Published 2024-10-28
Keywords
- Emerging technologies,
- Artificial Intelligence (AI),
- Internet of Things (IoT),
- Geotechnical engineering,
- Transformative shifts
How to Cite
Abstract
In this keynote lecture, the pressing challenges facing today's geotechnical engineering, particularly regarding the unpredictability of soil and rock properties, are explored. The multifaceted nature of uncertainty and complexity in geotechnical solutions is examined, with emphasis placed on the need for precision, realism, economy, and sustainability. Emerging technologies such as Artificial Intelligence (AI), the Internet of Things (IoT), Digital Twins, and Metaverse are leveraged, showcasing their transformative potential in addressing these challenges. Through a comprehensive review of recent studies and real-life case studies, the benefits and disadvantages of these technologies in geotechnical applications are highlighted. A central focus is placed on the introduction of a novel Deep Learning-Physics-Informed Neural Network (PINN) approach for predicting the axial capacity of drilled shafts, which integrates empirical data with geotechnical principles. The findings underscore the promise of emerging technologies to revolutionize geotechnical engineering and usher in a new era of precision and sustainability.
References
- Phoon, K. K., & Kulhawy, F. H. (1999). Characterization of geotechnical variability. Canadian Geotechnical Journal, 36(4), 612-624.
- Lacasse, S., & Nadim, F. (1996). Uncertainties in characterising soil properties. Geotechnical Engineering, 120(12), 1872-1897.
- Griffiths, D. V., & Fenton, G. A. (2004). Probabilistic methods for geotechnical engineering. Springer Science & Business Media.
- Zhang, R., et al. (2019). Machine learning in geotechnical engineering: Applications, challenges, and opportunities. Tunneling and Underground Space Technology, 95, 103160.
- Soga, K., Schooling, J., & Houlsby, G. (2015). Sensors and monitoring for infrastructure: A review of recent advances. Journal of Civil Structural Health Monitoring, 5(2), 111-128.
- Watson, A., & Butler, L. (2020). Application of digital twins in the infrastructure sector. Proceedings of the Institution of Civil Engineers - Smart Infrastructure and Construction, 173(2), 80-88.
- Dawood, N., et al. (2021). Building a digital twin for the construction industry: Challenges and opportunities. Automation in Construction, 122, 103517.
- M.E. Al-Atroush, and Tuğçe Başer (2024). A Novel Deep Learning-Physics-Informed Neural Network Approach for Predicting Ultimate Capacity of Drilled Shafts. Submitted to Géotechnique Letters.