Modelling spatial patterns using graph convolutional networks

Di Zhu, Yu Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations


The understanding of geographical reality is a process of data representation and pattern discovery. Former studies mainly adopted continuous-field models to represent spatial variables and to investigate the underlying spatial continuity/heterogeneity in a regular spatial domain. In this article, we introduce a more generalized model based on graph convolutional neural networks that can capture the complex parameters of spatial patterns underlying graph-structured spatial data, which generally contain both Euclidean spatial information and non-Euclidean feature information. A trainable site-selection framework is proposed to demonstrate the feasibility of our model in geographic decision problems.

Original languageEnglish (US)
Title of host publication10th International Conference on Geographic Information Science, GIScience 2018
EditorsAmy L. Griffin, Stephan Winter, Monika Sester
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
ISBN (Print)9783959770835
StatePublished - Aug 1 2018
Externally publishedYes
Event10th International Conference on Geographic Information Science, GIScience 2018 - Melbourne, Australia
Duration: Aug 28 2018Aug 31 2018

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
ISSN (Print)1868-8969


Other10th International Conference on Geographic Information Science, GIScience 2018

Bibliographical note

Funding Information:
Funding This research was supported by the National Key Research and Development Program of China [Grant Number: 2017YFB0503602] and the National Natural Science Foundation of China [Grant Number: 41625003].

Publisher Copyright:
© Di Zhu and Yu Liu.


  • Big geo-data
  • Deep neural networks
  • Graph convolution
  • Spatial pattern
  • Urban configuration


Dive into the research topics of 'Modelling spatial patterns using graph convolutional networks'. Together they form a unique fingerprint.

Cite this