Simelane, Melusi SRampersad, Ashiel2024-11-212024-11-212024-07http://hdl.handle.net/10204/13836Road maintenance is a crucial process for pavement management systems. South African local roads are in critical condition, and their management is not at optimum level which is evident by their poor condition. The aim of the paper is to provide a machine-learning algorithm to assist road authorities to provide maintenance strategies. The objective of the study was to determine the most effective condition index for pavement management of flexible pavements. This is achieved by conducting descriptive and inferential statistical analysis of two case studies (Low volume roads and High volume roads). Statistical analysis indicated that the visual condition index (VCI has inconsistencies compared to the surface and deduct point pavement condition index (CISURF & CIPAVE) found in TMH 22. Four machine learning models were created, the model with a potential for deployment was a Gradient Boosting Classifier (GBC) model. The GBC model had an accuracy of 74 %, 85 % and 93 % in relation to the VCI, CISURF & CIPAVE respectively. The CISURF & CIPAVE was hence identified as the most effective index for use in flexible pavementsFulltextenRoad maintenanceSouth African local roadsPavement management systemsLow volume roadsConference Presentation