Understanding mobility patterns
This page is about the applications of machine learning (ML) in the context of understanding mobility patterns. For an overview of mobility models more generally, please see the Wikipedia page on this topic.
Large amounts of geolocated traces are being collected that enable the analysis of mobility patterns. This can be useful for better managing existing as well as planning future transport systems. Machine learning (ML) offers great potential to progress the following areas.
To better understand existing transport systems, ML can be used to detect the structure of a transport network as well as its utilization. In the context of highly congested cities (especially with parked cars), this could, for example, support the discussion for a more equal street space allocation and the adoption of more low carbon mobility, such as walking or riding bicycles.
Furthermore, ML applied to analyze and classify travel patterns can help to better understand urban mobility flows. As human mobility in urban areas follow strong regularities, this understanding constitutes the basis for making short- and long-term predictions of mobility demand.
Next to that, ML can be used to assess the impact of a local context (such as the urban form) on mobility. Building up on this, planning strategies can be derived which support a low carbon transport future.
Background Readings[edit | edit source]
Vehicle and road detection[edit | edit source]
“Fast deep vehicle detection in aerial images (2017)”: An example of how high-resolution images can be used to detect vehicles.
Analysis and Classification of Travel Patterns[edit | edit source]
“Urban Human Mobility Data Mining: An Overview (2016)”: This review provides a great overview of the complete modelling process, starting from finding potential data sets, cleaning and preprocessing data sets, searching for patterns using ML, evaluating models and obtained patterns as well as acting on discovered knowledge. When it comes to finding mobility patterns, the authors also highlight different predictors and their applicability in different contexts.
“Truck traffic monitoring with satellite images (2019)”: An example of how satellite images can be utilised to detect average road traffic.
“Mining smart card data for transit riders' travel patterns (2013)”. An example of how smart card data is used to model travel patterns of transit riders in Beijing.
Impact of urban form on mobility:[edit | edit source]
“Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo (2018)”: An example of how gradient boost decision trees are used to examine the effect of urban form on mobility.
Community[edit | edit source]
Libraries and Tools[edit | edit source]
Data[edit | edit source]
Future Directions[edit | edit source]
References[edit | edit source]
- Creutzig, Felix; Javaid, Aneeque; Soomauroo, Zakia; Lohrey, Steffen; Milojevic-Dupont, Nikola; Ramakrishnan, Anjali; Sethi, Mahendra; Liu, Lijing; Niamir, Leila; d’Amour, Christopher Bren; Weddige, Ulf (2020-11-01). "Fair street space allocation: ethical principles and empirical insights". Transport Reviews. 40 (6): 711–733. doi:10.1080/01441647.2020.1762795. ISSN 0144-1647.
- González, Marta C.; Hidalgo, César A.; Barabási, Albert-László (2008). "Understanding individual human mobility patterns". Nature. 453 (7196): 779–782. doi:10.1038/nature06958. ISSN 1476-4687.
- Sommer, Lars Wilko; Schuchert, Tobias; Beyerer, Jurgen (2017). "Fast Deep Vehicle Detection in Aerial Images". 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). Santa Rosa, CA, USA: IEEE: 311–319. doi:10.1109/WACV.2017.41. ISBN 978-1-5090-4822-9.
- Zhao, Kai; Tarkoma, Sasu; Liu, Siyuan; Vo, Huy (2016). "Urban human mobility data mining: An overview". 2016 IEEE International Conference on Big Data (Big Data). Washington DC,USA: IEEE: 1911–1920. doi:10.1109/BigData.2016.7840811. ISBN 978-1-4673-9005-7.
- Kaack, Lynn H.; Chen, George H.; Morgan, M. Granger (2019-07-17). "Truck Traffic Monitoring with Satellite Images". arXiv:1907.07660 [cs].
- Ma, Xiaolei; Wu, Yao-Jan; Wang, Yinhai; Chen, Feng; Liu, Jianfeng (2013-11-01). "Mining smart card data for transit riders' travel patterns". Transportation Research Part C: Emerging Technologies. 36: 1–12. doi:10.1016/j.trc.2013.07.010. ISSN 0968-090X.
- Ding, Chuan; Cao, Xinyu (Jason); Næss, Petter (2018-04-01). "Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo". Transportation Research Part A: Policy and Practice. 110: 107–117. doi:10.1016/j.tra.2018.02.009. ISSN 0965-8564.