Geospatial Analysis and Modeling

Analysis and modeling of urban dynamics

3706.1 - Mapping similarities in temporal parking occupancy behavior based on city-wide parking meter data

Monday, July 3
4:10 PM - 4:30 PM
Location: Maryland A

Background and motivation
The shortage of parking spaces in many cities is a relevant problem in today’s world. Drivers often need to circle around city blocks wasting time and gas until they find a free parking space. The provision of maps with typical parking space occupancy patterns has the potential to reduce the severity of this problem, as these maps would help drivers avoid the most crowded roads at certain times. Also, this information is important to policymakers since they can enact parking price changes based on these patterns. Studies show that dynamic parking price adaptations based on parking demand can have a positive impact on the parking situation.
Parking occupancy in a particular road typically demonstrates recurrent temporal patterns of the day and of the week, which also reveals similarities to several other roads within the dataset. Therefore, by clustering, temporal similarities among roads can be identified and only the typical parking patterns need to be stored or transmitted to navigation systems.

Data set
In our study, we analyzed parking meter data from 176meters with the same pricing regulation in Hannover, Germany over a one-year period. Every parking meter sells parking tickets for all parking spaces in the adjacent parking lane. Our data set contains a record for every parking ticket consisting of timestamp of payment, parking meter ID, duration of validity, and ticket price. In total, more than one million parking tickets were analyzed for this study.

Methodology
First, intensive data cleansing is applied to filter parking meters with irregular usage patterns. Meters with time gaps or drastic changes in ticket sales, or with a very low total number of tickets, are identified and excluded for further analysis.
The occupancy of every parking lane is then calculated by accumulation of all parking tickets valid at a specific time instance.
Hierarchical clustering is computed based on a least-squares similarity measure of the average weekly patterns, limited to workdays, using the complete linkage method. The optimal cluster number is obtained by utilizing both the Davies-Bouldin and Silhouette Indices as cluster validation techniques to represent the intra- and inter-cluster relationships among parking meters within the dataset.
Finally, the location of the parking meters is evaluated regarding their cluster assignment and illustrated in a map.

Results and conclusion
Data cleansing revealed several irregularities in ticket sales over a one-year period. For example, several parking meters exhibited ticket sale behavior with sudden decreases or increases to unexpected amounts. Physical barriers such as road construction can be assumed to have contributed to the drastic ticket sale changes. After filtering these anomalies, the clustering of the average parking occupancy weekly pattern for the remaining 117 parking meters leaded to three clusters. Averaging the occupancies over all cluster members shows that the parking behavior follows distinct patterns with highest occupancy either in the morning, evening or constant occupancy throughout the day. Most interestingly, the locations of parking meter clusters, computed only based on temporal similarity, also show clear spatial region distinctions from other clusters.
In conclusion, clustering of parking meter data leads to distinct temporal parking behavior for different roads that also exhibit spatial similarities. These results can be used to provide parking maps indicating parking areas with similar temporal parking usage at low data storage requirements. Future work will investigate the relationship of land use and specific spatio-temporal parking patterns.

Fabian Bock

Research assistant
Leibniz University Hannover

Fabian Bock is a research assistant at the Institute of Cartography and Geoinformatics at Leibniz University Hannover since 2014 . He is member of the research training group SocialCars, funded by the German Research Fundation (DFG). The focus of his research lies in the automated generation of parking maps based on crowd-sensing.

Presentation(s):

Send Email for Fabian Bock

Karen Xia

Columbia University in the City of New York

Karen Xia is a third-year Bachelors student studying Computer Science and Statistics at Columbia University in the City of New York, in New York, U.S.A. During her stay in Hannover, Germany, Ms. Xia conducted parking occupancy and parking availability research jointly with the SocialCars Research Group and the University of Hannover. In this research project, she analyzed a previously untouched, large parking meter dataset consisting of over 16 million data points.

Presentation(s):

Send Email for Karen Xia

Monika Sester

Leibniz University Hannover

-

Presentation(s):

Send Email for Monika Sester

Send Email for Xiaobai Angela Yao


Assets

3706.1 - Mapping similarities in temporal parking occupancy behavior based on city-wide parking meter data

Handout

Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Mapping similarities in temporal parking occupancy behavior based on city-wide parking meter data