Digital Intelligence for the Built Environment: Data-Driven Design and Construction for Sustainable and Resilient Futures

The built environment faces increasing pressures from climate change, resource limitations, and rapid urbanisation. Simultaneously, projects now generate and utilise large volumes of data, from high-resolution environmental datasets and monitoring systems to detailed BIM models and records of construction processes. Computer simulation and data science can transform this information into digital intelligence, supporting decisions that enhance energy efficiency, reduce carbon emissions, adapt to climate risks, and strengthen social and economic resilience. However, the use of simulation and data-driven methods across design and construction remains inconsistent. Many projects apply performance modelling or data analytics at isolated stages, with limited feedback between design, construction, and in-use performance. Model assumptions are often not transparent, and monitoring data are seldom integrated into models to update predictions or inform adaptations. Consequently, the potential of digital approaches to foster sustainable and resilient outcomes across the building and infrastructure life cycle is not yet fully realised. Thus, there is a need to investigate how digital intelligence, rooted in computer simulation and data science, can support the design and delivery of sustainable and resilient built environment projects. This special issue welcomes contributions which demonstrate how data-driven approaches and computational models can lead to measurable improvements in environmental performance, climate adaptation, resource efficiency, circularity, safety, and social outcomes. systematically embedded in design and construction to support sustainable and resilient futures. The central problem is that, while powerful simulation tools, sensing technologies and analytical methods exist, they are often applied in fragmented ways, with weak links between predictions, realised performance and long-term adaptation. Project teams may struggle with tool interoperability, data quality, model calibration, uncertainty treatment and the communication of results to decision makers. This Topic seeks contributions that address these challenges by developing, demonstrating or critically assessing digital workflows that connect simulation, data science and sustainability or resilience objectives and extend these capabilities to the analysis of social outcomes using emerging digital methods. Recent advances in machine learning, optimisation, digital twins, cloud computing, open data standards and high-performance computing enable large design space exploration, hybrid physics-based and data-driven models, and continuous model updating using real-world data. By gathering studies that make use of these advances in transparent and robust ways, the Topic aims to provide practical and conceptual guidance on how digital intelligence can support climate-responsive design, low-carbon construction, risk-informed planning and the integration of social considerations within adaptive management of the built environment.This Research Topic is open to contributions in which computer simulation and/or data science play a central role and are clearly linked to sustainable or resilient design and construction outcomes and, where relevant, associated social impacts. Studies may address any project phase, from strategic planning and early design through detailed design, construction, commissioning, operation, maintenance and adaptation. All types of built assets are in scope, including buildings, infrastructure and urban systems. Both methodological and applied work are welcome, provided that the approach and its relevance to practice are clearly explained. Themes of interest include, but are not limited to:• Integrated workflows that link BIM, parametric or generative design environments with performance simulation and sustainability or resilience assessments• Digital twins and cyber-physical systems that combine simulation with monitored data to support low-carbon, climate-resilient and adaptive operation of assets and associated social impact.• Data-driven modelling and prediction of energy use, carbon emissions, occupant comfort, climate risk, structural reliability or service performance using statistical or machine learning methods• Simulation-based optimisation of energy, embodied and operational carbon, water, materials, cost, constructability, safety or whole life performance, including multi-objective approaches• Use of monitoring, sensing and long-term datasets to calibrate, validate and update models, and to close the gap between predicted and actual performance• Methods for representing and managing uncertainty, risk and cascading impacts in data-driven design and construction decision making, including scenario analysis for climate change and natural hazards• Computational and data-enabled approaches supporting industrialised, modular, offsite and automated construction aimed at resource efficiency, quality and safety• Digital methods to support circularity, deconstruction planning, material passports and whole life cycle assessments for sustainable and resilient projects• Visualisation, interactive interfaces and human-in-the-loop decision support that make complex simulation and data outputs accessible to designers, engineers, contractors, clients and communities• Case studies documenting successful, partial or challenging implementations of digital intelligence in real projects, including lessons learned, organisational change and barriers to wider adoption with attention to social outcomes where applicable. We invite a range of manuscript types consistent with the journal’s policies, including Original Research articles, Methods papers, Systematic Reviews, Mini Reviews, Hypothesis and Theory articles, Perspectives, Brief Research Reports, and Opinion articles that align with the Topic. Multidisciplinary contributions that bring together expertise in built environment disciplines, computer simulation and data science are particularly encouraged. All submissions should clearly describe the computational or data-driven approach used, explain its novelty and limitations, and discuss its implications for advancing sustainable and resilient design and construction in the built environment. Topic editors: Pavithra Rathnasiri, Tharindu KARUNARATNE Source: https://www.frontiersin.org/research-topics/77044/digital-intelligence-for-the-built-environment-data-driven-design-and-construction-for-sustainable-and-resilient-futures