EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Physics-Informed Digital Twin for Climate-Induced Degradation Prediction in Aging Coastal Bridges

Rhys Thornton, Eloise Mercer

Civil Engineering Science and Technology · 2026

DOI: 10.51903/19t45v40 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Civil Engineering Science and Technology, 2026. Verfasst von Rhys Thornton und 1 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Climate change has accelerated the deterioration of aging coastal bridges by increasing chloride exposure and environmental variability, creating significant challenges for long-term Structural Health Monitoring. While Digital Twin technology enables real-time infrastructure monitoring, existing approaches often lack explicit representation of the physical mechanisms governing structural degradation. This study aims to develop a Physics-Informed Digital Twin framework by integrating Physics-Informed Neural Networks (PINNs) with Internet of Things (IoT)-based sensing for long-term prediction of climate-induced bridge deterioration. The proposed framework combines real-time sensor synchronization, chloride diffusion physics, and deep learning to improve predictive accuracy and physical consistency. The model achieved a coefficient of determination (R²) of 0.98, a Mean Absolute Error (MAE) of 0.041, a Root Mean Square Error (RMSE) of 0.056, and a Mean Absolute Percentage Error (MAPE) of 2.84%, while accurately simulating structural degradation over a 50-year service life under multiple coastal microclimate scenarios. The novelty of this study lies in the integration of physics-informed learning, chloride transport mechanisms, and Digital Twin technology into a unified predictive framework for coastal bridge deterioration assessment. This framework extends conventional Digital Twin systems from monitoring to physics-guided prognostic analysis, providing a reliable tool for predictive maintenance and infrastructure resilience. The findings demonstrate that incorporating governing physical laws into Digital Twin architectures substantially improves the robustness, accuracy, and engineering reliability of long-term degradation prediction for aging coastal bridges.

Zitieren

APA

Thornton, R., & Mercer, E. (2026). Physics-Informed Digital Twin for Climate-Induced Degradation Prediction in Aging Coastal Bridges. Civil Engineering Science and Technology. https://doi.org/10.51903/19t45v40

Vancouver

Thornton R, Mercer E. Physics-Informed Digital Twin for Climate-Induced Degradation Prediction in Aging Coastal Bridges. Civil Engineering Science and Technology. 2026. doi:10.51903/19t45v40

BibTeX
@article{Thornton2026,
  author = {Thornton, Rhys and Mercer, Eloise},
  title = {Physics-Informed Digital Twin for Climate-Induced Degradation Prediction in Aging Coastal Bridges},
  journal = {Civil Engineering Science and Technology},
  year = {2026},
  doi = {10.51903/19t45v40}
}
Kostenlos starten →