Interpretable Prediction of Urban Mobility Flows with Deep Neural Networks as Gaussian Processes

Steentoft, Aike; Lee, Bu-Sung; Schläpfer, Markus (May 2022). Interpretable Prediction of Urban Mobility Flows with Deep Neural Networks as Gaussian Processes (CRED Research Paper 36). Bern: CRED - Center for Regional Economic Development

Preview

Text CRED-Research_Paper_Nr._36.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (5MB) | Preview

The ability to understand and predict the flows of people in cities is crucial for the
planning of transportation systems and other urban infrastructures. Deep-learning
approaches are powerful since they can capture non-linear relations between
geographic features and the resulting mobility flow from a given origin location to a
destination location. However, existing methods cannot quantify the uncertainty of
the predictions, limiting their interpretability and thus their use for practical
applications in urban infrastructure planning. To that end, we propose a Bayesian
deep-learning approach that formulates deep neural networks as Gaussian processes
and integrates automatic variable selection. Our method provides uncertainty
estimates for the predicted origin-destination flows while also allowing to identify
the most critical geographic features that drive the mobility patterns. The developed
machine learning approach is applied to large-scale taxi trip data from New York
City.

Interest & Impact

Downloads

97 since deposited on 09 May 2022
20 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item