In the rapidly evolving landscape of civil engineering, a groundbreaking review published in the journal *Applied Sciences* (translated from the Latin as “Applied Sciences”) is shedding light on how artificial intelligence (AI) and machine learning (ML) are transforming the industry. Led by Ali Bahadori-Jahromi from the Department of Civil Engineering and Built Environment at the University of West London, the research offers a comprehensive look at how these technologies are enhancing predictive accuracy, decision-making, and sustainability across various domains.
The study, which analyzed peer-reviewed publications from the past decade, reveals that AI and ML are not just buzzwords but are already making significant inroads into civil engineering practices. From structural health monitoring to geotechnical analysis, transportation systems, water management, and sustainable construction, these technologies are proving their mettle. “The integration of AI and ML has revolutionized civil engineering, enhancing predictive accuracy, decision-making, and sustainability,” Bahadori-Jahromi notes, highlighting the transformative potential of these tools.
One of the key contributions of the review is the introduction of a novel taxonomy that classifies AI/ML approaches by civil engineering domain, learning paradigm, and adoption maturity. This taxonomy is designed to guide future development and ensure that these technologies are applied in the most effective and efficient ways possible. The study also identifies several key applications, including pavement condition assessment, slope stability prediction, traffic flow forecasting, smart water management, and flood forecasting. Techniques such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Support Vector Machines (SVMs), and hybrid physics-informed neural networks (PINNs) are at the forefront of these advancements.
However, the review is not without its caveats. It highlights several challenges that need to be addressed, including limited high-quality datasets, the absence of AI provisions in design codes, integration barriers with IoT-based infrastructure, and computational complexity. “While explainable AI tools like SHAP and LIME improve interpretability, their practical feasibility in safety-critical contexts remains constrained,” Bahadori-Jahromi explains, pointing to the need for further research and development in this area.
Ethical considerations are also a significant focus of the study. The review addresses issues such as bias in training datasets and regulatory compliance, emphasizing the importance of ethical AI practices in civil engineering. “Ethical considerations, including bias in training datasets and regulatory compliance, are also addressed,” the study notes, underscoring the need for responsible and transparent use of AI and ML technologies.
Looking ahead, the study identifies several promising directions for future research. These include federated learning for data privacy, transfer learning for data-scarce regions, digital twins, and adherence to FAIR data principles. “This study underscores AI as a complementary tool, not a replacement, for traditional methods, fostering a data-driven, resilient, and sustainable built environment through interdisciplinary collaboration and transparent, explainable systems,” Bahadori-Jahromi concludes, highlighting the potential for AI and ML to complement rather than replace existing practices.
For the energy sector, the implications of this research are profound. As civil engineering practices become more efficient and sustainable, the energy sector stands to benefit from improved infrastructure management, reduced costs, and enhanced environmental performance. The integration of AI and ML in civil engineering could lead to more resilient and sustainable energy infrastructure, ultimately contributing to a more sustainable future.
In conclusion, the review by Bahadori-Jahromi and his team offers a compelling vision of how AI and ML can transform civil engineering. By addressing the challenges and opportunities presented by these technologies, the study provides a roadmap for future development and underscores the importance of interdisciplinary collaboration and ethical considerations in the pursuit of a data-driven, resilient, and sustainable built environment. Published in the journal *Applied Sciences*, this research is a significant step forward in the ongoing evolution of civil engineering practices.