A Comparative Evaluation of Machine-Learning Models for Road Surface Roughness Forecasting in ITSs

The forecasting of road surface conditions is a pivotal component for intelligent transportation systems, in terms of supporting maintenance planning, safety and mobility management. The increasing availability of large-scale monitoring data, collected from passenger vehicle fleets, enables the development of data-driven forecasting approaches. However, systematic comparisons between classical time-series models and machine-learning methods in this context remain limited. The proposed benchmarking framework evaluates direct road surface roughness forecasts at 1-, 7-, 14-, 30-, and 90-day horizons using multi-year vehicle-derived data collected across heterogeneous road segments. Daily roughness indicators are derived from raw measurements and modeled following a consistent, segment-wise experimental protocol. The proposed analysis involves the evaluation of multiple machine-learning regressors including Ridge, Random Forest and Gradient Boosting which are trained on lagged observations and rolling statistics. Performance of the models is assessed using two error metrics: unweighted and uncertainty-aware weighted. Findings indicate significant variations in predictive accuracy and robustness across models and segments, emphasizing the influence of feature-based learning strategies and data-quality weighting. The research provides a scalable and transparent methodology for evaluating forecasting models on vehicle-based road monitoring data, contributing practical guidance for the deployment of artificial intelligence in Intelligent Transport Systems (ITSs).