Abstract
In the current era of big data, vast amounts are generated rapidly from diverse, rich data sources. Embedded within these big data sets is valuable information and knowledge that can be uncovered using big data science techniques. Transportation data and meteorological data are prime examples of such big data. This paper presents a big data science solution for transportation analytics incorporating meteorological data. Specifically, we analyse meteorological data to examine the impact of various weather conditions (e.g., fog, rain, snow) on the on-time performance of public transit. Evaluation using real-life data collected from the Canadian city of Winnipeg demonstrates the practicality and effectiveness of our big data science solution in analysing bus delays caused by different meteorological conditions.