Saleh Seyedzadeh

This systematic review examines how digital technologies enable circular economy (CE) transitions across sectors and value chains. Analysing 266 peer-reviewed publications (2016–2025), we develop a comprehensive taxonomy of digital enablers—including IoT, AI, blockchain, cloud computing, additive manufacturing, and digital platforms—and map their applications to circular strategies such as reuse, remanufacturing, and recycling. Our findings reveal that data-driven technologies dominate CE implementation, with 89% of studies involving data collection, storage, analysis, or sharing functions. IoT emerges as the foundational technology for real-time tracking and monitoring, while AI and big data analytics optimise circular processes and predict maintenance needs. Blockchain ensures traceability and trust in circular supply chains, and cloud computing provides scalable infrastructure for collaboration. Manufacturing (41%) and construction (15.5%) are the most studied sectors, with strong European research leadership reflecting policy drivers such as Digital Product Passports. We identify three impact types: enabling (process optimisation), disruptive (business model innovation), and facilitating (ecosystem collaboration). Key barriers include technical complexity, organisational resistance, high implementation costs, and regulatory gaps. The review concludes with recommendations for integrated, multi-stakeholder approaches to realise a digitally enabled circular economy.

Buildings account for 40% of global energy consumption and 36% of CO2 emissions, making retrofitting existing structures a critical climate action pathway. Here, we present a transformative computational framework that could revolutionise national-scale retrofit decision-making by combining advanced machine learning with distributed optimisation. Our framework, tested on England's 21.5 million homes using the Domestic Energy Performance Certificate dataset, demonstrates efficiency improvements 84% better than current policy approaches at substantially lower costs. By integrating gradient-boosted decision trees with novel multi-objective optimisation algorithms across distributed computing infrastructure, we enable previously impossible large-scale retrofit planning. The system evaluates over 323 million potential retrofitting interventions, including glazing, boiler, wall, and roof improvements, identifying optimal combinations that maximise energy savings while minimising costs. When applied to a national policy scenario equivalent to the UK's Minimum Energy Efficiency Standards, our equivalent abatement approach achieves the same energy efficiency while matching the performance achieved in the preceding study with a smaller decision space. Results represent potential savings of billions while more effectively advancing Sustainable Development Goals 7, 11, and 13. This methodology demonstrates how computational intelligence can transform climate policy implementation, with immediate applications for energy efficiency programmes worldwide and broader implications for resource-optimised urban planning.

This paper proposes a non-invasive, data-driven methodology for monitoring and optimising machine utilisation in manufacturing environments. By analysing high-resolution power consumption data, the system automatically classifies machine states (off, idling, and working, and segments operational periods into discrete production events. Unsupervised learning techniques enable the identification of production patterns, product typologies, and anomalies, supporting improvements in operational efficiency and quality control. The approach also estimates energy consumption and cost using time-of-use tariffs, offering insights into both performance and sustainability. Experimental evaluations across multiple industrial settings demonstrate the method’s robustness, with high agreement with production records and significant potential for reducing idle time, improving scheduling, and enhancing resource allocation. This work presents a scalable and interpretable analytics framework to support data-driven decision-making in modern manufacturing operations.

Predicting risk of future dementia is essential for primary prevention strategies, particularly in the era of novel immunotherapies. However, few studies have developed population-level prediction models using existing routine healthcare data. In this longitudinal retrospective cohort study, we predicted incident dementia using primary and secondary care health records at 5, 10 and 13 years in 144 113 Scottish older adults who were dementia-free prior to 1st April 2009. Gradient-boosting (XGBoost) prediction models were trained on two feature subsets: data-driven (using all 171 extracted variables) and clinically supervised (22 curated variables). We used a random-stratified internal validation set to rank top predictors in each model, assessing performance stratified by age and socioeconomic deprivation. Predictions were stratified into 10 equally sized risk deciles and ranked by response rate. Over 13 years of follow-up, 11 143 (8%) patients developed dementia. The data-driven models achieved marginally better precision-recall area-under-the-curve scores of 0.18, 0.26 and 0.30 compared to clinically supervised models with scores of 0.17, 0.27 and 0.29 for incident dementia at 5, 10 and 13 years, respectively. The clinically supervised model achieved comparable specificity 0.88 [95% confidence interval (CI) 0.87–0.88] and sensitivity (0.55, 95% CI 0.53–0.57) to the data-driven model for prediction at 13 years. The most important model features were age, deprivation and frailty, measured by a modified electronic frailty index excluding known cognitive deficits. Model precision was consistent across socioeconomic deprivation quintiles but lower in younger-onset (<70 years) dementia cases. At 13 years, dementia was diagnosed in 32% of the population classified as highest risk with 40% of individuals in this group below the age of 80. Personalized estimates of future dementia risk from routinely collected healthcare data could influence risk factor modification and help to target brain imaging and novel immunotherapies in selected individuals with pre-symptomatic disease.

