| Summary: | New technologies applied to transportation services and the shifting to sustainable modes of transportation turned bike-sharing systems more relevant in the urban mobility scenario. This thesis aims to understand the spatiotemporal station and trip activity patterns in Lisbon bike-sharing system in 2018 and understand trip rate changes in Lisbon bike-sharing system in 2019 and 2020 compared to 2018. By analyzing the spatiotemporal distribution of trips through stations and the weather factors combined with the usage rate throughout the years, it is possible to improve and make the system more suitable to the users’ demand. In this research work, we used large open datasets made available by the Lisbon City Hall, that are deployed by using the CRISP-DM. Our major work contribution was the development of a data analytics process for urban data, specifically bike-sharing data, that helps to understand how people move in the city using bikes. Moreover, we aimed to understand how mobility patterns change over time and the impact of pandemic events. Major findings show that most bike-sharing happens on weekdays, with no precipitation and mild temperature. Additionally, there was an exponential increase in the number of trips, cut short by COVID-19 pandemics. The current approach can be applied to any city with digital data available.
|
|---|