Winter Road Friction Estimations via Multi-Source Road Weather Data—A Case Study of Alberta, Canada

Road friction has long been recognized as one of the most effective winter road maintenance (WRM) performance measures. It allows WRM personnel to make more informed decisions improve their services and helps users trip-related decisions. In this paper, a machine-learning-based methodological framework was developed model using inputs from mobile weather information systems (RWIS) that collect spatially continuous data grip. This study also attempts estimate stationary RWIS are installed far each other, thereby leaving large areas unmonitored. To fill in spatial gaps, kriging interpolator create map. Slippery risk levels were classified provide an overview conditions via warning The proposed method evaluated with selected highway segment Alberta, Canada. Results show models herein highly accurate (93.3%) estimating identifying dangerous segments color-coded Given its high performance, potential for large-scale implementation facilitate efficient while improving safety mobility traveling public.