This book provides in-depth results and case studies in innovation from actual work undertaken in collaboration with industry partners in Architecture, Engineering, and Construction (AEC). Scientific advances and innovative technologies in the sector are key to shaping the changes emerging as a result of Industry 4.0. Mainstream Building Information Management (BIM) is seen as a vehicle for addressing issues such as industry fragmentation, value-driven solutions, decision-making, client engagement, and design/process flow; however, advanced simulation, computer vision, Internet of Things (IoT), blockchain, machine learning, deep learning, and linked data all provide immense opportunities for dealing with these challenges and can provide evidenced-based innovative solutions not seen before. These technologies are perceived as the “true” enablers of future practice, but only recently has the AEC sector recognised terms such as “golden key” and “golden thread” as part of BIM processes and workflows. This book builds on the success of a number of initiatives and projects by the authors, which include seminal findings from the literature, research and development, and practice-based solutions produced for industry. It presents these findings through real projects and case studies developed by the authors and reports on how these technologies made a real-world impact. The chapters and cases in the book are developed around these overarching themes: • BIM and AEC Design and Optimisation: Application of Artificial Intelligence in Design • BIM and XR as Advanced Visualisation and Simulation Tools • Design Informatics and Advancements in BIM Authoring • Green Building Assessment: Emerging Design Support Tools • Computer Vision and Image Processing for Expediting Project Management and Operations • Blockchain, Big Data, and IoT for Facilitated Project Management • BIM Strategies and Leveraged Solutions This book is a timely and relevant synthesis of a number of cogent subjects underpinning the paradigm shift needed for the AEC industry and is essential reading for all involved in the sector. It is particularly suited for use in Masters-level programs in Architecture, Engineering, and Construction.

Overview/Challenge: This chapter investigates the complex procedures and processes involved in monitoring and assessment. This presents high-level challenges, focussing in particular on concrete joints and cracks. It presents a case for undertaking these tasks in a much more efficient, logical, and informed way. Design/Methodology/Approach: Extant literature was used to identify a number of technological solutions. Factors and variables were then collated and mapped into a proof-of-concept prototype for 4D automated concrete joint layout planning. A new two-phased process was deployed to cover both the technical and theoretical aspects. Findings: This prototype highlighted the data exchange structures underpinning this solution, including the underpinning logic, developed Autodesk Revit plug-in, and automated concreting scheduling system. This endeavour expedites and optimises the design, planning, and delivery stages of concrete pouring. Originality/Future Vision: This work presented a novel and bespoke integrated platform for structural design and construction integration. This brings together the capabilities of different software applications through a 4D BIM use case. Future opportunities include the incorporation of Machine Learning (ML) and Artificial Intelligence (AI) to further support/train data.

Overview/Challenge: This chapter evaluates five major themes considered integral to the delivery of costing structures underpinning IPD. It challenges current thinking, conventions, and available tools in the market, arguing that things need to change in order to better support the integration of BIM, ABC, and EVM into IPD cost practices. Design/Methodology/Approach: Literature was evaluated to ascertain the applicability and validity of assumptions. This was aligned to real-life settings, using an amalgamation of exploratory case study research and experiment research. Findings: A framework was developed to address the identified challenges. This integrated EVM, ABC, and IPD to determine participants’ risk/reward sharing ratio. A case study was presented to demonstrate findings, noting the successful integration of BIM with IPD to inform decision-making. Originality/Future Vision: The EVM-web grid can act as a ‘smart tool’ to provide recommendations and optimal corrective actions. The use of openBIM could also be used to improve the management of AEC digital data, especially through future 4D/5D BIM platforms.

Overview/Challenge: This chapter highlights the challenges of securing effective design collaboration between different parties – in particular, the confluence of architectural and structural design integration. It proffers the need for a system that integrates architectural and structural models to automate and facilitate intelligent structural model generation and optimisation. Design/Methodology/Approach: A four-stage approach was designed to resolve integration challenges. This focuses on tall building design structural optimisation using a Building Information Modelling (BIM)–based platform. Findings: A prototype was developed to integrate various actors involved in the design process. This actively brings two disciplines together for one common purpose, thereby enabling automation and synergy between computational analysis procedures and architectural parametric data-driven design. Originality/Future Vision: Integration and collaborative design relates directly with the concepts of Industry 4.0; however, AEC will need to embrace new skillsets in order to fully leverage these benefits.

Overview/Challenge: This chapter reflects on the need to streamline and optimise processes in order to deliver better value. In doing so, it evaluates manufacturing and the concept of Design for Manufacture and Assembly (DfMA). The critical challenges presented here embody the integration of sub-assemblies and component-based systems with prefabrication construction processes. Design/Methodology/Approach: An explicit mixed-method approach was adopted to identify the main issues, priorities, and opportunities. A case study approach was used to develop a working prototype for discussion. Findings: A four-phase prototype was developed and presented as an exemplar solution. This introduced the utilisation of a BIM Objects Library and core components (specially selected for this case study) based on a two-bedroom house. This component-based BIM library followed DfMA principles, thereby enabling optimisation (to support assembly and disassembly). Originality/Future Vision: Several advanced opportunities are available for exploitation; however, in order to maximise these opportunities, AEC should engage digital specialists and design teams conversant in DfMA to transition away from traditional working practices to those more aligned with manufacturing.