Artificial Intelligence (AI) is reshaping structural health monitoring (SHM) by enabling data-driven maintenance and safety management of critical infrastructure over its entire life cycle. Bridges, buildings, tunnels, pipelines, dams, and other assets are exposed to long-term deterioration processes—such as corrosion, fatigue, concrete degradation, settlement, scour, and climate-induced stressors—as well as everyday operational loads from traffic and wind. Traditional inspection and monitoring practices often struggle to track gradual damage evolution and to translate heterogeneous sensing data into timely maintenance actions. AI, including machine learning and deep learning, offers powerful capabilities for pattern recognition, anomaly detection, and predictive modeling based on vibration, strain, image, acoustic, and environmental measurements. By focusing on long-term performance and life-cycle management rather than only immediate post-event response, AI-enabled SHM can become a cornerstone of safer, more sustainable, and cost-effective infrastructure systems.
The goal of this Research Topic is to advance AI-driven SHM methodologies that directly support infrastructure maintenance and safety management throughout the life cycle, beyond the narrow context of seismic emergency response. We seek contributions that tackle damage and degradation mechanisms such as corrosion, fatigue, cracking, leakage, settlement, scour, and climate-driven deterioration, while treating seismic loads as just one of several possible hazards.
A central emphasis is placed on the AI techniques themselves: self- and semi-supervised learning to leverage large unlabeled datasets; physics-informed and hybrid mechanistic–data-driven models that embed structural behavior; graph neural networks and transformers for complex structural topologies and time-dependent signals; and multimodal fusion of vibration, wave, image, and environmental data. We particularly welcome studies that link AI-based indicators to condition indices, remaining service life, life-cycle cost, maintenance prioritization, and risk-informed decision-making. By bringing together researchers and practitioners from structural engineering, computer science, and asset management, this Research Topic aims to promote reproducible, scalable, and trustworthy AI solutions for routine and strategic infrastructure stewardship.
This Research Topic focuses on AI applications in SHM that enhance maintenance, inspection planning, and safety assurance for civil infrastructure over its full service life. Target systems include buildings, bridges, tunnels, pipelines, dams, offshore and coastal structures, and other critical assets subjected to long-term deterioration and operational loads. Relevant themes include, but are not limited to:
1. AI-based detection, localization, and quantification of corrosion, fatigue, cracking, leakage, settlement, and scour;
2. Vision- and UAV-based inspection for surface and near-surface damage;
3. Digital twins and surrogate models for condition assessment, prognosis, and maintenance planning;
4. Multimodal data fusion, domain adaptation, and transfer learning across structures and environments;
5. Uncertainty quantification, reliability assessment, and trustworthy / explainable AI for decision support.
We welcome original research articles, reviews, methods papers, perspectives, brief research reports, data and benchmark reports, and well-documented case studies from real assets or experimental campaigns.
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.
Keywords: Structural Health Monitoring, Damage Detection, Machine Learning, Deep Learning, Computer Vision, Physics-Informed Neural Networks, Digital Twins, Vibration- and Wave-Based Methods, Multimodal Data Fusion, Post-Event Rapid Assessment
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.
