Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research toward the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of simi...

Full description

Saved in:
Bibliographic Details
Main Authors: Haohua Zheng, Jianchen Zhang, Heying Li, Guangxia Wang, Jianzhong Guo, Jiayao Wang
Format: Article
Language:English
Published: MDPI AG 2024-08-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/13/9/300
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260781471367168
author Haohua Zheng
Jianchen Zhang
Heying Li
Guangxia Wang
Jianzhong Guo
Jiayao Wang
author_facet Haohua Zheng
Jianchen Zhang
Heying Li
Guangxia Wang
Jianzhong Guo
Jiayao Wang
author_sort Haohua Zheng
collection DOAJ
description Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research toward the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where the feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another for extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we use a set of metrics considering both quantitative and qualitative aspects of the road network. On road types with similar sample sizes, the HAN model outperforms other models in both transductive and inductive tasks. Its accuracy (ACC) is higher by 1.62% and 0.67%, and its F1-score is higher by 1.43% and 0.81%, respectively. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.
format Article
id doaj-art-7c8b785d339e41d3a339d065eebcb6da
institution OA Journals
issn 2220-9964
language English
publishDate 2024-08-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-7c8b785d339e41d3a339d065eebcb6da2025-08-20T01:55:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-08-0113930010.3390/ijgi13090300Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural NetworkHaohua Zheng0Jianchen Zhang1Heying Li2Guangxia Wang3Jianzhong Guo4Jiayao Wang5College of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng 475004, ChinaSelecting road networks in cartographic generalization has consistently posed formidable challenges, driving research toward the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where the feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another for extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we use a set of metrics considering both quantitative and qualitative aspects of the road network. On road types with similar sample sizes, the HAN model outperforms other models in both transductive and inductive tasks. Its accuracy (ACC) is higher by 1.62% and 0.67%, and its F1-score is higher by 1.43% and 0.81%, respectively. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.https://www.mdpi.com/2220-9964/13/9/300cartographic generalizationroad network selectionHeterogeneous Graph Attention Networkmeta-path
spellingShingle Haohua Zheng
Jianchen Zhang
Heying Li
Guangxia Wang
Jianzhong Guo
Jiayao Wang
Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
ISPRS International Journal of Geo-Information
cartographic generalization
road network selection
Heterogeneous Graph Attention Network
meta-path
title Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
title_full Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
title_fullStr Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
title_full_unstemmed Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
title_short Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network
title_sort road network intelligent selection method based on heterogeneous graph attention neural network
topic cartographic generalization
road network selection
Heterogeneous Graph Attention Network
meta-path
url https://www.mdpi.com/2220-9964/13/9/300
work_keys_str_mv AT haohuazheng roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork
AT jianchenzhang roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork
AT heyingli roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork
AT guangxiawang roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork
AT jianzhongguo roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork
AT jiayaowang roadnetworkintelligentselectionmethodbasedonheterogeneousgraphattentionneuralnetwork