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

Aike Steentoft, Bu-Sung Lee, Markus Schl Pfer

Diskussionsschriften from Universitaet Bern, Departement Volkswirtschaft - CRED

Abstract: 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.

Keywords: mobility; Bayesian deep learning; smart cities; transportation system planning (search for similar items in EconPapers)
JEL-codes: C45 R41 (search for similar items in EconPapers)
Date: 2022-05
New Economics Papers: this item is included in nep-big, nep-cmp, nep-tre and nep-ure
References: Add references at CitEc
Citations:

Downloads: (external link)
https://repec.vwiit.ch/cred/CREDResearchPaper36.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rdv:wpaper:credresearchpaper36

Access Statistics for this paper

More papers in Diskussionsschriften from Universitaet Bern, Departement Volkswirtschaft - CRED Contact information at EDIRC.
Bibliographic data for series maintained by Franz Koelliker ().