AI Foundation Models and Knowledge Engineering for Smart Construction and Infrastructure Systems

Recent advances in large foundation models promise to automate complex tasks in architecture, engineering, and construction (AEC). These models offer powerful generative and analytical capabilities that can transform design workflows, construction planning, and infrastructure monitoring. However, generic AI systems often fall short when facing domain-specific constraints, uncertain conditions, or safety-critical decisions in the AEC domain. Knowledge engineering, the process of extracting, structuring, and embedding expert domain knowledge, offers a pathway to bridge this gap. By encoding the rules, heuristics, and constraints that govern AEC practices, knowledge engineering enables the development of AI systems that are not only more accurate, but also aligned with real-world requirements and professional expertise. When combined with explainable AI techniques and human-in-the-loop (HITL) oversight, this integration can enable more transparent, context-aware, and trustworthy AI systems tailored to AEC applications.



This Research Topic aims to explore how knowledge engineering and foundational AI models, such as large generative language or vision models, can be safely adapted for construction and infrastructure systems. As these powerful models are increasingly applied to design, construction, and management of built environments, embedding structured domain knowledge is essential to ensure technical relevance, regulatory compliance, and operational safety. We seek to bring together research that integrates explicit domain knowledge, human-in-the-loop (HITL) frameworks, explainable AI, and governance strategies to improve the transparency, accountability, and trustworthiness of AI-driven workflows in AEC. By focusing on the synergy between foundational models and civil engineering expertise, this collection highlights pathways for developing AI systems that support sustainable, resilient, and intelligent construction and infrastructure solutions.



We welcome original research, systematic reviews, case studies, and theoretical perspectives on the following themes (but are not limited to):



- Embedding civil engineering knowledge into foundational AI models



- Explainable and safe generative AI for infrastructure design and management



- Human-in-the-loop frameworks for digital twins and BIM



- AI-based structural health monitoring and predictive maintenance



- Ethical, legal, and governance frameworks for AI in AEC applications



Submissions should address practical challenges in construction and infrastructure systems, and demonstrate how foundational AI can be adapted to serve the goals of safety, resilience, and sustainability. We especially encourage interdisciplinary contributions that integrate perspectives from civil engineering, computer science, data science, architecture, and public policy.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review

Keywords: oundation models, knowledge engineering, Generative AI, digital twins, large language model, human-in-the-loop, resilient infrastructure, smart construction, information management

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.