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 language||English (US)|
|Title of host publication||10th International Conference on Geographic Information Science, GIScience 2018|
|Editors||Amy L. Griffin, Stephan Winter, Monika Sester|
|Publisher||Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing|
|State||Published - Aug 1 2018|
|Event||10th International Conference on Geographic Information Science, GIScience 2018 - Melbourne, Australia|
Duration: Aug 28 2018 → Aug 31 2018
|Name||Leibniz International Proceedings in Informatics, LIPIcs|
|Other||10th International Conference on Geographic Information Science, GIScience 2018|
|Period||8/28/18 → 8/31/18|
Bibliographical noteFunding 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].
© Di Zhu and Yu Liu.
- Big geo-data
- Deep neural networks
- Graph convolution
- Spatial pattern
- Urban configuration