IDEAS home Printed from https://ideas.repec.org/h/elg/eechap/21868_6.html
   My bibliography  Save this book chapter

The potential of explainable deep learning for public transport planning

In: Handbook on Artificial Intelligence and Transport

Author

Listed:
  • Wenzhe Sun
  • Jan-Dirk Schmöcker
  • Youxi Lai
  • Koji Fukuda

Abstract

Deep learning has been widely used in transportation studies, especially for prediction tasks. It has been proven powerful in predicting travel demand for a transportation node or a general spatial unit. Recently, graph convolutional networks (GCNs) have drawn much attention with their ability to model complex interactions between spatial units of an area by describing them with graphs. Multi-relational GCNs can be used for cases that consider multiple node features and relations between nodes. These have a variety of applications for public transport planning. To introduce GCNs and their variants to a wider range of audiences, this chapter aims to provide a general and easy-to-follow framework based on several examples. Furthermore, this chapter discusses the potential to explain such black boxes by using Shapley additive explanations (SHAP). SHAP may address the concern that arises among transport planners and operators regarding model interpretability.

Suggested Citation

  • Wenzhe Sun & Jan-Dirk Schmöcker & Youxi Lai & Koji Fukuda, 2023. "The potential of explainable deep learning for public transport planning," Chapters, in: Hussein Dia (ed.), Handbook on Artificial Intelligence and Transport, chapter 6, pages 155-175, Edward Elgar Publishing.
    • Handle: RePEc:elg:eechap:21868_6
    as

    Download full text from publisher

    File URL: https://www.elgaronline.com/doi/10.4337/9781803929545.00013
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:elg:eechap:21868_6. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Darrel McCalla (email available below). General contact details of provider: http://www.e-elgar.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.