates renovation scenario sampling (based on a semantic domain model of renovation, called NovaDM), scenario clustering (specifically k-means) in terms of Key Performance Indicator evaluations, and dimensionality reduction (specifically Principal Component Analysis) so that the sampled scenarios and discovered clusters can be visualized in a meaningful way. The approach is empirically evaluated on a large residential building case study in Denmark. Case study results show that the visualization captures and communicates critical high-level information about the "structure" of the enormous, complex underlying renovation design space, in terms of qualitative KPI profiles (e.g. fairly low privacy, very high cost, etc.), thus significantly enhancing renovation decision making.