Recently, with the development of computational capabilities and data availability, artificial intelligence (AI), including machine learning and deep learning, has gained tremendous attention in various fields of engineering. AI models have the capability to solve complex problems starting directly from the data by capturing the underlying physics without the need for developing analytical or mechanical models. In line with this, AI-enhanced solutions in civil engineering are emerging at a rapid pace with promising results. However, despite their high capabilities, such models are generally considered “black boxes,” which limits their practical applications in civil engineering. Hence, the interpretation of such models is essentially important to increase their practical application.
This Research Topic is dedicated to the innovative applications of AI (e.g., machine learning, including supervised and unsupervised ML, deep learning, fuzzy logic, and optimization algorithms) to solve complex problems in the wide realm of civil engineering with a particular focus on the use of Explainable AI (XAI) for practical applicability of such models. This Research Topic welcomes AI-enhanced cutting-edge studies on a wide range of applications in civil engineering, including structural engineering, earthquake engineering, wind engineering, geotechnical engineering, sustainability, transportation and traffic engineering, environmental engineering, and water engineering.
The topics of interest include, but are not limited to:
• Applications of data-driven AI techniques to solve complex problems in various fields of civil engineering;
• Machine learning and deep learning for performance prediction and failure mode identifications;
• Multi-objective optimization techniques for material and structural optimization;
• AI-aided smart-city, sustainability, and circular economy studies;
• AI-enhanced fragility and risk assessment of civil infrastructure, structural and community resilience, structural health monitoring, and damage detection;
• Development of practical tools, such as graphical user interface (GUI)-based tools for practical implementations of AI-based models;
• Explainability and interpretations of AI models;
• Reliability evaluation of AI-based models;
• Supervised, unsupervised, and reinforcement learning.
Recently, with the development of computational capabilities and data availability, artificial intelligence (AI), including machine learning and deep learning, has gained tremendous attention in various fields of engineering. AI models have the capability to solve complex problems starting directly from the data by capturing the underlying physics without the need for developing analytical or mechanical models. In line with this, AI-enhanced solutions in civil engineering are emerging at a rapid pace with promising results. However, despite their high capabilities, such models are generally considered “black boxes,” which limits their practical applications in civil engineering. Hence, the interpretation of such models is essentially important to increase their practical application.
This Research Topic is dedicated to the innovative applications of AI (e.g., machine learning, including supervised and unsupervised ML, deep learning, fuzzy logic, and optimization algorithms) to solve complex problems in the wide realm of civil engineering with a particular focus on the use of Explainable AI (XAI) for practical applicability of such models. This Research Topic welcomes AI-enhanced cutting-edge studies on a wide range of applications in civil engineering, including structural engineering, earthquake engineering, wind engineering, geotechnical engineering, sustainability, transportation and traffic engineering, environmental engineering, and water engineering.
The topics of interest include, but are not limited to:
• Applications of data-driven AI techniques to solve complex problems in various fields of civil engineering;
• Machine learning and deep learning for performance prediction and failure mode identifications;
• Multi-objective optimization techniques for material and structural optimization;
• AI-aided smart-city, sustainability, and circular economy studies;
• AI-enhanced fragility and risk assessment of civil infrastructure, structural and community resilience, structural health monitoring, and damage detection;
• Development of practical tools, such as graphical user interface (GUI)-based tools for practical implementations of AI-based models;
• Explainability and interpretations of AI models;
• Reliability evaluation of AI-based models;
• Supervised, unsupervised, and reinforcement learning.