Automatic road network selection method considering functional semantic features of roads with graph convolutional networks

Abstract

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people’s needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography.

Keywords:

• Road network selection
• graph convolutional network
• functional features
• map generalization
• POI data

Acknowledgments

The authors gratefully acknowledge the comments from the editor and the reviewers.

Disclosure statement

The authors reported no potential conflict of interest.

Data and codes availability statement

The data and codes that support the findings of this study are available on ‘figshare.com’, with the identifier at the public link: https://doi.org/10.6084/m9.figshare.23654001.

Additional information

Funding

This study was supported by the Funds of the National Key Research and Development Program of China (No. 2022YFB3904203), the National Natural Science Foundation of China (No. 42271462, 42171441, and 42271485), the Science and Technology Innovation Program of Hunan Province (No. 2024AQ2026) and the Hunan Provincial Natural Science Foundation of China (No. 2024JJ8343, 2021JJ40727).

Notes on contributors

Jianbo Tang

Jianbo Tang is an associate professor at Central South University. His research interests include trajectory data analysis, geographical scene modeling, and spatiotemporal data mining. He contributed to the conceptualization, methodology, writing (review & editing), and funding acquisition.

Min Deng

Min Deng is a professor at Central South University. His current research interests include spatiotemporal data mining and map generalization. He contributed to the conceptualization, methodology, resources, and funding acquisition.

Ju Peng

Ju Peng is a Ph.D. candidate at Central South University. Her research interests include map generalization, trajectory data mining, and spatiotemporal data mining. She contributed to the conceptualization, data processing, experiment analysis, visualization, and writing (original draft, review & editing).

Huimin Liu

Huimin Liu is an associate professor at Central South University. Her research interests include map generalization and spatiotemporal data mining. She contributed to data processing, data collection, visualization, and funding acquisition.

Xuexi Yang

Xuexi Yang is an Associate Professor at Central South University. His research interests include knowledge graph, and spatiotemporal data mining. He contributed to data collection, visualization, and funding acquisition.

Xueying Chen

Xueying Chen is a postgraduate student at Central South University, Changsha. Her research interest includes map generalization and trajectory data analysis. She contributed to data collection, experiment analysis, and visualization.