USE OF AI & MACHINE LEARNING IN CIVIL ENGINEERING

Abstract

Artificial Intelligence (AI) and Machine Learning (ML) are increasingly being adopted in Civil Engineering to
support prediction, automation, monitoring, optimization, and data-driven decision-making. This review examines
applications across structural engineering and structural health monitoring, construction management and safety,
transportation and pavement engineering, concrete and construction materials, geotechnical engineering, water
resources, Building Information Modeling (BIM), and earthquake engineering. The literature shows that supervised
learning methods such as artificial neural networks, support vector machines, decision trees, random forests, and
ensemble models are widely used for regression and classification, while deep learning methods such as
convolutional neural networks, recurrent neural networks, and long short-term memory networks are increasingly
used for images, sensor signals, and time-series data. Recent work also highlights transformer models, physicsinformed machine learning, digital twins, and multimodal systems. AI/ML can improve prediction, automate
repetitive inspection and monitoring tasks, and support engineering decisions; however, practical adoption is
constrained by data quality, limited field datasets, generalization, interpretability, uncertainty quantification,
computational requirements, and integration with established engineering workflows. The review identifies research
gaps and argues that trustworthy AI should complement rather than replace engineering principles, standards,
validation, and professional judgment.