Babawarun, T.Ngwangwa, H.2025-10-232025-10-232025http://hdl.handle.net/2263/104890Papers presented virtually at the 43rd International Southern African Transport Conference on 07 - 10 July 2025.Effective road maintenance strategies require accurate condition assessment, prediction, optimisation and decision-making. Traditional road surface monitoring methods, such as visual inspections and the use of ultrasonic sensors, are often costly, labour-intensive, and prone to human error. With the rapid advancement of advancement of digital technologies such as artificial intelligence (AI), particularly machine learning (ML), and deep learning (DL) have revolutionized road damage detection by offering scalable, cost-effective solutions for road surface condition assessment. The review explores recent developments in AI-driven road damage detection, focusing on machine learning techniques such as Artificial Neural networks (ANNs), deep learning approaches including Convolutional Neural Networks (CNN). It concluded that AI-powered road monitoring systems offer significant advantages over traditional methods in terms of accuracy, efficiency, scalability and predictive capability. However, challenges such as data dependency, model generalization, and real-time implementation remains an area for future research.11 pagesPDFSouthern African Transport Conference 2025Road infrastructure managementRoad maintenance strategiesArtificial Neural Network (ANN)Article