SHORT-TERM TRAVEL-TIME PREDICTION MODELING AUGMENTED WITH RADAR-BASED PRECIPITATION PREDICTIONS AND SCALING OF SAME

摘要

A framework for estimating short-term travel times for one or more roadway links of a transportation network infrastructure models traffic speed predictions from collected traffic speed data and augments these predictions with precipitation predictions for the links being modeled. The framework employs strategies for scaling these augmented models for larger segments and areas of a roadway to minimize processing and training time. The travel time estimates generated by the framework are utilized to provide accurate routing information and recommendations to motorists, and to conduct more efficient traffic monitoring and infrastructure planning and maintenance activities.