This review demonstrates that GenAI has substantial potential to support intelligent, sustainable, and data-driven civil engineering practices while emphasizing the need for human expertise and responsible AI implementation.
Abstract
Generative Artificial Intelligence (GenAI) is emerging as a transformative technology in civil engineering, offering advanced computational capabilities that enhance engineering design, project planning, infrastructure management, and decision-making. Unlike traditional artificial intelligence, GenAI can generate text, technical documentation, designs, and analytical outputs, thereby improving productivity and reducing the time required for complex engineering tasks. This review provides a comprehensive overview of recent advancements in GenAI and its applications across key civil engineering domains, including structural engineering, construction management, Building Information Modeling (BIM), transportation engineering, geotechnical engineering, and infrastructure monitoring. The study synthesizes findings from recent literature to examine the benefits, challenges, research gaps, and future trends associated with GenAI adoption. The review highlights the significant role of GenAI in design optimization, project scheduling, predictive maintenance, risk assessment, technical documentation, and smart infrastructure development. It also discusses critical challenges such as data quality, model reliability, explainability, cybersecurity, ethical concerns, and professional accountability. Overall, the review demonstrates that GenAI has substantial potential to support intelligent, sustainable, and data-driven civil engineering practices while emphasizing the need for human expertise and responsible AI implementation.
The rapid transition from Industry 4.0 to Industry 5.0 has significantly increased the complexity of manufacturing systems while accelerating the development and deployment of smart and sustainable materials in advanced industrial applications. These emerging materials require intelligent decision-making approaches that integrate data, advanced analytics, optimization, digital twins, and human expertise throughout their design, production, monitoring, and lifecycle management. Although artificial intelligence, machine learning, digital twins, and mathematical optimization have independently advanced intelligent manufacturing, their isolated application often limits adaptability, explainability, and resilience. This study presents a systematic literature review of Decision Intelligence (DI) in collaborative intelligent manufacturing following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, synthesizing evidence from 140 peer-reviewed publications. The review comprehensively examines the evolution of Decision Intelligence, core enabling technologies, layered architectures, industrial applications, human-centered decision-making, implementation challenges, and emerging research trends. The findings indicate that effective Decision Intelligence requires the seamless integration of artificial intelligence, optimization, digital twins, knowledge graphs, explainable AI, and Human-in-the-Loop AI within a unified decision ecosystem that combines computational intelligence with human judgment. The proposed framework and research roadmap provide valuable theoretical insights and practical guidance for developing resilient, explainable, and human-centric Decision Intelligence systems that support the realization of Industry 5.0 manufacturing for smart and sustainable materials.
H. Mural, Mahbub E. Khoda, Abdul Halim et al.· Journal of Sustainable Smart...· 0 citations
The swift evolution of technologies like artificial intelligence (AI), the Internet of Things (IoT), Building Information Modeling (BIM), cloud computing, and sensor technology has dramatically reshaped how society manages modern civil infrastructure. Among these innovations, the Digital Twin (DT) has emerged as a standout technology: a dynamic virtual representation of physical infrastructure that continuously exchanges real-time data with its physical counterpart. By merging AI with DT, infrastructure systems can engage in smart monitoring, predictive maintenance, fault diagnosis, performance optimization, and even autonomous decision-making throughout their lifecycle. This powerful combination boosts operational efficiency, cuts down maintenance costs, enhances safety, and promotes sustainable infrastructure development. This study reviews the integration of DT technology with AI for smart infrastructure applications. It explores the core concepts, enabling technologies, architecture, and lifecycle of AI-driven DT, while showcasing their applications across buildings, bridges, transportation networks, highways, railways, water distribution systems, and smart cities. Additionally, it discusses the latest advancements in machine learning, deep learning, computer vision, generative AI, large language models (LLMs), and physics-informed AI that elevate the capabilities of DT for infrastructure monitoring and management. It also critically analyzes existing literature to pinpoint current achievements, implementation strategies, and technological progress across various civil engineering fields. The review highlights several key research challenges, such as data interoperability, cybersecurity, computational complexity, scalability, standardization, data quality, and model validation. It also explores exciting future research opportunities in areas like explainable AI, autonomous DT, edge computing, 6G communication, quantum computing, and sustainable infrastructure management.
