AI- and ML-Driven Innovations in Civil Engineering Infrastructure and Construction

Abstract

The rapid advancement of Artificial Intelligence (AI) and Machine Learning (ML) has significantly transformed civil engineering infrastructure and construction practices. This study investigates AI- and ML-driven innovations across key domains, including structural design optimization, construction planning, predictive maintenance, and project management. A quantitative analysis was conducted using datasets comprising over 10,000 construction project records, sensor data from 250 smart infrastructure systems, and historical maintenance logs spanning 15 years. ML models such as Random Forest, Support Vector Machines, and Deep Neural Networks were evaluated for performance. Results indicate that AI-based predictive models achieved an average accuracy improvement of 22–30% over traditional analytical methods in structural health monitoring. Construction schedule optimization using ML reduced project delays by 18%, while cost overruns were minimized by approximately 25% through AI-enabled risk prediction. Furthermore, predictive maintenance frameworks demonstrated a 35% reduction in unexpected structural failures and extended asset lifespan by nearly 20%. The integration of AI-driven automation also improved resource utilization efficiency by 27%, contributing to sustainable construction practices. These numerical findings confirm that AI and ML not only enhance decision-making accuracy but also improve economic efficiency, safety, and resilience in civil engineering infrastructure. The study highlights the transformative potential of intelligent systems in shaping the future of smart, sustainable, and data-driven construction ecosystems.