Geo big data for urban analytics and management : challenges and opportunities. Case study : heavy traffic patterns with user-ghenerated data (WAZE)

According to United Nations statistics, 54.6 percent of the world population lived in urban settlements in 2016. Studies show that this global percentage will increase drastically and one in every three people will live in cities of future. Transportation systems are the one of the main pillars of city management. Air pollution derived from transportation systems affects millions of peoples’ quality of life and causes many premature death all around the world. Thus, it is inevitable that there is an emerging and urgent need for better understanding of cities. The main objective of this thesis is to utilize user-generated geo-located big data and make an experimental analysis covering urban analytics and management to detect heavy traffic patterns in Milan city by using a chain of different techniques. Open Transport Map data which contains Milan Municipality roads is used as a base map. Traffic jam information is extracted from WAZE data by applying certain algorithms implemented in python programming language. After pre-processing, WAZE data is snapped onto Milan road network as dynamic segments by using linear referencing method in ArcMap software. Following that, hot spot analysis is performed to find hot spots in Milan city. As a last step hot spots are viewed on Google Earth. It is captured that there are heavy traffic patterns close to important points in Milan city for domestic and international tourists during the summer period. Overall this study shows that user-generated data reflects the city’s heavy traffic patterns. The result of this research is expected to give an idea about Milan city heavy traffic patterns to city scientists for urban transportation planning studies.