Mahadeva M., M. C. S.· Journal of Recent Activities...· 0 citations
Artificial intelligence (AI) is increasingly being incorporated into engineering practices, transforming the design, construction, operation, and maintenance of systems. The present study explores recent peer-reviewed literature on three interwoven aspects of this transformation: ethical governance, societal change, and environmental sustainability. The review covers new governance instruments such as the European Union Artificial Intelligence Act, ISO/IEC 42001, and the NIST AI Risk Management Framework, as well as explainable-AI (XAI) methods that engineers are increasingly using to explain to regulators, clients, and the public why their safety-critical decisions are made. Also, it addresses the implications of AI on engineering labor markets, professional education and decision-making power, including the differential exposure of high-skill cognitive tasks to automation, and the need for new skills. Furthermore, it considers the dual nature of AI in terms of its contribution to resource optimization, predictive maintenance and integration of renewable energy, and its contribution to an increasing computational carbon and water footprint that can offset these benefits, a tension that is sometimes referred to as the Jevons paradox. The review suggests an integrated framework of responsible AI engineering that connects the three elements of responsible AI: technical explainability, institutional accountability, and life-cycle environmental auditing. The review concludes that long-term acceptability and acceptance of AI in engineering practice will not only be determined by the performance of the models themselves, but also by the ability of the engineering discipline to govern AI transparently, fairly and within planetary limits.
Large AI models are reshaping intelligent manufacturing from isolated automation toward knowledge-intensive, model-assisted production systems. Yet their industrial value depends not on model scale alone, but on how language, vision, code, sensor data, engineering knowledge, and feedback mechanisms are integrated into deployable manufacturing workflows. This review examines recent progress in large AI models for intelligent manufacturing, covering model architectures, adaptation strategies, system integration, and applications across product development, production processes, equipment maintenance, and manufacturing services. A lifecycle-based framework is used to organize the literature and distinguish model capabilities from the data resources, retrieval mechanisms, simulation and optimization tools, digital twins, edge-cloud infrastructure, and human validation required for deployment. Current evidence suggests that large models show more reliable value in bounded, information-rich tasks, whereas safety-critical control and production-scale autonomy remain insufficiently validated. The review further summarizes challenges in data quality, domain adaptation, reliability, interpretability, latency, cybersecurity, cost, benchmarking, and responsibility allocation. By linking application scenarios, system-level enablers, and evidence maturity, this review provides a structured perspective for assessing the practical value of large AI models in manufacturing.
Baotong Chen, Lu Dai, Chuangjian Wang et al.· IEEE Access· 0 citations
AI based sustainable architectures is an emerging interdisciplinary approach that combines sustainable design principles, modern information systems, financial risk management and artificial intelligence, solving modern environmental and economic challenges. The study examines the potential of AI technologies to improve the design optimization, resource efficiency, and life cycle sustainability in the fields of architecture and construction. AI helps in informed decision-making by leveraging data-driven modeling, predictive analytics, and intelligent automation, which minimizes environmental effects and enhances building performance in areas such as material selection, energy management, and structural planning. The study also explores the potential of smart systems, the Internet of Things (IoT) and digital twin technologies in the further development of sustainable construction methods. These technologies enable monitoring, predictive maintenance and adaptive control of building systems in real-time, which leads to lower operating costs and better energy efficiency. Furthermore, the study emphasizes that lifecycle aspects such as maintenance, deconstruction, and material re-use are crucial, contributing to the principles of circular economy in the built environment. In addition, the conversation includes topics of financial risk management and green consumerism. AI can improve risk assessments by analyzing credit, market, and operational risks in real-time, as well as integrating environmental, social, and governance (ESG) considerations into financial decision-making. Moreover, AI has the potential to shape consumer behavior by facilitating personalized sustainability communication and improving green marketing efforts, which foster sustainable consumption. Additionally, AI plays a role in influencing consumer behavior by enabling personalized sustainability communication and enhancing green marketing strategies, promoting sustainable consumption.
Abdul Hamid, S. Ahmed· Journal of Computer Science...· 0 citations
Artificial intelligence (AI) is transforming smart manufacturing by enabling intelligent automation, data-driven decisions, and stronger collaboration between humans and manufacturing systems. The widespread adoption of collaborative robots, the industrial internet of things, and cyber-physical systems is driving demand for manufacturing environments that are safer, more flexible, and more efficient. Despite AI’s broad application in manufacturing, few studies have combined adaptive safety and intelligent task allocation within a single human-centered framework. This review offers a comprehensive look at AI applications that support these two complementary functions. Literature from Scopus, Web of Science, IEEE Xplore, ScienceDirect, SpringerLink, and the ACM Digital Library was systematically reviewed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and analysed thematically. The findings show that machine learning, deep learning, computer vision, reinforcement learning, knowledge-driven approaches, digital twins, and explainable AI contribute to improvements in predictive maintenance, quality inspection, production scheduling, adaptive safety, and collaborative decision-making. That said, challenges remain - such as interoperability, explainability, limited access to high-quality manufacturing data, industrial validation, and integrating multiple AI technologies. This review gives researchers and practitioners a holistic perspective and highlights integrated, human-centered AI frameworks as key enablers of resilient, efficient, and sustainable Industry 5.0 manufacturing systems.
Zaliha Baso, N. Yadav, P. Faujdar· Cureus Journal of Computer S...· 0 citations